├── LICENSE ├── README.md ├── RL_with_Action_Representation ├── .gitkeep ├── HyAR │ ├── .gitkeep │ ├── HyAR_RL │ │ ├── main_embedding_direction_catch_ddpg.py │ │ ├── main_embedding_direction_catch_td3.py │ │ ├── main_embedding_goal_ddpg.py │ │ ├── main_embedding_goal_td3.py │ │ ├── main_embedding_hard_goal_ddpg.py │ │ ├── main_embedding_hard_goal_td3.py │ │ ├── main_embedding_hard_move_ddpg.py │ │ ├── main_embedding_hard_move_td3.py │ │ ├── main_embedding_platform_ddpg.py │ │ ├── main_embedding_platform_td3.py │ │ ├── main_embedding_simple_move_ddpg.py │ │ ├── main_embedding_simple_move_td3.py │ │ └── utils.py │ ├── README.md │ ├── Raw_RL │ │ ├── main_direction_catch_ddpg.py │ │ ├── main_direction_catch_hhqn.py │ │ ├── main_direction_catch_hhqn_td3.py │ │ ├── main_direction_catch_hppo.py │ │ ├── main_direction_catch_pdqn.py │ │ ├── main_direction_catch_pdqn_td3.py │ │ ├── main_direction_catch_td3.py │ │ ├── main_goal_ddpg.py │ │ ├── main_goal_hhqn.py │ │ ├── main_goal_hhqn_td3.py │ │ ├── main_goal_hppo.py │ │ ├── main_goal_pdqn.py │ │ ├── main_goal_pdqn_td3.py │ │ ├── main_goal_td3.py │ │ ├── main_hard_goal_ddpg.py │ │ ├── main_hard_goal_hhqn.py │ │ ├── main_hard_goal_hhqn_td3.py │ │ ├── main_hard_goal_hppo.py │ │ ├── main_hard_goal_pdqn.py │ │ ├── main_hard_goal_pdqn_td3.py │ │ ├── main_hard_goal_td3.py │ │ ├── main_hard_move_ddpg.py │ │ ├── main_hard_move_hhqn.py │ │ ├── main_hard_move_hhqn_td3.py │ │ ├── main_hard_move_hppo.py │ │ ├── main_hard_move_pdqn.py │ │ ├── main_hard_move_pdqn_td3.py │ │ ├── main_hard_move_td3.py │ │ ├── main_platform_ddpg.py │ │ ├── main_platform_hhqn.py │ │ ├── main_platform_hhqn_td3.py │ │ ├── main_platform_hppo.py │ │ ├── main_platform_pdqn.py │ │ ├── main_platform_pdqn_td3.py │ │ ├── main_platform_td3.py │ │ ├── main_simple_move_ddpg.py │ │ ├── main_simple_move_hhqn.py │ │ ├── main_simple_move_hhqn_td3.py │ │ ├── main_simple_move_hppo.py │ │ ├── main_simple_move_pdqn.py │ │ ├── main_simple_move_pdqn_td3.py │ │ ├── main_simple_move_td3.py │ │ └── utils.py │ ├── agents │ │ ├── P_DDPG.py │ │ ├── P_DDPG_relable.py │ │ ├── P_TD3.py │ │ ├── P_TD3_relable.py │ │ ├── agent.py │ │ ├── basis │ │ │ ├── __init__.py │ │ │ ├── basis.py │ │ │ ├── fourier_basis.py │ │ │ ├── polynomial_basis.py │ │ │ ├── scaled_basis.py │ │ │ └── simple_basis.py │ │ ├── hhqn.py │ │ ├── hhqn_td3.py │ │ ├── hppo.py │ │ ├── hppo_noshare.py │ │ ├── memory │ │ │ ├── __init__.py │ │ │ └── memory.py │ │ ├── pdqn.py │ │ ├── pdqn_MPE.py │ │ ├── pdqn_MPE_4_direction.py │ │ ├── pdqn_MPE_direction_catch.py │ │ ├── pdqn_hard_goal.py │ │ ├── pdqn_hard_goal_td3.py │ │ ├── pdqn_td3.py │ │ ├── pdqn_td3_MPE.py │ │ ├── run_plot_opr.py │ │ └── utils │ │ │ ├── __init__.py │ │ │ ├── noise.py │ │ │ ├── ppo_utils.py │ │ │ └── utils.py │ ├── assets │ │ └── HyAR_concept.png │ ├── common │ │ ├── __init__.py │ │ ├── goal_domain.py │ │ ├── platform_domain.py │ │ ├── soccer_domain.py │ │ └── wrappers.py │ ├── embedding │ │ ├── ActionRepresentation_vae.py │ │ └── Utils │ │ │ ├── Basis.py │ │ │ ├── Critic.py │ │ │ ├── Policy.py │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ ├── Basis.cpython-37.pyc │ │ │ ├── __init__.cpython-37.pyc │ │ │ └── utils.cpython-37.pyc │ │ │ └── utils.py │ ├── gym-goal-master │ │ ├── .gitignore │ │ ├── LICENSE │ │ ├── README.md │ │ ├── gym_goal │ │ │ ├── __init__.py │ │ │ └── envs │ │ │ │ ├── __init__.py │ │ │ │ ├── config.py │ │ │ │ ├── goal_env.py │ │ │ │ └── util.py │ │ ├── img │ │ │ └── goal_domain.png │ │ └── setup.py │ ├── gym-platform-master │ │ ├── .gitignore │ │ ├── LICENSE.md │ │ ├── README.md │ │ ├── gym_platform │ │ │ ├── __init__.py │ │ │ └── envs │ │ │ │ ├── __init__.py │ │ │ │ ├── assets │ │ │ │ ├── background.png │ │ │ │ ├── background_white.png │ │ │ │ ├── enemy.png │ │ │ │ ├── platform.png │ │ │ │ ├── platform_v3.png │ │ │ │ └── player.png │ │ │ │ └── platform_env.py │ │ ├── img │ │ │ └── platform_domain.png │ │ └── setup.py │ └── multiagent │ │ ├── __init__.py │ │ ├── core.py │ │ ├── environment.py │ │ ├── multi_discrete.py │ │ ├── policy.py │ │ ├── rendering.py │ │ ├── scenario.py │ │ └── scenarios │ │ ├── __init__.py │ │ ├── hard_catch.py │ │ ├── hard_catch_v1.py │ │ ├── simple.py │ │ ├── simple_adversary.py │ │ ├── simple_attack.py │ │ ├── simple_catch.py │ │ ├── simple_crypto.py │ │ ├── simple_grab.py │ │ ├── simple_move.py │ │ ├── simple_move_4_direction.py │ │ ├── simple_move_4_direction_v1.py │ │ ├── simple_move_direction.py │ │ ├── simple_push.py │ │ ├── simple_reference.py │ │ ├── simple_speaker_listener.py │ │ ├── simple_spread.py │ │ ├── simple_tag.py │ │ └── simple_world_comm.py └── README.md ├── RL_with_Environment_Representation ├── .gitkeep ├── PAnDR │ ├── .gitkeep │ ├── README.md │ ├── assets │ │ └── PAnDR_concept.png │ ├── env_utils.py │ ├── main_train.py │ ├── myant │ │ ├── myant.egg-info │ │ │ ├── PKG-INFO │ │ │ ├── SOURCES.txt │ │ │ ├── dependency_links.txt │ │ │ ├── requires.txt │ │ │ └── top_level.txt │ │ ├── myant │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ └── __init__.cpython-37.pyc │ │ │ ├── envs │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-37.pyc │ │ │ │ │ └── myant.cpython-37.pyc │ │ │ │ └── myant.py │ │ │ └── utils.py │ │ └── setup.py │ ├── myspaceship │ │ ├── myspaceship.egg-info │ │ │ ├── PKG-INFO │ │ │ ├── SOURCES.txt │ │ │ ├── dependency_links.txt │ │ │ ├── requires.txt │ │ │ └── top_level.txt │ │ ├── myspaceship │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ └── __init__.cpython-37.pyc │ │ │ └── envs │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-37.pyc │ │ │ │ └── myspaceship.cpython-37.pyc │ │ │ │ └── myspaceship.py │ │ └── setup.py │ ├── myswimmer │ │ ├── myswimmer.egg-info │ │ │ ├── PKG-INFO │ │ │ ├── SOURCES.txt │ │ │ ├── dependency_links.txt │ │ │ ├── requires.txt │ │ │ └── top_level.txt │ │ ├── myswimmer │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ └── __init__.cpython-37.pyc │ │ │ ├── envs │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-37.pyc │ │ │ │ │ └── myswimmer.cpython-37.pyc │ │ │ │ └── myswimmer.py │ │ │ └── utils.py │ │ └── setup.py │ ├── pandr_arguments.py │ ├── pandr_storage.py │ ├── pandr_utils.py │ ├── pdvf_networks.py │ ├── ppo │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-37.pyc │ │ │ ├── arguments.cpython-37.pyc │ │ │ ├── distributions.cpython-37.pyc │ │ │ ├── envs.cpython-37.pyc │ │ │ ├── evaluation.cpython-37.pyc │ │ │ ├── model.cpython-37.pyc │ │ │ ├── storage.cpython-37.pyc │ │ │ └── utils.cpython-37.pyc │ │ ├── algo │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-37.pyc │ │ │ │ └── ppo.cpython-37.pyc │ │ │ └── ppo.py │ │ ├── arguments.py │ │ ├── distributions.py │ │ ├── envs.py │ │ ├── eval_main.py │ │ ├── evaluation.py │ │ ├── model.py │ │ ├── ppo_main.py │ │ ├── storage.py │ │ └── utils.py │ └── train_utils.py ├── README.md └── ccm │ ├── README.md │ ├── assets │ ├── ccm_framework.png │ └── contrastive_context_encoder.png │ ├── configs │ ├── __pycache__ │ │ └── default.cpython-36.pyc │ ├── ant-dir.json │ ├── ant-goal.json │ ├── cheetah-damping.json │ ├── cheetah-dir.json │ ├── cheetah-mass.json │ ├── cheetah-vel.json │ ├── default.py │ ├── fetch-pickplace.json │ ├── fetch-slide.json │ ├── hopper_rand_params.json │ ├── humanoid-dir.json │ ├── ml1.json │ ├── ml10.json │ ├── ml45.json │ ├── point-robot.json │ ├── reacher-goal.json │ ├── sparse-point-robot.json │ ├── walker-vel-sparse.json │ └── walker_rand_params.json │ ├── environment.yml │ ├── launch.py │ ├── launch_experiment.py │ ├── plot_csv.py │ ├── rand_param_envs │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-35.pyc │ │ ├── __init__.cpython-36.pyc │ │ ├── base.cpython-35.pyc │ │ ├── base.cpython-36.pyc │ │ └── hopper_rand_params.cpython-35.pyc │ ├── base.py │ ├── gym │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-35.pyc │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── configuration.cpython-35.pyc │ │ │ ├── configuration.cpython-36.pyc │ │ │ ├── core.cpython-35.pyc │ │ │ ├── core.cpython-36.pyc │ │ │ ├── error.cpython-35.pyc │ │ │ ├── error.cpython-36.pyc │ │ │ ├── version.cpython-35.pyc │ │ │ └── version.cpython-36.pyc │ │ ├── benchmarks │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-35.pyc │ │ │ │ ├── __init__.cpython-36.pyc │ │ │ │ ├── registration.cpython-35.pyc │ │ │ │ ├── registration.cpython-36.pyc │ │ │ │ ├── scoring.cpython-35.pyc │ │ │ │ └── scoring.cpython-36.pyc │ │ │ ├── registration.py │ │ │ ├── scoring.py │ │ │ └── tests │ │ │ │ ├── __init__.py │ │ │ │ └── test_benchmark.py │ │ ├── configuration.py │ │ ├── core.py │ │ ├── envs │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-35.pyc │ │ │ │ ├── __init__.cpython-36.pyc │ │ │ │ ├── registration.cpython-35.pyc │ │ │ │ └── registration.cpython-36.pyc │ │ │ ├── algorithmic │ │ │ │ ├── __init__.py │ │ │ │ ├── algorithmic_env.py │ │ │ │ ├── copy_.py │ │ │ │ ├── duplicated_input.py │ │ │ │ ├── repeat_copy.py │ │ │ │ ├── reverse.py │ │ │ │ ├── reversed_addition.py │ │ │ │ └── tests │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── test_algorithmic.py │ │ │ ├── atari │ │ │ │ ├── __init__.py │ │ │ │ └── atari_env.py │ │ │ ├── board_game │ │ │ │ ├── __init__.py │ │ │ │ ├── go.py │ │ │ │ └── hex.py │ │ │ ├── box2d │ │ │ │ ├── __init__.py │ │ │ │ ├── bipedal_walker.py │ │ │ │ ├── car_dynamics.py │ │ │ │ ├── car_racing.py │ │ │ │ └── lunar_lander.py │ │ │ ├── classic_control │ │ │ │ ├── __init__.py │ │ │ │ ├── acrobot.py │ │ │ │ ├── assets │ │ │ │ │ └── clockwise.png │ │ │ │ ├── cartpole.py │ │ │ │ ├── continuous_mountain_car.py │ │ │ │ ├── mountain_car.py │ │ │ │ ├── pendulum.py │ │ │ │ └── rendering.py │ │ │ ├── debugging │ │ │ │ ├── __init__.py │ │ │ │ ├── one_round_deterministic_reward.py │ │ │ │ ├── one_round_nondeterministic_reward.py │ │ │ │ ├── two_round_deterministic_reward.py │ │ │ │ └── two_round_nondeterministic_reward.py │ │ │ ├── mujoco │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-35.pyc │ │ │ │ │ ├── __init__.cpython-36.pyc │ │ │ │ │ ├── ant.cpython-35.pyc │ │ │ │ │ ├── half_cheetah.cpython-35.pyc │ │ │ │ │ ├── hopper.cpython-35.pyc │ │ │ │ │ ├── humanoid.cpython-35.pyc │ │ │ │ │ ├── humanoidstandup.cpython-35.pyc │ │ │ │ │ ├── inverted_double_pendulum.cpython-35.pyc │ │ │ │ │ ├── inverted_pendulum.cpython-35.pyc │ │ │ │ │ ├── mujoco_env.cpython-35.pyc │ │ │ │ │ ├── mujoco_env.cpython-36.pyc │ │ │ │ │ ├── reacher.cpython-35.pyc │ │ │ │ │ ├── swimmer.cpython-35.pyc │ │ │ │ │ └── walker2d.cpython-35.pyc │ │ │ │ ├── ant.py │ │ │ │ ├── assets │ │ │ │ │ ├── ant.xml │ │ │ │ │ ├── half_cheetah.xml │ │ │ │ │ ├── hopper.xml │ │ │ │ │ ├── humanoid.xml │ │ │ │ │ ├── humanoidstandup.xml │ │ │ │ │ ├── inverted_double_pendulum.xml │ │ │ │ │ ├── inverted_pendulum.xml │ │ │ │ │ ├── meshes │ │ │ │ │ │ ├── base.stl │ │ │ │ │ │ ├── base_L.stl │ │ │ │ │ │ ├── caster.stl │ │ │ │ │ │ ├── caster_L.stl │ │ │ │ │ │ ├── coffe_mate.stl │ │ │ │ │ │ ├── elbow_flex.stl │ │ │ │ │ │ ├── finger_tip_l.stl │ │ │ │ │ │ ├── finger_tip_pad2_l.stl │ │ │ │ │ │ ├── finger_tip_pad2_r.stl │ │ │ │ │ │ ├── finger_tip_r.stl │ │ │ │ │ │ ├── forearm.stl │ │ │ │ │ │ ├── forearm_roll.stl │ │ │ │ │ │ ├── forearm_roll_L.stl │ │ │ │ │ │ ├── gripper_palm.stl │ │ │ │ │ │ ├── head_pan.stl │ │ │ │ │ │ ├── head_pan_L.stl │ │ │ │ │ │ ├── head_tilt.stl │ │ │ │ │ │ ├── head_tilt_L.stl │ │ │ │ │ │ ├── hok_tilt.stl │ │ │ │ │ │ ├── l_finger.stl │ │ │ │ │ │ ├── l_finger_tip.stl │ │ │ │ │ │ ├── l_floating.stl │ │ │ │ │ │ ├── noddlesoup.stl │ │ │ │ │ │ ├── pr2_wheel.stl │ │ │ │ │ │ ├── shoulder_lift.stl │ │ │ │ │ │ ├── shoulder_pan.stl │ │ │ │ │ │ ├── shoulder_yaw.stl │ │ │ │ │ │ ├── tilting_hokuyo.stl │ │ │ │ │ │ ├── tilting_hokuyo_L.stl │ │ │ │ │ │ ├── torso.stl │ │ │ │ │ │ ├── torso_lift.stl │ │ │ │ │ │ ├── torso_lift_L.stl │ │ │ │ │ │ ├── upper_arm.stl │ │ │ │ │ │ ├── upper_arm_roll.stl │ │ │ │ │ │ ├── upper_arm_roll_L.stl │ │ │ │ │ │ ├── upper_finger_l.stl │ │ │ │ │ │ ├── upper_finger_r.stl │ │ │ │ │ │ ├── wheel.stl │ │ │ │ │ │ ├── white_rain.stl │ │ │ │ │ │ ├── windex.stl │ │ │ │ │ │ ├── wrist_flex.stl │ │ │ │ │ │ ├── wrist_roll.stl │ │ │ │ │ │ └── wrist_roll_L.stl │ │ │ │ │ ├── point.xml │ │ │ │ │ ├── pr2.xml │ │ │ │ │ ├── reacher.xml │ │ │ │ │ ├── swimmer.xml │ │ │ │ │ └── walker2d.xml │ │ │ │ ├── half_cheetah.py │ │ │ │ ├── hopper.py │ │ │ │ ├── humanoid.py │ │ │ │ ├── humanoidstandup.py │ │ │ │ ├── inverted_double_pendulum.py │ │ │ │ ├── inverted_pendulum.py │ │ │ │ ├── mujoco_env.py │ │ │ │ ├── reacher.py │ │ │ │ ├── swimmer.py │ │ │ │ └── walker2d.py │ │ │ ├── parameter_tuning │ │ │ │ ├── __init__.py │ │ │ │ ├── convergence.py │ │ │ │ └── train_deep_cnn.py │ │ │ ├── registration.py │ │ │ ├── safety │ │ │ │ ├── README.md │ │ │ │ ├── __init__.py │ │ │ │ ├── offswitch_cartpole.py │ │ │ │ ├── offswitch_cartpole_prob.py │ │ │ │ ├── predict_actions_cartpole.py │ │ │ │ ├── predict_obs_cartpole.py │ │ │ │ └── semisuper.py │ │ │ ├── tests │ │ │ │ ├── __init__.py │ │ │ │ ├── rollout.json │ │ │ │ ├── spec_list.py │ │ │ │ ├── test_determinism.py │ │ │ │ ├── test_envs.py │ │ │ │ ├── test_envs_semantics.py │ │ │ │ ├── test_registration.py │ │ │ │ └── test_safety_envs.py │ │ │ └── toy_text │ │ │ │ ├── __init__.py │ │ │ │ ├── blackjack.py │ │ │ │ ├── discrete.py │ │ │ │ ├── frozen_lake.py │ │ │ │ ├── guessing_game.py │ │ │ │ ├── hotter_colder.py │ │ │ │ ├── nchain.py │ │ │ │ ├── roulette.py │ │ │ │ └── taxi.py │ │ ├── error.py │ │ ├── monitoring │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-35.pyc │ │ │ │ ├── __init__.cpython-36.pyc │ │ │ │ ├── stats_recorder.cpython-35.pyc │ │ │ │ ├── stats_recorder.cpython-36.pyc │ │ │ │ ├── video_recorder.cpython-35.pyc │ │ │ │ └── video_recorder.cpython-36.pyc │ │ │ ├── stats_recorder.py │ │ │ ├── tests │ │ │ │ ├── __init__.py │ │ │ │ ├── helpers.py │ │ │ │ ├── test_monitor.py │ │ │ │ └── test_video_recorder.py │ │ │ └── video_recorder.py │ │ ├── scoreboard │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-35.pyc │ │ │ │ ├── __init__.cpython-36.pyc │ │ │ │ ├── api.cpython-35.pyc │ │ │ │ ├── api.cpython-36.pyc │ │ │ │ ├── registration.cpython-35.pyc │ │ │ │ └── registration.cpython-36.pyc │ │ │ ├── api.py │ │ │ ├── client │ │ │ │ ├── README.md │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-35.pyc │ │ │ │ │ ├── __init__.cpython-36.pyc │ │ │ │ │ ├── api_requestor.cpython-35.pyc │ │ │ │ │ ├── api_requestor.cpython-36.pyc │ │ │ │ │ ├── http_client.cpython-35.pyc │ │ │ │ │ ├── http_client.cpython-36.pyc │ │ │ │ │ ├── resource.cpython-35.pyc │ │ │ │ │ ├── resource.cpython-36.pyc │ │ │ │ │ ├── util.cpython-35.pyc │ │ │ │ │ └── util.cpython-36.pyc │ │ │ │ ├── api_requestor.py │ │ │ │ ├── http_client.py │ │ │ │ ├── resource.py │ │ │ │ ├── tests │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── helper.py │ │ │ │ │ ├── test_evaluation.py │ │ │ │ │ └── test_file_upload.py │ │ │ │ └── util.py │ │ │ ├── registration.py │ │ │ ├── scoring.py │ │ │ └── tests │ │ │ │ ├── __init__.py │ │ │ │ ├── test_registration.py │ │ │ │ └── test_scoring.py │ │ ├── spaces │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-35.pyc │ │ │ │ ├── __init__.cpython-36.pyc │ │ │ │ ├── box.cpython-35.pyc │ │ │ │ ├── box.cpython-36.pyc │ │ │ │ ├── discrete.cpython-35.pyc │ │ │ │ ├── discrete.cpython-36.pyc │ │ │ │ ├── multi_binary.cpython-35.pyc │ │ │ │ ├── multi_binary.cpython-36.pyc │ │ │ │ ├── multi_discrete.cpython-35.pyc │ │ │ │ ├── multi_discrete.cpython-36.pyc │ │ │ │ ├── prng.cpython-35.pyc │ │ │ │ ├── prng.cpython-36.pyc │ │ │ │ ├── tuple_space.cpython-35.pyc │ │ │ │ └── tuple_space.cpython-36.pyc │ │ │ ├── box.py │ │ │ ├── discrete.py │ │ │ ├── multi_binary.py │ │ │ ├── multi_discrete.py │ │ │ ├── prng.py │ │ │ ├── tests │ │ │ │ ├── __init__.py │ │ │ │ └── test_spaces.py │ │ │ └── tuple_space.py │ │ ├── tests │ │ │ └── test_core.py │ │ ├── utils │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-35.pyc │ │ │ │ ├── __init__.cpython-36.pyc │ │ │ │ ├── atomic_write.cpython-35.pyc │ │ │ │ ├── atomic_write.cpython-36.pyc │ │ │ │ ├── closer.cpython-35.pyc │ │ │ │ ├── closer.cpython-36.pyc │ │ │ │ ├── colorize.cpython-35.pyc │ │ │ │ ├── colorize.cpython-36.pyc │ │ │ │ ├── ezpickle.cpython-35.pyc │ │ │ │ ├── ezpickle.cpython-36.pyc │ │ │ │ ├── json_utils.cpython-35.pyc │ │ │ │ ├── json_utils.cpython-36.pyc │ │ │ │ ├── reraise.cpython-35.pyc │ │ │ │ ├── reraise.cpython-36.pyc │ │ │ │ ├── reraise_impl_py3.cpython-35.pyc │ │ │ │ ├── reraise_impl_py3.cpython-36.pyc │ │ │ │ ├── seeding.cpython-35.pyc │ │ │ │ └── seeding.cpython-36.pyc │ │ │ ├── atomic_write.py │ │ │ ├── closer.py │ │ │ ├── colorize.py │ │ │ ├── ezpickle.py │ │ │ ├── json_utils.py │ │ │ ├── play.py │ │ │ ├── reraise.py │ │ │ ├── reraise_impl_py2.py │ │ │ ├── reraise_impl_py3.py │ │ │ ├── seeding.py │ │ │ └── tests │ │ │ │ ├── test_atexit.py │ │ │ │ └── test_seeding.py │ │ ├── version.py │ │ └── wrappers │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-35.pyc │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── frame_skipping.cpython-35.pyc │ │ │ ├── frame_skipping.cpython-36.pyc │ │ │ ├── monitoring.cpython-35.pyc │ │ │ ├── monitoring.cpython-36.pyc │ │ │ ├── time_limit.cpython-35.pyc │ │ │ └── time_limit.cpython-36.pyc │ │ │ ├── frame_skipping.py │ │ │ ├── monitoring.py │ │ │ ├── tests │ │ │ ├── __init__.py │ │ │ └── test_wrappers.py │ │ │ └── time_limit.py │ ├── hopper_rand_params.py │ ├── mujoco_py │ │ ├── .ruby-version │ │ ├── Gemfile │ │ ├── Gemfile.lock │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-35.pyc │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── config.cpython-35.pyc │ │ │ ├── config.cpython-36.pyc │ │ │ ├── error.cpython-35.pyc │ │ │ ├── error.cpython-36.pyc │ │ │ ├── glfw.cpython-35.pyc │ │ │ ├── mjconstants.cpython-35.pyc │ │ │ ├── mjconstants.cpython-36.pyc │ │ │ ├── mjcore.cpython-35.pyc │ │ │ ├── mjcore.cpython-36.pyc │ │ │ ├── mjlib.cpython-35.pyc │ │ │ ├── mjlib.cpython-36.pyc │ │ │ ├── mjtypes.cpython-35.pyc │ │ │ ├── mjtypes.cpython-36.pyc │ │ │ ├── mjviewer.cpython-35.pyc │ │ │ ├── mjviewer.cpython-36.pyc │ │ │ ├── platname_targdir.cpython-35.pyc │ │ │ ├── util.cpython-35.pyc │ │ │ └── util.cpython-36.pyc │ │ ├── codegen.rb │ │ ├── config.py │ │ ├── error.py │ │ ├── gen_binding.sh │ │ ├── glfw.py │ │ ├── mjconstants.py │ │ ├── mjcore.py │ │ ├── mjextra.py │ │ ├── mjlib.py │ │ ├── mjtypes.py │ │ ├── mjviewer.py │ │ ├── platname_targdir.py │ │ ├── util.py │ │ └── vendor │ │ │ └── osx │ │ │ └── mujoco │ │ │ └── mujoco.h │ ├── pr2_env_reach.py │ └── walker2d_rand_params.py │ ├── rlkit │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-35.pyc │ │ └── __init__.cpython-36.pyc │ ├── core │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── eval_util.cpython-36.pyc │ │ │ ├── logger.cpython-36.pyc │ │ │ ├── rl_algorithm.cpython-36.pyc │ │ │ ├── serializable.cpython-36.pyc │ │ │ ├── tabulate.cpython-36.pyc │ │ │ └── util.cpython-36.pyc │ │ ├── eval_util.py │ │ ├── logger.py │ │ ├── rl_algorithm.py │ │ ├── serializable.py │ │ ├── tabulate.py │ │ └── util.py │ ├── data_management │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── env_replay_buffer.cpython-36.pyc │ │ │ ├── normalizer.cpython-36.pyc │ │ │ ├── path_builder.cpython-36.pyc │ │ │ ├── replay_buffer.cpython-36.pyc │ │ │ └── simple_replay_buffer.cpython-36.pyc │ │ ├── env_replay_buffer.py │ │ ├── normalizer.py │ │ ├── path_builder.py │ │ ├── replay_buffer.py │ │ └── simple_replay_buffer.py │ ├── envs │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-35.pyc │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── ant.cpython-35.pyc │ │ │ ├── ant.cpython-36.pyc │ │ │ ├── ant_dir.cpython-36.pyc │ │ │ ├── ant_goal.cpython-36.pyc │ │ │ ├── ant_multitask_base.cpython-35.pyc │ │ │ ├── ant_multitask_base.cpython-36.pyc │ │ │ ├── fetch_pickandplace.cpython-36.pyc │ │ │ ├── fetch_push.cpython-36.pyc │ │ │ ├── fetch_reach.cpython-36.pyc │ │ │ ├── fetch_slide.cpython-36.pyc │ │ │ ├── half_cheetah.cpython-36.pyc │ │ │ ├── half_cheetah_damping.cpython-36.pyc │ │ │ ├── half_cheetah_dir.cpython-36.pyc │ │ │ ├── half_cheetah_mass.cpython-36.pyc │ │ │ ├── half_cheetah_vel.cpython-36.pyc │ │ │ ├── humanoid_dir.cpython-36.pyc │ │ │ ├── ml1.cpython-36.pyc │ │ │ ├── ml10.cpython-36.pyc │ │ │ ├── ml45.cpython-36.pyc │ │ │ ├── mujoco_env.cpython-35.pyc │ │ │ ├── mujoco_env.cpython-36.pyc │ │ │ ├── nwalker_vel.cpython-36.pyc │ │ │ ├── point_robot.cpython-36.pyc │ │ │ ├── reacher_goal.cpython-36.pyc │ │ │ ├── sparse_point_robot.cpython-36.pyc │ │ │ ├── walker_rand_params_wrapper.cpython-36.pyc │ │ │ └── wrappers.cpython-36.pyc │ │ ├── ant.py │ │ ├── ant_dir.py │ │ ├── ant_goal.py │ │ ├── ant_multitask_base.py │ │ ├── assets │ │ │ ├── ant.xml │ │ │ └── low_gear_ratio_ant.xml │ │ ├── fetch_pickandplace.py │ │ ├── fetch_push.py │ │ ├── half_cheetah.py │ │ ├── half_cheetah_damping.py │ │ ├── half_cheetah_dir.py │ │ ├── half_cheetah_mass.py │ │ ├── half_cheetah_vel.py │ │ ├── hopper_rand_params_wrapper.py │ │ ├── humanoid_dir.py │ │ ├── mujoco_env.py │ │ ├── nwalker_vel.py │ │ ├── point_robot.py │ │ ├── reacher_goal.py │ │ ├── sparse_point_robot.py │ │ ├── walker2d_rand_params.py │ │ ├── walker_rand_params_wrapper.py │ │ └── wrappers.py │ ├── launchers │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── config.cpython-36.pyc │ │ │ └── launcher_util.cpython-36.pyc │ │ ├── config.py │ │ └── launcher_util.py │ ├── policies │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-36.pyc │ │ │ └── base.cpython-36.pyc │ │ ├── argmax.py │ │ ├── base.py │ │ └── simple.py │ ├── samplers │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── in_place.cpython-36.pyc │ │ │ └── util.cpython-36.pyc │ │ ├── in_place.py │ │ ├── util.py │ │ └── utile.py │ └── torch │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-36.pyc │ │ ├── core.cpython-36.pyc │ │ ├── distributions.cpython-36.pyc │ │ ├── modules.cpython-36.pyc │ │ ├── networks.cpython-36.pyc │ │ └── pytorch_util.cpython-36.pyc │ │ ├── core.py │ │ ├── data_management │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-36.pyc │ │ │ └── normalizer.cpython-36.pyc │ │ └── normalizer.py │ │ ├── distributions.py │ │ ├── modules.py │ │ ├── networks.py │ │ ├── pytorch_util.py │ │ └── sac │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-36.pyc │ │ ├── agent.cpython-36.pyc │ │ ├── policies.cpython-36.pyc │ │ └── sac.cpython-36.pyc │ │ ├── agent.py │ │ ├── policies.py │ │ └── sac.py │ ├── sim_policy.py │ └── walker2d_rand_params.py ├── RL_with_Other_Representations ├── .gitkeep ├── README.md └── VDFP │ ├── .gitkeep │ ├── README.md │ ├── assets │ └── VDFP_framework.png │ ├── networks │ ├── a2c.py │ ├── ddpg.py │ ├── ddsr.py │ ├── ppo.py │ ├── vdfp.py │ ├── vdfp_concat.py │ ├── vdfp_icnn.py │ ├── vdfp_lstm.py │ ├── vdfp_mlp.py │ ├── vdfp_neicnn.py │ ├── vdfp_ppo.py │ └── vdfp_relu.py │ └── run │ ├── ablation │ ├── mujoco_run_vdfp_concat.py │ ├── mujoco_run_vdfp_icnn.py │ ├── mujoco_run_vdfp_lstm.py │ ├── mujoco_run_vdfp_mlp.py │ └── mujoco_run_vdfp_relu.py │ ├── delay_reward │ ├── mujoco_run_a2c_delay.py │ ├── mujoco_run_ddpg_delay.py │ ├── mujoco_run_ddsr_delay.py │ ├── mujoco_run_ppo_delay.py │ └── mujoco_run_vdfp_delay.py │ ├── evaluation │ ├── mujoco_run_a2c.py │ ├── mujoco_run_ddpg.py │ ├── mujoco_run_ddsr.py │ └── mujoco_run_ppo.py │ ├── mujoco_run_vdfp.py │ ├── mujoco_run_vdfp_ppo.py │ └── run_vdfp.sh ├── RL_with_Policy_Representation ├── .gitkeep ├── Policy-based_RL_with_PeVFA │ ├── .gitkeep │ └── PPO-PeVFA │ │ ├── .gitkeep │ │ ├── README.md │ │ ├── mujoco_run_ppo_epoch.py │ │ ├── mujoco_run_ppo_pevf_aux_opr.py │ │ ├── mujoco_run_ppo_pevf_aux_spr.py │ │ ├── mujoco_run_ppo_pevf_cl_opr.py │ │ ├── mujoco_run_ppo_pevf_cl_spr.py │ │ ├── mujoco_run_ppo_pevf_e2e_opr_Sep.py │ │ ├── mujoco_run_ppo_pevf_e2e_ranpr.py │ │ ├── mujoco_run_ppo_pevf_e2e_rpr_freq.py │ │ ├── mujoco_run_ppo_pevf_e2e_spr_Sep.py │ │ ├── mujoco_run_ppo_pevf_e2e_stat_pr_freq.py │ │ └── networks │ │ ├── .gitkeep │ │ ├── ppo.py │ │ ├── ppo_pevf_aux_opr.py │ │ ├── ppo_pevf_aux_spr_ad.py │ │ ├── ppo_pevf_cl_opr.py │ │ ├── ppo_pevf_cl_spr_ad.py │ │ ├── ppo_pevf_e2e_opr1.py │ │ ├── ppo_pevf_e2e_ranpr.py │ │ ├── ppo_pevf_e2e_rpr.py │ │ ├── ppo_pevf_e2e_spr_ad.py │ │ └── ppo_pevf_e2e_stat_pr.py ├── README.md └── Value-based_RL_with_PeVFA │ └── .gitkeep ├── RL_with_State_Representation ├── .gitkeep └── README.md └── assets ├── .gitkeep ├── Ecology_of_SSRL.png ├── alg_framework.png ├── ar_readme_figs └── ar_framework.png ├── er_readme_figs └── ER_framework.png ├── hyar_results.png ├── pandr_results.png ├── pevfa_results.png ├── pr_readme_figs ├── .gitkeep ├── GPI_with_PeVFA.png └── policy_generalization.png └── sr_readme_figs └── sr_framework.png /RL_with_Action_Representation/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/.gitkeep -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/.gitkeep -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/agents/basis/__init__.py: -------------------------------------------------------------------------------- 1 | from agents.basis.basis import Basis 2 | from agents.basis.scaled_basis import ScaledBasis 3 | from agents.basis.simple_basis import SimpleBasis 4 | from agents.basis.fourier_basis import FourierBasis 5 | from agents.basis.polynomial_basis import PolynomialBasis 6 | 7 | __all__ = ["Basis", "ScaledBasis", "SimpleBasis", "FourierBasis", "PolynomialBasis"] 8 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/agents/basis/basis.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | 4 | class Basis(object): 5 | """ 6 | Trivial basis 7 | """ 8 | 9 | def __init__(self, nvars): 10 | self.num_terms = nvars 11 | self._shrink = np.ones((self.num_terms,)) 12 | 13 | def get_num_basis_functions(self): 14 | return self.num_terms 15 | 16 | def compute_features(self, state): 17 | return state 18 | 19 | def get_shrink(self): 20 | return self._shrink 21 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/agents/basis/polynomial_basis.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from .basis import Basis 3 | 4 | 5 | class PolynomialBasis(Basis): 6 | """ 7 | Induces a polynomial basis (excluding combinations) over the state variables. 8 | 9 | Example: 10 | -------- 11 | basis = PolynomialBasis(2, order=2) 12 | basis.compute_features(np.array([-2, 3]) 13 | array([ -2, 3, 4, 9 ]) 14 | """ 15 | 16 | def __init__(self, nvars, order=2, bias_unit=False): 17 | super().__init__(nvars) 18 | self.order = order 19 | self._bias_unit = bias_unit 20 | self.num_terms = order*nvars 21 | if self._bias_unit: 22 | self.num_terms += 1 23 | 24 | def compute_features(self, state): 25 | features = np.concatenate([state**i for i in range(1,self.order+1)]) 26 | if self._bias_unit: 27 | features = np.concatenate(([1.], features)) 28 | return features 29 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/agents/basis/scaled_basis.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from .basis import Basis 3 | 4 | 5 | class ScaledBasis(Basis): 6 | """ 7 | Scales variables in the range [0,1] 8 | """ 9 | 10 | def __init__(self, nvars, low, high, bias_unit=False): 11 | super().__init__(nvars) 12 | self.low = low 13 | self.high = high 14 | self.range = self.high-self.low 15 | self._bias_unit = bias_unit 16 | if self._bias_unit: 17 | self.num_terms += 1 18 | 19 | def scale_state(self, state): 20 | return (state - self.low)/self.range 21 | 22 | def compute_features(self, state): 23 | scaled_state = self.scale_state(state) 24 | if self._bias_unit: 25 | scaled_state = np.concatenate(([1.], scaled_state)) 26 | return scaled_state 27 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/agents/basis/simple_basis.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from .basis import Basis 3 | 4 | 5 | class SimpleBasis(Basis): 6 | """ 7 | Simple basis with an optional bias unit 8 | """ 9 | 10 | def __init__(self, nvars, bias_unit=False): 11 | super().__init__(nvars) 12 | self._bias_unit = bias_unit 13 | if self._bias_unit: 14 | self.num_terms += 1 15 | 16 | def compute_features(self, state): 17 | if self._bias_unit: 18 | state = np.concatenate(([1.], state)) 19 | return state 20 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/agents/memory/__init__.py: -------------------------------------------------------------------------------- 1 | from agents.memory.memory import Memory 2 | 3 | __all__ = ["Memory"] 4 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/agents/utils/__init__.py: -------------------------------------------------------------------------------- 1 | def soft_update_target_network(source_network, target_network, tau): 2 | for target_param, param in zip(target_network.parameters(), source_network.parameters()): 3 | target_param.data.copy_(tau * param.data + (1.0 - tau) * target_param.data) 4 | 5 | 6 | def hard_update_target_network(source_network, target_network): 7 | for target_param, param in zip(target_network.parameters(), source_network.parameters()): 8 | target_param.data.copy_(param.data) 9 | 10 | 11 | 12 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/agents/utils/noise.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | 4 | class OrnsteinUhlenbeckActionNoise(object): 5 | """ 6 | Based on http://math.stackexchange.com/questions/1287634/implementing-ornstein-uhlenbeck-in-matlab 7 | Source: https://github.com/vy007vikas/PyTorch-ActorCriticRL/blob/master/utils.py 8 | """ 9 | 10 | def __init__(self, action_dim, mu=0, theta=0.15, sigma=0.2, random_machine=np.random): 11 | super(OrnsteinUhlenbeckActionNoise, self).__init__() 12 | self.random = random_machine 13 | self.action_dim = action_dim 14 | self.mu = mu 15 | self.theta = theta 16 | self.sigma = sigma 17 | self.X = np.ones(self.action_dim) * self.mu 18 | 19 | def reset(self): 20 | self.X = np.ones(self.action_dim) * self.mu 21 | 22 | def sample(self): 23 | dx = self.theta * (self.mu - self.X) 24 | dx = dx + self.sigma * self.random.randn(len(self.X)) 25 | self.X = self.X + dx 26 | return self.X 27 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/assets/HyAR_concept.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/assets/HyAR_concept.png -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/common/__init__.py: -------------------------------------------------------------------------------- 1 | import click 2 | import ast 3 | 4 | 5 | class ClickPythonLiteralOption(click.Option): 6 | 7 | def type_cast_value(self, ctx, value): 8 | try: 9 | return ast.literal_eval(value) 10 | except Exception as e: 11 | print(e) 12 | raise click.BadParameter(value) 13 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/common/platform_domain.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | import gym 3 | 4 | 5 | class PlatformFlattenedActionWrapper(gym.ActionWrapper): 6 | """ 7 | Changes the format of the parameterised action space to conform to that of Goal-v0 and Platform-v0 8 | """ 9 | def __init__(self, env): 10 | super(PlatformFlattenedActionWrapper, self).__init__(env) 11 | old_as = env.action_space 12 | num_actions = old_as.spaces[0].n 13 | self.action_space = gym.spaces.Tuple(( 14 | old_as.spaces[0], # actions 15 | *(gym.spaces.Box(old_as.spaces[1].spaces[i].low, old_as.spaces[1].spaces[i].high, dtype=np.float32) 16 | for i in range(0, num_actions)) 17 | )) 18 | 19 | def action(self, action): 20 | return action 21 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/embedding/Utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/embedding/Utils/__init__.py -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/embedding/Utils/__pycache__/Basis.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/embedding/Utils/__pycache__/Basis.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/embedding/Utils/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/embedding/Utils/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/embedding/Utils/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/embedding/Utils/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-goal-master/LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2019 Craig Bester 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-goal-master/gym_goal/__init__.py: -------------------------------------------------------------------------------- 1 | from gym.envs.registration import register 2 | 3 | register( 4 | id='Goal-v0', 5 | entry_point='gym_goal.envs:GoalEnv', 6 | ) -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-goal-master/gym_goal/envs/__init__.py: -------------------------------------------------------------------------------- 1 | from gym_goal.envs.goal_env import GoalEnv 2 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-goal-master/img/goal_domain.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/gym-goal-master/img/goal_domain.png -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-goal-master/setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | 3 | setup( 4 | name='gym_goal', 5 | version='0.0.1', 6 | description='Goal domain OpenAI Gym environment', 7 | author='Craig James Bester', 8 | packages=['gym_goal'], 9 | install_requires=['gym', 10 | 'pygame', #'pygame>=1.9.3' 11 | 'numpy', #'numpy>=1.14.0' 12 | ] 13 | ) 14 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/LICENSE.md: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2019 Craig Bester 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/__init__.py: -------------------------------------------------------------------------------- 1 | from gym.envs.registration import register 2 | 3 | register( 4 | id='Platform-v0', 5 | entry_point='gym_platform.envs:PlatformEnv', 6 | max_episode_steps=200, 7 | # TODO: max_episode_steps=200, 8 | # TODO: reward_threshold=1.0? maybe 0.8 or 0.9 9 | ) -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/__init__.py: -------------------------------------------------------------------------------- 1 | from gym_platform.envs.platform_env import PlatformEnv 2 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/background.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/background.png -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/background_white.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/background_white.png -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/enemy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/enemy.png -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/platform.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/platform.png -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/platform_v3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/platform_v3.png -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/player.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/gym-platform-master/gym_platform/envs/assets/player.png -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/img/platform_domain.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Action_Representation/HyAR/gym-platform-master/img/platform_domain.png -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/gym-platform-master/setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | 3 | setup( 4 | name='gym_platform', 5 | version='0.0.1', 6 | description='Platform domain OpenAI Gym environment', 7 | author='Craig Bester', 8 | packages=['gym_platform'], 9 | include_package_data=True, # include asset files. TODO: specify specific files? 10 | install_requires=['gym', 11 | 'pygame', #'pygame>=1.9.3' 12 | 'numpy', #'numpy>=1.14.0' 13 | ] 14 | ) 15 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/multiagent/__init__.py: -------------------------------------------------------------------------------- 1 | from gym.envs.registration import register 2 | 3 | # Multiagent envs 4 | # ---------------------------------------- 5 | 6 | register( 7 | id='MultiagentSimple-v0', 8 | entry_point='multiagent.envs:SimpleEnv', 9 | # FIXME(cathywu) currently has to be exactly max_path_length parameters in 10 | # rllab run script 11 | max_episode_steps=100, 12 | ) 13 | 14 | register( 15 | id='MultiagentSimpleSpeakerListener-v0', 16 | entry_point='multiagent.envs:SimpleSpeakerListenerEnv', 17 | max_episode_steps=100, 18 | ) 19 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/multiagent/scenario.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | # defines scenario upon which the world is built 4 | class BaseScenario(object): 5 | # create elements of the world 6 | def make_world(self): 7 | raise NotImplementedError() 8 | # create initial conditions of the world 9 | def reset_world(self, world): 10 | raise NotImplementedError() 11 | -------------------------------------------------------------------------------- /RL_with_Action_Representation/HyAR/multiagent/scenarios/__init__.py: -------------------------------------------------------------------------------- 1 | import imp 2 | import os.path as osp 3 | 4 | 5 | def load(name): 6 | pathname = osp.join(osp.dirname(__file__), name) 7 | return imp.load_source('', pathname) 8 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/.gitkeep -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/.gitkeep -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/assets/PAnDR_concept.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/assets/PAnDR_concept.png -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant.egg-info/PKG-INFO: -------------------------------------------------------------------------------- 1 | Metadata-Version: 1.0 2 | Name: myant 3 | Version: 0.0.1 4 | Summary: UNKNOWN 5 | Home-page: UNKNOWN 6 | Author: UNKNOWN 7 | Author-email: UNKNOWN 8 | License: UNKNOWN 9 | Description: UNKNOWN 10 | Platform: UNKNOWN 11 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant.egg-info/SOURCES.txt: -------------------------------------------------------------------------------- 1 | setup.py 2 | myant.egg-info/PKG-INFO 3 | myant.egg-info/SOURCES.txt 4 | myant.egg-info/dependency_links.txt 5 | myant.egg-info/requires.txt 6 | myant.egg-info/top_level.txt -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant.egg-info/dependency_links.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant.egg-info/requires.txt: -------------------------------------------------------------------------------- 1 | gym 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant.egg-info/top_level.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant/__init__.py: -------------------------------------------------------------------------------- 1 | from gym.envs.registration import register 2 | 3 | register( 4 | id='myant-v0', 5 | entry_point='myant.envs:AntEnv', 6 | max_episode_steps=256, 7 | reward_threshold=-3.75, 8 | ) 9 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/myant/myant/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant/envs/__init__.py: -------------------------------------------------------------------------------- 1 | from myant.envs.myant import AntEnv 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant/envs/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/myant/myant/envs/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/myant/envs/__pycache__/myant.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/myant/myant/envs/__pycache__/myant.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myant/setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | 3 | setup(name='myant', 4 | version='0.0.1', 5 | install_requires=['gym']#And any other dependencies required 6 | ) 7 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship.egg-info/PKG-INFO: -------------------------------------------------------------------------------- 1 | Metadata-Version: 1.0 2 | Name: myspaceship 3 | Version: 0.0.1 4 | Summary: UNKNOWN 5 | Home-page: UNKNOWN 6 | Author: UNKNOWN 7 | Author-email: UNKNOWN 8 | License: UNKNOWN 9 | Description: UNKNOWN 10 | Platform: UNKNOWN 11 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship.egg-info/SOURCES.txt: -------------------------------------------------------------------------------- 1 | setup.py 2 | myspaceship.egg-info/PKG-INFO 3 | myspaceship.egg-info/SOURCES.txt 4 | myspaceship.egg-info/dependency_links.txt 5 | myspaceship.egg-info/requires.txt 6 | myspaceship.egg-info/top_level.txt -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship.egg-info/dependency_links.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship.egg-info/requires.txt: -------------------------------------------------------------------------------- 1 | gym 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship.egg-info/top_level.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship/__init__.py: -------------------------------------------------------------------------------- 1 | from gym.envs.registration import register 2 | 3 | register( 4 | id='spaceship-v0', 5 | entry_point='myspaceship.envs:SpaceshipEnv', 6 | ) -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship/envs/__init__.py: -------------------------------------------------------------------------------- 1 | from myspaceship.envs.myspaceship import SpaceshipEnv 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship/envs/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship/envs/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship/envs/__pycache__/myspaceship.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/myspaceship/myspaceship/envs/__pycache__/myspaceship.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myspaceship/setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | 3 | setup(name='myspaceship', 4 | version='0.0.1', 5 | install_requires=['gym']#And any other dependencies required 6 | ) 7 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer.egg-info/PKG-INFO: -------------------------------------------------------------------------------- 1 | Metadata-Version: 1.0 2 | Name: myswimmer 3 | Version: 0.0.1 4 | Summary: UNKNOWN 5 | Home-page: UNKNOWN 6 | Author: UNKNOWN 7 | Author-email: UNKNOWN 8 | License: UNKNOWN 9 | Description: UNKNOWN 10 | Platform: UNKNOWN 11 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer.egg-info/SOURCES.txt: -------------------------------------------------------------------------------- 1 | setup.py 2 | myswimmer.egg-info/PKG-INFO 3 | myswimmer.egg-info/SOURCES.txt 4 | myswimmer.egg-info/dependency_links.txt 5 | myswimmer.egg-info/requires.txt 6 | myswimmer.egg-info/top_level.txt -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer.egg-info/dependency_links.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer.egg-info/requires.txt: -------------------------------------------------------------------------------- 1 | gym 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer.egg-info/top_level.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer/__init__.py: -------------------------------------------------------------------------------- 1 | from gym.envs.registration import register 2 | 3 | register( 4 | id='myswimmer-v0', 5 | entry_point='myswimmer.envs:SwimmerEnv', 6 | max_episode_steps=1000, 7 | reward_threshold=360.0, 8 | ) 9 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer/envs/__init__.py: -------------------------------------------------------------------------------- 1 | from myswimmer.envs.myswimmer import SwimmerEnv 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer/envs/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer/envs/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer/envs/__pycache__/myswimmer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/myswimmer/myswimmer/envs/__pycache__/myswimmer.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/myswimmer/setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | 3 | setup(name='myswimmer', 4 | version='0.0.1', 5 | install_requires=['gym']#And any other dependencies required 6 | ) 7 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/__pycache__/arguments.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/__pycache__/arguments.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/__pycache__/distributions.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/__pycache__/distributions.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/__pycache__/envs.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/__pycache__/envs.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/__pycache__/evaluation.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/__pycache__/evaluation.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/__pycache__/model.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/__pycache__/model.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/__pycache__/storage.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/__pycache__/storage.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/algo/__init__.py: -------------------------------------------------------------------------------- 1 | from .ppo import PPO -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/algo/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/algo/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/PAnDR/ppo/algo/__pycache__/ppo.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/PAnDR/ppo/algo/__pycache__/ppo.cpython-37.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/assets/ccm_framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/assets/ccm_framework.png -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/assets/contrastive_context_encoder.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/assets/contrastive_context_encoder.png -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/__pycache__/default.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/configs/__pycache__/default.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/ant-dir.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "ant-dir", 3 | "n_train_tasks": 2, 4 | "n_eval_tasks": 2, 5 | "env_params": { 6 | "n_tasks": 2 7 | } 8 | , 9 | "algo_params": { 10 | "meta_batch": 8, 11 | "num_initial_steps": 2000, 12 | "num_steps_prior": 400, 13 | "num_steps_posterior": 0, 14 | "num_extra_rl_steps_posterior": 600, 15 | "num_train_steps_per_itr": 8000, 16 | "num_evals": 4, 17 | "num_steps_per_eval": 600, 18 | "num_exp_traj_eval": 2, 19 | "embedding_batch_size": 256, 20 | "embedding_mini_batch_size": 256, 21 | "use_information_bottleneck": false 22 | } 23 | } 24 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/ant-goal.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "ant-goal", 3 | "n_train_tasks": 150, 4 | "n_eval_tasks": 10, 5 | "env_params": { 6 | "n_tasks": 150 7 | }, 8 | "env_params2": { 9 | "env_type": "test", 10 | "n_tasks": 10 11 | } 12 | , 13 | "algo_params": { 14 | "num_iterations": 1000, 15 | "meta_batch": 20, 16 | "num_initial_steps": 2000, 17 | "num_steps_prior": 800, 18 | "num_steps_posterior": 0, 19 | "num_extra_rl_steps_posterior": 1200, 20 | "num_train_steps_per_itr": 4000, 21 | "num_evals": 1, 22 | "num_steps_per_eval": 600, 23 | "num_exp_traj_eval": 2, 24 | "embedding_batch_size": 256, 25 | "embedding_mini_batch_size": 256, 26 | "kl_lambda": 1.0, 27 | "use_information_bottleneck": false 28 | } 29 | } 30 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/cheetah-damping.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "cheetah-damping", 3 | "n_train_tasks": 30, 4 | "n_eval_tasks": 5, 5 | "env_params": { 6 | "n_tasks": 30 7 | }, 8 | "env_params2": { 9 | "env_type": "test", 10 | "n_tasks": 5 11 | } 12 | , 13 | "algo_params": { 14 | "meta_batch": 12, 15 | "num_initial_steps": 1000, 16 | "num_steps_prior": 200, 17 | "num_steps_posterior": 0, 18 | "num_extra_rl_steps_posterior": 300, 19 | "num_train_steps_per_itr": 2000, 20 | "num_evals": 1, 21 | "num_steps_per_eval": 600, 22 | "num_exp_traj_eval": 2, 23 | "embedding_batch_size": 100, 24 | "embedding_mini_batch_size": 100, 25 | "use_information_bottleneck": false 26 | } 27 | } 28 | 29 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/cheetah-dir.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "cheetah-dir", 3 | "n_train_tasks": 2, 4 | "n_eval_tasks": 2, 5 | "env_params": { 6 | "n_tasks": 2 7 | } 8 | , 9 | "algo_params": { 10 | "meta_batch": 8, 11 | "num_initial_steps": 2, 12 | "num_steps_prior": 10, 13 | "num_steps_posterior": 0, 14 | "num_extra_rl_steps_posterior": 10, 15 | "num_train_steps_per_itr": 2, 16 | "num_evals": 4, 17 | "num_steps_per_eval": 600, 18 | "num_exp_traj_eval": 2, 19 | "embedding_batch_size": 100, 20 | "embedding_mini_batch_size": 100, 21 | "use_information_bottleneck": false, 22 | "recurrent": false 23 | } 24 | } 25 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/cheetah-mass.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "cheetah-mass", 3 | "n_train_tasks": 60, 4 | "n_eval_tasks": 10, 5 | "env_params": { 6 | "n_tasks": 60, 7 | "sparse": true 8 | }, 9 | "env_params2": { 10 | "env_type": "test", 11 | "n_tasks": 10, 12 | "sparse": true 13 | } 14 | , 15 | "algo_params": { 16 | "num_iterations": 600, 17 | "meta_batch": 20, 18 | "num_initial_steps": 512, 19 | "num_steps_prior": 256, 20 | "num_steps_posterior": 512, 21 | "num_extra_rl_steps_posterior": 0, 22 | "num_train_steps_per_itr": 1000, 23 | "num_evals": 1, 24 | "num_steps_per_eval": 320, 25 | "num_exp_traj_eval": 4, 26 | "max_path_length": 64, 27 | "embedding_batch_size": 128, 28 | "embedding_mini_batch_size": 128, 29 | "batch_size": 128, 30 | "kl_lambda": 1e-4, 31 | "use_information_bottleneck": true, 32 | "meta_episode_len": 2, 33 | "use_next_state": true 34 | } 35 | } 36 | 37 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/cheetah-vel.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "cheetah-vel", 3 | "n_train_tasks": 100, 4 | "n_eval_tasks": 10, 5 | "env_params": { 6 | "n_tasks": 100, 7 | "sparse": true 8 | }, 9 | "env_params2": { 10 | "env_type": "test", 11 | "n_tasks": 10, 12 | "sparse": true 13 | } 14 | , 15 | "algo_params": { 16 | "num_iterations": 2000, 17 | "meta_batch": 16, 18 | "num_initial_steps": 512, 19 | "num_steps_prior": 256, 20 | "num_steps_posterior": 128, 21 | "num_extra_rl_steps_posterior": 256, 22 | "num_train_steps_per_itr": 1000, 23 | "num_evals": 1, 24 | "num_steps_per_eval": 128, 25 | "num_exp_traj_eval": 2, 26 | "max_path_length": 64, 27 | "embedding_batch_size": 64, 28 | "embedding_mini_batch_size": 64, 29 | "batch_size": 64, 30 | "kl_lambda": 1e-4, 31 | "use_information_bottleneck": true, 32 | "meta_episode_len": 1, 33 | "use_next_state": false 34 | } 35 | } 36 | 37 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/fetch-pickplace.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "fetch_pickandplace", 3 | "n_train_tasks": 2, 4 | "n_eval_tasks": 2, 5 | "env_params": { 6 | "n_tasks": 2 7 | } 8 | , 9 | "algo_params": { 10 | "meta_batch": 4, 11 | "num_initial_steps": 2000, 12 | "num_steps_prior": 1000, 13 | "num_steps_posterior": 0, 14 | "num_extra_rl_steps_posterior": 1000, 15 | "num_evals": 4, 16 | "num_steps_per_eval": 600, 17 | "num_exp_traj_eval": 2, 18 | "embedding_batch_size": 256, 19 | "embedding_mini_batch_size": 256 20 | } 21 | } 22 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/fetch-slide.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "fetch_slide", 3 | "n_train_tasks": 100, 4 | "n_eval_tasks": 30, 5 | "env_params": { 6 | "n_tasks": 130 7 | } 8 | , 9 | "algo_params": { 10 | "num_initial_steps": 2000, 11 | "num_steps_prior": 400, 12 | "num_steps_posterior": 0, 13 | "num_extra_rl_steps_posterior": 600, 14 | "num_train_steps_per_itr": 4000, 15 | "num_evals": 1, 16 | "num_steps_per_eval": 600, 17 | "num_exp_traj_eval": 2, 18 | "embedding_batch_size": 256, 19 | "embedding_mini_batch_size": 256 20 | } 21 | } 22 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/hopper_rand_params.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "hopper-rand-params", 3 | "n_train_tasks": 40, 4 | "n_eval_tasks": 10, 5 | "env_params": { 6 | "n_tasks": 50 7 | } 8 | , 9 | "algo_params": { 10 | "meta_batch": 10, 11 | "num_initial_steps": 2000, 12 | "num_steps_prior": 400, 13 | "num_steps_posterior": 0, 14 | "num_extra_rl_steps_posterior": 600, 15 | "num_train_steps_per_itr": 4000, 16 | "num_evals": 2, 17 | "num_steps_per_eval": 600, 18 | "num_exp_traj_eval": 2, 19 | "embedding_batch_size": 100, 20 | "embedding_mini_batch_size": 100 21 | } 22 | } 23 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/humanoid-dir.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "humanoid-dir", 3 | "n_train_tasks": 100, 4 | "n_eval_tasks": 10, 5 | "env_params": { 6 | "n_tasks": 110 7 | } 8 | , 9 | "algo_params": { 10 | "meta_batch": 20, 11 | "num_initial_steps": 2000, 12 | "num_steps_prior": 400, 13 | "num_steps_posterior": 0, 14 | "num_extra_rl_steps_posterior": 600, 15 | "num_train_steps_per_itr": 4000, 16 | "num_evals": 1, 17 | "num_steps_per_eval": 600, 18 | "num_exp_traj_eval": 2, 19 | "embedding_batch_size": 256, 20 | "embedding_mini_batch_size": 256, 21 | "use_information_bottleneck": false, 22 | "recurrent": false 23 | } 24 | } 25 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/ml1.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "ML1_test", 3 | "n_train_tasks": 50, 4 | "n_eval_tasks": 5, 5 | "net_size": 300, 6 | "env_params": { 7 | "n_tasks": 55 8 | } 9 | , 10 | "algo_params": { 11 | "meta_batch": 16, 12 | "num_initial_steps": 2000, 13 | "num_steps_prior": 400, 14 | "num_steps_posterior": 0, 15 | "num_extra_rl_steps_posterior": 600, 16 | "num_train_steps_per_itr": 4000, 17 | "num_evals": 2, 18 | "num_steps_per_eval": 600, 19 | "num_exp_traj_eval": 2, 20 | "embedding_batch_size": 100, 21 | "embedding_mini_batch_size": 100, 22 | "use_information_bottleneck": false 23 | } 24 | } 25 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/ml10.json: -------------------------------------------------------------------------------- 1 | { 2 | 3 | "env_name": "ML45_test", 4 | "n_train_tasks": 450, 5 | "n_eval_tasks": 25, 6 | "env_params": { 7 | "n_tasks": 450 8 | }, 9 | "env_params2": { 10 | "env_type": "test", 11 | "n_tasks": 25 12 | }, 13 | "algo_params": { 14 | "meta_batch": 16, 15 | "num_initial_steps": 2000, 16 | "num_steps_prior": 400, 17 | "num_steps_posterior": 0, 18 | "num_extra_rl_steps_posterior": 600, 19 | "num_train_steps_per_itr": 4000, 20 | "num_evals": 1, 21 | "num_steps_per_eval": 600, 22 | "num_exp_traj_eval": 2, 23 | "embedding_batch_size": 150, 24 | "embedding_mini_batch_size": 150, 25 | "kl_lambda": 1 26 | } 27 | } 28 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/ml45.json: -------------------------------------------------------------------------------- 1 | { 2 | 3 | "env_name": "ML45_test", 4 | "n_train_tasks": 45, 5 | "n_eval_tasks": 5, 6 | "env_params": { 7 | "n_tasks": 45 8 | }, 9 | "env_params2": { 10 | "env_type": "test", 11 | "n_tasks": 5 12 | }, 13 | "algo_params": { 14 | "num_iterations": 1000, 15 | "meta_batch": 16, 16 | "num_initial_steps": 1600, 17 | "num_steps_prior": 600, 18 | "num_steps_posterior": 0, 19 | "num_extra_rl_steps_posterior": 800, 20 | "num_train_steps_per_itr": 4000, 21 | "num_evals": 2, 22 | "num_steps_per_eval": 600, 23 | "num_exp_traj_eval": 2, 24 | "embedding_batch_size": 64, 25 | "embedding_mini_batch_size": 64, 26 | "kl_lambda": 0.1, 27 | "use_information_bottleneck": false 28 | } 29 | } 30 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/point-robot.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "sparse-point-robot1", 3 | "n_train_tasks": 40, 4 | "n_eval_tasks": 5, 5 | "env_params": { 6 | "n_tasks": 40 7 | } 8 | , 9 | "env_params2": { 10 | "env_type": "test", 11 | "n_tasks": 5, 12 | "sparse": true 13 | } 14 | , 15 | "algo_params": { 16 | "meta_batch": 24, 17 | "num_initial_steps": 2000, 18 | "num_tasks_sample": 8, 19 | "num_steps_prior": 300, 20 | "num_steps_posterior": 1200, 21 | "num_extra_rl_steps_posterior": 0, 22 | "num_train_steps_per_itr": 1000, 23 | "num_steps_per_eval": 320, 24 | "embedding_batch_size": 240, 25 | "embedding_mini_batch_size": 240, 26 | "num_evals": 3, 27 | "batch_size": 240, 28 | "max_path_length": 40, 29 | "discount": 0.90, 30 | "reward_scale": 100.0, 31 | "sparse_rewards": 1, 32 | "kl_lambda": 1.0, 33 | "meta_episode_len": 5, 34 | "use_information_bottleneck": true, 35 | "use_next_state": false 36 | } 37 | } 38 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/reacher-goal.json: -------------------------------------------------------------------------------- 1 | { 2 | "exp_name": "newmetaexplore", 3 | "env_name": "reacher-goal-sparse", 4 | "n_train_tasks": 45, 5 | "n_eval_tasks": 5, 6 | "env_params": { 7 | "n_tasks": 45, 8 | "sparse": true 9 | }, 10 | "env_params2": { 11 | "env_type": "test", 12 | "n_tasks": 5, 13 | "sparse": true 14 | } 15 | , 16 | "algo_params": { 17 | "num_iterations": 2000, 18 | "num_initial_steps": 256, 19 | "num_steps_prior": 256, 20 | "num_steps_posterior": 256, 21 | "num_extra_rl_steps_posterior": 256, 22 | "num_train_steps_per_itr": 1000, 23 | "num_evals": 3, 24 | "num_steps_per_eval": 256, 25 | "embedding_batch_size": 192, 26 | "embedding_mini_batch_size": 192, 27 | "batch_size": 192, 28 | "max_path_length": 64, 29 | "reward_scale": 100.0, 30 | "kl_lambda": 1e-0, 31 | "discount": 0.90, 32 | "use_information_bottleneck": true, 33 | "meta_episode_len": 3, 34 | "use_next_state": false 35 | } 36 | } 37 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/sparse-point-robot.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "sparse-point-robot1", 3 | "n_train_tasks": 80, 4 | "n_eval_tasks": 10, 5 | "env_params": { 6 | "n_tasks": 80, 7 | "sparse": true, 8 | "goal_radius": 0.3 9 | }, 10 | "env_params2": { 11 | "env_type": "test", 12 | "n_tasks": 10, 13 | "sparse": true, 14 | "goal_radius": 0.3 15 | } 16 | , 17 | "algo_params": { 18 | "num_iterations": 1000, 19 | "meta_batch": 16, 20 | "num_initial_steps": 128, 21 | "num_tasks_sample": 10, 22 | "num_steps_prior": 128, 23 | "num_steps_posterior": 128, 24 | "num_extra_rl_steps_posterior": 128, 25 | "num_train_steps_per_itr": 1000, 26 | "num_evals": 3, 27 | "num_steps_per_eval": 192, 28 | "num_exp_traj_eval": 2, 29 | "embedding_batch_size": 96, 30 | "embedding_mini_batch_size": 96, 31 | "batch_size": 96, 32 | "max_path_length": 32, 33 | "reward_scale": 100.0, 34 | "kl_lambda": 1e-0, 35 | "discount": 0.90, 36 | "use_information_bottleneck": true, 37 | "use_next_state": false, 38 | "meta_episode_len": 4 39 | } 40 | } 41 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/walker-vel-sparse.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "nwalker-vel-sparse", 3 | "n_train_tasks": 100, 4 | "n_eval_tasks": 10, 5 | "latent_size": 2, 6 | "env_params": { 7 | "n_tasks": 100 8 | } 9 | , 10 | "env_params2": { 11 | "env_type": "test", 12 | "n_tasks": 10, 13 | "sparse": true 14 | }, 15 | "algo_params": { 16 | "meta_batch": 16, 17 | "num_iterations": 2000, 18 | "num_initial_steps": 128, 19 | "num_steps_prior": 256, 20 | "num_steps_posterior": 256, 21 | "num_extra_rl_steps_posterior": 256, 22 | "num_evals": 1, 23 | "num_train_steps_per_itr": 1000, 24 | "num_steps_per_eval": 256, 25 | "embedding_batch_size": 64, 26 | "embedding_mini_batch_size": 64, 27 | "batch_size": 64, 28 | "max_path_length": 64, 29 | "kl_lambda": 1e-0, 30 | "meta_episode_len": 2, 31 | "reward_scale": 10, 32 | "use_information_bottleneck": true, 33 | "use_next_state": false 34 | }, 35 | "util_params": { 36 | "base_log_dir":"outputmetacure" 37 | 38 | } 39 | } 40 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/configs/walker_rand_params.json: -------------------------------------------------------------------------------- 1 | { 2 | "env_name": "walker-rand-params", 3 | "n_train_tasks": 40, 4 | "n_eval_tasks": 10, 5 | "env_params": { 6 | "n_tasks": 50 7 | } 8 | , 9 | "algo_params": { 10 | "meta_batch": 10, 11 | "num_initial_steps": 2000, 12 | "num_steps_prior": 400, 13 | "num_steps_posterior": 0, 14 | "num_extra_rl_steps_posterior": 600, 15 | "num_train_steps_per_itr": 4000, 16 | "num_evals": 2, 17 | "num_steps_per_eval": 600, 18 | "num_exp_traj_eval": 2, 19 | "embedding_batch_size": 100, 20 | "embedding_mini_batch_size": 100 21 | } 22 | } 23 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/launch.py: -------------------------------------------------------------------------------- 1 | """ 2 | Launch an experiment on local machine with docker 3 | """ 4 | 5 | import sys 6 | 7 | import doodad as dd 8 | import doodad.ssh as ssh 9 | import doodad.mount as mount 10 | 11 | 12 | mode_local = dd.mode.LocalDocker( 13 | image='rakelly/rlkit:latest' 14 | ) 15 | 16 | # Set up code and output directories 17 | OUTPUT_DIR = 'output' # doodad will prepend `/mounts` to this, set config in code to output to this path 18 | mounts = [ 19 | mount.MountLocal(local_dir='~/rlkit', pythonpath=True), # point to your code 20 | mount.MountLocal(local_dir='~/.mujoco', mount_point='/root/.mujoco'), # point to your mujoco 21 | mount.MountLocal(local_dir='~/rlkit/output', mount_point=OUTPUT_DIR, output=True), 22 | ] 23 | 24 | call = sys.argv[1] + ' 1' # assume script has arg for docker mode 25 | dd.launch_python( 26 | target=call, # call target script (absolute path) 27 | mode=mode_local, 28 | mount_points=mounts, 29 | verbose=True, 30 | ) 31 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.base import MetaEnv 2 | from rand_param_envs.gym.envs.registration import register 3 | 4 | register( 5 | id='Walker2DRandParams-v0', 6 | entry_point='rand_param_envs.walker2d_rand_params:Walker2DRandParamsEnv', 7 | ) 8 | 9 | register( 10 | id='HopperRandParams-v0', 11 | entry_point='rand_param_envs.hopper_rand_params:HopperRandParamsEnv', 12 | ) 13 | 14 | register( 15 | id='PR2Env-v0', 16 | entry_point='rand_param_envs.pr2_env_reach:PR2Env', 17 | ) 18 | 19 | 20 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/base.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/base.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/base.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/base.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/hopper_rand_params.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/__pycache__/hopper_rand_params.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/configuration.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/configuration.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/configuration.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/configuration.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/core.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/core.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/core.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/core.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/error.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/error.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/error.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/error.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/version.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/version.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/version.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/__pycache__/version.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/registration.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/registration.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/registration.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/registration.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/scoring.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/scoring.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/scoring.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/__pycache__/scoring.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/benchmarks/tests/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/__pycache__/registration.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/__pycache__/registration.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/__pycache__/registration.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/__pycache__/registration.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/algorithmic/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.envs.algorithmic.copy_ import CopyEnv 2 | from rand_param_envs.gym.envs.algorithmic.repeat_copy import RepeatCopyEnv 3 | from rand_param_envs.gym.envs.algorithmic.duplicated_input import DuplicatedInputEnv 4 | from rand_param_envs.gym.envs.algorithmic.reverse import ReverseEnv 5 | from rand_param_envs.gym.envs.algorithmic.reversed_addition import ReversedAdditionEnv 6 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/algorithmic/copy_.py: -------------------------------------------------------------------------------- 1 | """ 2 | Task is to copy content from the input tape to 3 | the output tape. http://arxiv.org/abs/1511.07275 4 | """ 5 | import numpy as np 6 | from rand_param_envs.gym.envs.algorithmic import algorithmic_env 7 | 8 | class CopyEnv(algorithmic_env.TapeAlgorithmicEnv): 9 | def __init__(self, base=5, chars=True): 10 | super(CopyEnv, self).__init__(base=base, chars=chars) 11 | 12 | def target_from_input_data(self, input_data): 13 | return input_data 14 | 15 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/algorithmic/duplicated_input.py: -------------------------------------------------------------------------------- 1 | """ 2 | Task is to return every nth character from the input tape. 3 | http://arxiv.org/abs/1511.07275 4 | """ 5 | from __future__ import division 6 | import numpy as np 7 | from rand_param_envs.gym.envs.algorithmic import algorithmic_env 8 | 9 | class DuplicatedInputEnv(algorithmic_env.TapeAlgorithmicEnv): 10 | def __init__(self, duplication=2, base=5): 11 | self.duplication = duplication 12 | super(DuplicatedInputEnv, self).__init__(base=base, chars=True) 13 | 14 | def generate_input_data(self, size): 15 | res = [] 16 | if size < self.duplication: 17 | size = self.duplication 18 | for i in range(size//self.duplication): 19 | char = self.np_random.randint(self.base) 20 | for _ in range(self.duplication): 21 | res.append(char) 22 | return res 23 | 24 | def target_from_input_data(self, input_data): 25 | return [input_data[i] for i in range(0, len(input_data), self.duplication)] 26 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/algorithmic/repeat_copy.py: -------------------------------------------------------------------------------- 1 | """ 2 | Task is to copy content multiple times from the input tape to 3 | the output tape. http://arxiv.org/abs/1511.07275 4 | """ 5 | import numpy as np 6 | from rand_param_envs.gym.envs.algorithmic import algorithmic_env 7 | 8 | class RepeatCopyEnv(algorithmic_env.TapeAlgorithmicEnv): 9 | MIN_REWARD_SHORTFALL_FOR_PROMOTION = -.1 10 | def __init__(self, base=5): 11 | super(RepeatCopyEnv, self).__init__(base=base, chars=True) 12 | self.last = 50 13 | 14 | def target_from_input_data(self, input_data): 15 | return input_data + list(reversed(input_data)) + input_data 16 | 17 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/algorithmic/reverse.py: -------------------------------------------------------------------------------- 1 | """ 2 | Task is to reverse content over the input tape. 3 | http://arxiv.org/abs/1511.07275 4 | """ 5 | 6 | import numpy as np 7 | from rand_param_envs.gym.envs.algorithmic import algorithmic_env 8 | 9 | class ReverseEnv(algorithmic_env.TapeAlgorithmicEnv): 10 | MIN_REWARD_SHORTFALL_FOR_PROMOTION = -.1 11 | def __init__(self, base=2): 12 | super(ReverseEnv, self).__init__(base=base, chars=True, starting_min_length=1) 13 | self.last = 50 14 | 15 | def target_from_input_data(self, input_str): 16 | return list(reversed(input_str)) 17 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/algorithmic/reversed_addition.py: -------------------------------------------------------------------------------- 1 | from __future__ import division 2 | import numpy as np 3 | from rand_param_envs.gym.envs.algorithmic import algorithmic_env 4 | 5 | class ReversedAdditionEnv(algorithmic_env.GridAlgorithmicEnv): 6 | def __init__(self, rows=2, base=3): 7 | super(ReversedAdditionEnv, self).__init__(rows=rows, base=base, chars=False) 8 | 9 | def target_from_input_data(self, input_strings): 10 | curry = 0 11 | target = [] 12 | for digits in input_strings: 13 | total = sum(digits) + curry 14 | target.append(total % self.base) 15 | curry = total // self.base 16 | 17 | if curry > 0: 18 | target.append(curry) 19 | return target 20 | 21 | @property 22 | def time_limit(self): 23 | # Quirk preserved for the sake of consistency: add the length of the input 24 | # rather than the length of the desired output (which may differ if there's 25 | # an extra carried digit). 26 | # TODO: It seems like this time limit is so strict as to make Addition3-v0 27 | # unsolvable, since agents aren't even given enough time steps to look at 28 | # all the digits. (The solutions on the scoreboard seem to only work by 29 | # save-scumming.) 30 | return self.input_width*2 + 4 31 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/algorithmic/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/algorithmic/tests/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/atari/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.envs.atari.atari_env import AtariEnv 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/board_game/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.envs.board_game.go import GoEnv 2 | from rand_param_envs.gym.envs.board_game.hex import HexEnv 3 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/box2d/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.envs.box2d.lunar_lander import LunarLander 2 | from rand_param_envs.gym.envs.box2d.lunar_lander import LunarLanderContinuous 3 | from rand_param_envs.gym.envs.box2d.bipedal_walker import BipedalWalker, BipedalWalkerHardcore 4 | from rand_param_envs.gym.envs.box2d.car_racing import CarRacing 5 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/classic_control/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.envs.classic_control.cartpole import CartPoleEnv 2 | from rand_param_envs.gym.envs.classic_control.mountain_car import MountainCarEnv 3 | from rand_param_envs.gym.envs.classic_control.continuous_mountain_car import Continuous_MountainCarEnv 4 | from rand_param_envs.gym.envs.classic_control.pendulum import PendulumEnv 5 | from rand_param_envs.gym.envs.classic_control.acrobot import AcrobotEnv 6 | 7 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/classic_control/assets/clockwise.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/classic_control/assets/clockwise.png -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/debugging/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.envs.debugging.one_round_deterministic_reward import OneRoundDeterministicRewardEnv 2 | from rand_param_envs.gym.envs.debugging.two_round_deterministic_reward import TwoRoundDeterministicRewardEnv 3 | from rand_param_envs.gym.envs.debugging.one_round_nondeterministic_reward import OneRoundNondeterministicRewardEnv 4 | from rand_param_envs.gym.envs.debugging.two_round_nondeterministic_reward import TwoRoundNondeterministicRewardEnv 5 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/debugging/one_round_deterministic_reward.py: -------------------------------------------------------------------------------- 1 | """ 2 | Simple environment with known optimal policy and value function. 3 | 4 | This environment has just two actions. 5 | Action 0 yields 0 reward and then terminates the session. 6 | Action 1 yields 1 reward and then terminates the session. 7 | 8 | Optimal policy: action 1. 9 | 10 | Optimal value function: v(0)=1 (there is only one state, state 0) 11 | """ 12 | 13 | from rand_param_envs import gym 14 | import random 15 | from rand_param_envs.gym import spaces 16 | 17 | class OneRoundDeterministicRewardEnv(gym.Env): 18 | def __init__(self): 19 | self.action_space = spaces.Discrete(2) 20 | self.observation_space = spaces.Discrete(1) 21 | self._reset() 22 | 23 | def _step(self, action): 24 | assert self.action_space.contains(action) 25 | if action: 26 | reward = 1 27 | else: 28 | reward = 0 29 | 30 | done = True 31 | return self._get_obs(), reward, done, {} 32 | 33 | def _get_obs(self): 34 | return 0 35 | 36 | def _reset(self): 37 | return self._get_obs() 38 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.envs.mujoco.mujoco_env import MujocoEnv 2 | # ^^^^^ so that user gets the correct error 3 | # message if mujoco is not installed correctly 4 | from rand_param_envs.gym.envs.mujoco.ant import AntEnv 5 | from rand_param_envs.gym.envs.mujoco.half_cheetah import HalfCheetahEnv 6 | from rand_param_envs.gym.envs.mujoco.hopper import HopperEnv 7 | from rand_param_envs.gym.envs.mujoco.walker2d import Walker2dEnv 8 | from rand_param_envs.gym.envs.mujoco.humanoid import HumanoidEnv 9 | from rand_param_envs.gym.envs.mujoco.inverted_pendulum import InvertedPendulumEnv 10 | from rand_param_envs.gym.envs.mujoco.inverted_double_pendulum import InvertedDoublePendulumEnv 11 | from rand_param_envs.gym.envs.mujoco.reacher import ReacherEnv 12 | from rand_param_envs.gym.envs.mujoco.swimmer import SwimmerEnv 13 | from rand_param_envs.gym.envs.mujoco.humanoidstandup import HumanoidStandupEnv 14 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/ant.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/ant.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/half_cheetah.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/half_cheetah.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/hopper.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/hopper.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/humanoid.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/humanoid.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/humanoidstandup.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/humanoidstandup.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/inverted_double_pendulum.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/inverted_double_pendulum.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/inverted_pendulum.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/inverted_pendulum.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/mujoco_env.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/mujoco_env.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/mujoco_env.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/mujoco_env.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/reacher.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/reacher.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/swimmer.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/swimmer.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/walker2d.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/__pycache__/walker2d.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/base.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/base.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/base_L.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/base_L.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/caster.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/caster.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/caster_L.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/caster_L.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/coffe_mate.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/coffe_mate.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/elbow_flex.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/elbow_flex.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/finger_tip_l.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/finger_tip_l.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/finger_tip_pad2_l.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/finger_tip_pad2_l.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/finger_tip_pad2_r.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/finger_tip_pad2_r.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/finger_tip_r.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/finger_tip_r.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/forearm.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/forearm.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/forearm_roll.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/forearm_roll.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/forearm_roll_L.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/forearm_roll_L.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/gripper_palm.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/gripper_palm.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/head_pan.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/head_pan.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/head_pan_L.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/head_pan_L.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/head_tilt.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/head_tilt.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/head_tilt_L.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/head_tilt_L.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/hok_tilt.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/hok_tilt.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/l_finger.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/l_finger.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/l_finger_tip.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/l_finger_tip.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/l_floating.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/l_floating.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/noddlesoup.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/noddlesoup.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/pr2_wheel.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/pr2_wheel.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/shoulder_lift.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/shoulder_lift.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/shoulder_pan.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/shoulder_pan.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/shoulder_yaw.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/shoulder_yaw.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/tilting_hokuyo.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/tilting_hokuyo.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/tilting_hokuyo_L.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/tilting_hokuyo_L.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/torso.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/torso.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/torso_lift.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/torso_lift.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/torso_lift_L.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/torso_lift_L.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_arm.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_arm.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_arm_roll.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_arm_roll.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_arm_roll_L.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_arm_roll_L.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_finger_l.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_finger_l.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_finger_r.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/upper_finger_r.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/wheel.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/wheel.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/white_rain.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/white_rain.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/windex.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/windex.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/wrist_flex.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/wrist_flex.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/wrist_roll.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/wrist_roll.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/wrist_roll_L.stl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/assets/meshes/wrist_roll_L.stl -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/half_cheetah.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from rand_param_envs.gym import utils 3 | from rand_param_envs.gym.envs.mujoco import mujoco_env 4 | 5 | class HalfCheetahEnv(mujoco_env.MujocoEnv, utils.EzPickle): 6 | def __init__(self): 7 | mujoco_env.MujocoEnv.__init__(self, 'half_cheetah.xml', 5) 8 | utils.EzPickle.__init__(self) 9 | 10 | def _step(self, action): 11 | xposbefore = self.model.data.qpos[0, 0] 12 | self.do_simulation(action, self.frame_skip) 13 | xposafter = self.model.data.qpos[0, 0] 14 | ob = self._get_obs() 15 | reward_ctrl = - 0.1 * np.square(action).sum() 16 | reward_run = (xposafter - xposbefore)/self.dt 17 | reward = reward_ctrl + reward_run 18 | done = False 19 | return ob, reward, done, dict(reward_run=reward_run, reward_ctrl=reward_ctrl) 20 | 21 | def _get_obs(self): 22 | return np.concatenate([ 23 | self.model.data.qpos.flat[1:], 24 | self.model.data.qvel.flat, 25 | ]) 26 | 27 | def reset_model(self): 28 | qpos = self.init_qpos + self.np_random.uniform(low=-.1, high=.1, size=self.model.nq) 29 | qvel = self.init_qvel + self.np_random.randn(self.model.nv) * .1 30 | self.set_state(qpos, qvel) 31 | return self._get_obs() 32 | 33 | def viewer_setup(self): 34 | self.viewer.cam.distance = self.model.stat.extent * 0.5 35 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/inverted_pendulum.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from rand_param_envs.gym import utils 3 | from rand_param_envs.gym.envs.mujoco import mujoco_env 4 | 5 | class InvertedPendulumEnv(mujoco_env.MujocoEnv, utils.EzPickle): 6 | def __init__(self): 7 | utils.EzPickle.__init__(self) 8 | mujoco_env.MujocoEnv.__init__(self, 'inverted_pendulum.xml', 2) 9 | 10 | def _step(self, a): 11 | reward = 1.0 12 | self.do_simulation(a, self.frame_skip) 13 | ob = self._get_obs() 14 | notdone = np.isfinite(ob).all() and (np.abs(ob[1]) <= .2) 15 | done = not notdone 16 | return ob, reward, done, {} 17 | 18 | def reset_model(self): 19 | qpos = self.init_qpos + self.np_random.uniform(size=self.model.nq, low=-0.01, high=0.01) 20 | qvel = self.init_qvel + self.np_random.uniform(size=self.model.nv, low=-0.01, high=0.01) 21 | self.set_state(qpos, qvel) 22 | return self._get_obs() 23 | 24 | def _get_obs(self): 25 | return np.concatenate([self.model.data.qpos, self.model.data.qvel]).ravel() 26 | 27 | def viewer_setup(self): 28 | v = self.viewer 29 | v.cam.trackbodyid = 0 30 | v.cam.distance = v.model.stat.extent 31 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/mujoco/swimmer.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from rand_param_envs.gym import utils 3 | from rand_param_envs.gym.envs.mujoco import mujoco_env 4 | 5 | class SwimmerEnv(mujoco_env.MujocoEnv, utils.EzPickle): 6 | def __init__(self): 7 | mujoco_env.MujocoEnv.__init__(self, 'swimmer.xml', 4) 8 | utils.EzPickle.__init__(self) 9 | 10 | def _step(self, a): 11 | ctrl_cost_coeff = 0.0001 12 | xposbefore = self.model.data.qpos[0, 0] 13 | self.do_simulation(a, self.frame_skip) 14 | xposafter = self.model.data.qpos[0, 0] 15 | reward_fwd = (xposafter - xposbefore) / self.dt 16 | reward_ctrl = - ctrl_cost_coeff * np.square(a).sum() 17 | reward = reward_fwd + reward_ctrl 18 | ob = self._get_obs() 19 | return ob, reward, False, dict(reward_fwd=reward_fwd, reward_ctrl=reward_ctrl) 20 | 21 | def _get_obs(self): 22 | qpos = self.model.data.qpos 23 | qvel = self.model.data.qvel 24 | return np.concatenate([qpos.flat[2:], qvel.flat]) 25 | 26 | def reset_model(self): 27 | self.set_state( 28 | self.init_qpos + self.np_random.uniform(low=-.1, high=.1, size=self.model.nq), 29 | self.init_qvel + self.np_random.uniform(low=-.1, high=.1, size=self.model.nv) 30 | ) 31 | return self._get_obs() 32 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/parameter_tuning/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.envs.parameter_tuning.convergence import ConvergenceControl 2 | from rand_param_envs.gym.envs.parameter_tuning.train_deep_cnn import CNNClassifierTraining 3 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/safety/README.md: -------------------------------------------------------------------------------- 1 | # Safety series README 2 | 3 | This README is to document AI safety issues that have not yet been addressed by the environments in the safety series. 4 | 5 | ## Possible envs 6 | - Wireheading / Delusion Box 7 | - IRL 8 | 9 | ## Impossible envs 10 | - Env modifying agents (breaks the cartesian barrier) 11 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/safety/__init__.py: -------------------------------------------------------------------------------- 1 | # interpretability envs 2 | from rand_param_envs.gym.envs.safety.predict_actions_cartpole import PredictActionsCartpoleEnv 3 | from rand_param_envs.gym.envs.safety.predict_obs_cartpole import PredictObsCartpoleEnv 4 | 5 | # semi_supervised envs 6 | from rand_param_envs.gym.envs.safety.semisuper import \ 7 | SemisuperPendulumNoiseEnv, SemisuperPendulumRandomEnv, SemisuperPendulumDecayEnv 8 | 9 | # off_switch envs 10 | from rand_param_envs.gym.envs.safety.offswitch_cartpole import OffSwitchCartpoleEnv 11 | from rand_param_envs.gym.envs.safety.offswitch_cartpole_prob import OffSwitchCartpoleProbEnv 12 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/tests/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/tests/spec_list.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym import envs 2 | import os 3 | import logging 4 | logger = logging.getLogger(__name__) 5 | 6 | def should_skip_env_spec_for_tests(spec): 7 | # We skip tests for envs that require dependencies or are otherwise 8 | # troublesome to run frequently 9 | ep = spec._entry_point 10 | # Skip mujoco tests for pull request CI 11 | skip_mujoco = not (os.environ.get('MUJOCO_KEY_BUNDLE') or os.path.exists(os.path.expanduser('~/.mujoco'))) 12 | if skip_mujoco and ep.startswith('gym.envs.mujoco:'): 13 | return True 14 | if ( spec.id.startswith("Go") or 15 | spec.id.startswith("Hex") or 16 | ep.startswith('gym.envs.box2d:') or 17 | ep.startswith('gym.envs.parameter_tuning:') or 18 | ep.startswith('gym.envs.safety:Semisuper') or 19 | (ep.startswith("gym.envs.atari") and not spec.id.startswith("Pong")) 20 | ): 21 | logger.warning("Skipping tests for env {}".format(ep)) 22 | return True 23 | return False 24 | 25 | spec_list = [spec for spec in sorted(envs.registry.all(), key=lambda x: x.id) if spec._entry_point is not None and not should_skip_env_spec_for_tests(spec)] 26 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/tests/test_safety_envs.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs import gym 2 | 3 | 4 | def test_semisuper_true_rewards(): 5 | env = gym.make('SemisuperPendulumNoise-v0') 6 | env.reset() 7 | 8 | observation, perceived_reward, done, info = env.step(env.action_space.sample()) 9 | true_reward = info['true_reward'] 10 | 11 | # The noise in the reward should ensure these are different. If we get spurious errors, we can remove this check 12 | assert perceived_reward != true_reward 13 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/envs/toy_text/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.envs.toy_text.blackjack import BlackjackEnv 2 | from rand_param_envs.gym.envs.toy_text.roulette import RouletteEnv 3 | from rand_param_envs.gym.envs.toy_text.frozen_lake import FrozenLakeEnv 4 | from rand_param_envs.gym.envs.toy_text.nchain import NChainEnv 5 | from rand_param_envs.gym.envs.toy_text.hotter_colder import HotterColder 6 | from rand_param_envs.gym.envs.toy_text.guessing_game import GuessingGame 7 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.monitoring.stats_recorder import StatsRecorder 2 | from rand_param_envs.gym.monitoring.video_recorder import VideoRecorder 3 | from rand_param_envs.gym.wrappers.monitoring import load_results, detect_training_manifests, load_env_info_from_manifests, _open_monitors -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/stats_recorder.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/stats_recorder.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/stats_recorder.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/stats_recorder.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/video_recorder.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/video_recorder.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/video_recorder.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/__pycache__/video_recorder.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/tests/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/monitoring/tests/helpers.py: -------------------------------------------------------------------------------- 1 | import contextlib 2 | import shutil 3 | import tempfile 4 | 5 | @contextlib.contextmanager 6 | def tempdir(): 7 | temp = tempfile.mkdtemp() 8 | yield temp 9 | shutil.rmtree(temp) 10 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/api.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/api.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/api.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/api.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/registration.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/registration.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/registration.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/__pycache__/registration.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/README.md: -------------------------------------------------------------------------------- 1 | # Client 2 | 3 | This client was forked from the (Stripe 4 | Python)[https://github.com/stripe/stripe-python] bindings. 5 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__init__.py: -------------------------------------------------------------------------------- 1 | import logging 2 | import os 3 | 4 | from rand_param_envs.gym import error 5 | 6 | logger = logging.getLogger(__name__) 7 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/api_requestor.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/api_requestor.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/api_requestor.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/api_requestor.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/http_client.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/http_client.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/http_client.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/http_client.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/resource.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/resource.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/resource.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/resource.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/util.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/util.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/util.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/__pycache__/util.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/tests/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/tests/helper.py: -------------------------------------------------------------------------------- 1 | import mock 2 | import unittest 3 | import uuid 4 | 5 | def fake_id(prefix): 6 | entropy = ''.join([a for a in str(uuid.uuid4()) if a.isalnum()]) 7 | return '{}_{}'.format(prefix, entropy) 8 | 9 | class APITestCase(unittest.TestCase): 10 | def setUp(self): 11 | super(APITestCase, self).setUp() 12 | self.requestor_patcher = mock.patch('gym.scoreboard.client.api_requestor.APIRequestor') 13 | requestor_class_mock = self.requestor_patcher.start() 14 | self.requestor_mock = requestor_class_mock.return_value 15 | 16 | def mock_response(self, res): 17 | self.requestor_mock.request = mock.Mock(return_value=(res, 'reskey')) 18 | 19 | class TestData(object): 20 | @classmethod 21 | def file_upload_response(cls): 22 | return { 23 | 'id': fake_id('file'), 24 | 'object': 'file', 25 | } 26 | 27 | @classmethod 28 | def evaluation_response(cls): 29 | return { 30 | 'id': fake_id('file'), 31 | 'object': 'evaluation', 32 | } 33 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/tests/test_evaluation.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.scoreboard.client.tests import helper 2 | from rand_param_envs.gym import scoreboard 3 | 4 | class EvaluationTest(helper.APITestCase): 5 | def test_create_evaluation(self): 6 | self.mock_response(helper.TestData.evaluation_response()) 7 | 8 | evaluation = scoreboard.Evaluation.create() 9 | assert isinstance(evaluation, scoreboard.Evaluation) 10 | 11 | self.requestor_mock.request.assert_called_with( 12 | 'post', 13 | '/v1/evaluations', 14 | {}, 15 | None 16 | ) 17 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/tests/test_file_upload.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.scoreboard.client.tests import helper 2 | from rand_param_envs.gym import scoreboard 3 | 4 | class FileUploadTest(helper.APITestCase): 5 | def test_create_file_upload(self): 6 | self.mock_response(helper.TestData.file_upload_response()) 7 | 8 | file_upload = scoreboard.FileUpload.create() 9 | assert isinstance(file_upload, scoreboard.FileUpload), 'File upload is: {!r}'.format(file_upload) 10 | 11 | self.requestor_mock.request.assert_called_with( 12 | 'post', 13 | '/v1/files', 14 | params={}, 15 | ) 16 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/client/util.py: -------------------------------------------------------------------------------- 1 | import logging 2 | import os 3 | import sys 4 | 5 | logger = logging.getLogger(__name__) 6 | 7 | def utf8(value): 8 | if isinstance(value, unicode) and sys.version_info < (3, 0): 9 | return value.encode('utf-8') 10 | else: 11 | return value 12 | 13 | def file_size(f): 14 | return os.fstat(f.fileno()).st_size 15 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/tests/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/scoreboard/tests/test_registration.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.scoreboard import registration 2 | 3 | def test_correct_registration(): 4 | try: 5 | registration.registry.finalize(strict=True) 6 | except registration.RegistrationError as e: 7 | assert False, "Caught: {}".format(e) 8 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.spaces.box import Box 2 | from rand_param_envs.gym.spaces.discrete import Discrete 3 | from rand_param_envs.gym.spaces.multi_discrete import MultiDiscrete, DiscreteToMultiDiscrete, BoxToMultiDiscrete 4 | from rand_param_envs.gym.spaces.multi_binary import MultiBinary 5 | from rand_param_envs.gym.spaces.prng import seed 6 | from rand_param_envs.gym.spaces.tuple_space import Tuple 7 | 8 | __all__ = ["Box", "Discrete", "MultiDiscrete", "DiscreteToMultiDiscrete", "BoxToMultiDiscrete", "MultiBinary", "Tuple"] 9 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/box.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/box.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/box.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/box.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/discrete.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/discrete.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/discrete.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/discrete.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/multi_binary.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/multi_binary.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/multi_binary.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/multi_binary.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/multi_discrete.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/multi_discrete.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/multi_discrete.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/multi_discrete.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/prng.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/prng.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/prng.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/prng.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/tuple_space.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/tuple_space.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/tuple_space.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/__pycache__/tuple_space.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/discrete.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | from rand_param_envs import gym 4 | import time 5 | from rand_param_envs.gym.spaces import prng 6 | 7 | class Discrete(gym.Space): 8 | """ 9 | {0,1,...,n-1} 10 | 11 | Example usage: 12 | self.observation_space = spaces.Discrete(2) 13 | """ 14 | def __init__(self, n): 15 | self.n = n 16 | def sample(self): 17 | return prng.np_random.randint(self.n) 18 | def contains(self, x): 19 | if isinstance(x, int): 20 | as_int = x 21 | elif isinstance(x, (np.generic, np.ndarray)) and (x.dtype.kind in np.typecodes['AllInteger'] and x.shape == ()): 22 | as_int = int(x) 23 | else: 24 | return False 25 | return as_int >= 0 and as_int < self.n 26 | def __repr__(self): 27 | return "Discrete(%d)" % self.n 28 | def __eq__(self, other): 29 | return self.n == other.n 30 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/multi_binary.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs import gym 2 | from rand_param_envs.gym.spaces import prng 3 | import numpy as np 4 | 5 | class MultiBinary(gym.Space): 6 | def __init__(self, n): 7 | self.n = n 8 | def sample(self): 9 | return prng.np_random.randint(low=0, high=2, size=self.n) 10 | def contains(self, x): 11 | return ((x==0) | (x==1)).all() 12 | def to_jsonable(self, sample_n): 13 | return sample_n.tolist() 14 | def from_jsonable(self, sample_n): 15 | return np.array(sample_n) -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/prng.py: -------------------------------------------------------------------------------- 1 | import numpy 2 | 3 | np_random = numpy.random.RandomState() 4 | 5 | def seed(seed=None): 6 | """Seed the common numpy.random.RandomState used in spaces 7 | 8 | CF 9 | https://github.com/openai/gym/commit/58e6aa95e5af2c738557431f812abb81c505a7cf#commitcomment-17669277 10 | for some details about why we seed the spaces separately from the 11 | envs, but tl;dr is that it's pretty uncommon for them to be used 12 | within an actual algorithm, and the code becomes simpler to just 13 | use this common numpy.random.RandomState. 14 | """ 15 | np_random.seed(seed) 16 | 17 | # This numpy.random.RandomState gets used in all spaces for their 18 | # 'sample' method. It's not really expected that people will be using 19 | # these in their algorithms. 20 | seed(0) 21 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/tests/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/tests/test_spaces.py: -------------------------------------------------------------------------------- 1 | import json # note: ujson fails this test due to float equality 2 | import numpy as np 3 | import pytest 4 | from rand_param_envs.gym.spaces import Tuple, Box, Discrete, MultiDiscrete 5 | 6 | 7 | @pytest.mark.parametrize("space", [ 8 | Discrete(3), 9 | Tuple([Discrete(5), Discrete(10)]), 10 | Tuple([Discrete(5), Box(np.array([0,0]),np.array([1,5]))]), 11 | Tuple((Discrete(5), Discrete(2), Discrete(2))), 12 | MultiDiscrete([ [0, 1], [0, 1], [0, 100] ]) 13 | ]) 14 | def test_roundtripping(space): 15 | sample_1 = space.sample() 16 | sample_2 = space.sample() 17 | assert space.contains(sample_1) 18 | assert space.contains(sample_2) 19 | json_rep = space.to_jsonable([sample_1, sample_2]) 20 | 21 | json_roundtripped = json.loads(json.dumps(json_rep)) 22 | 23 | samples_after_roundtrip = space.from_jsonable(json_roundtripped) 24 | sample_1_prime, sample_2_prime = samples_after_roundtrip 25 | 26 | s1 = space.to_jsonable([sample_1]) 27 | s1p = space.to_jsonable([sample_1_prime]) 28 | s2 = space.to_jsonable([sample_2]) 29 | s2p = space.to_jsonable([sample_2_prime]) 30 | assert s1 == s1p, "Expected {} to equal {}".format(s1, s1p) 31 | assert s2 == s2p, "Expected {} to equal {}".format(s2, s2p) 32 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/spaces/tuple_space.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym import Space 2 | 3 | class Tuple(Space): 4 | """ 5 | A tuple (i.e., product) of simpler spaces 6 | 7 | Example usage: 8 | self.observation_space = spaces.Tuple((spaces.Discrete(2), spaces.Discrete(3))) 9 | """ 10 | def __init__(self, spaces): 11 | self.spaces = spaces 12 | 13 | def sample(self): 14 | return tuple([space.sample() for space in self.spaces]) 15 | 16 | def contains(self, x): 17 | if isinstance(x, list): 18 | x = tuple(x) # Promote list to tuple for contains check 19 | return isinstance(x, tuple) and len(x) == len(self.spaces) and all( 20 | space.contains(part) for (space,part) in zip(self.spaces,x)) 21 | 22 | def __repr__(self): 23 | return "Tuple(" + ", ". join([str(s) for s in self.spaces]) + ")" 24 | 25 | def to_jsonable(self, sample_n): 26 | # serialize as list-repr of tuple of vectors 27 | return [space.to_jsonable([sample[i] for sample in sample_n]) \ 28 | for i, space in enumerate(self.spaces)] 29 | 30 | def from_jsonable(self, sample_n): 31 | return zip(*[space.from_jsonable(sample_n[i]) for i, space in enumerate(self.spaces)]) 32 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/tests/test_core.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym import core 2 | 3 | class ArgumentEnv(core.Env): 4 | calls = 0 5 | 6 | def __init__(self, arg): 7 | self.calls += 1 8 | self.arg = arg 9 | 10 | def test_env_instantiation(): 11 | # This looks like a pretty trivial, but given our usage of 12 | # __new__, it's worth having. 13 | env = ArgumentEnv('arg') 14 | assert env.arg == 'arg' 15 | assert env.calls == 1 16 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__init__.py: -------------------------------------------------------------------------------- 1 | """A set of common utilities used within the environments. These are 2 | not intended as API functions, and will not remain stable over time. 3 | """ 4 | 5 | # These submodules should not have any import-time dependencies. 6 | # We want this since we use `utils` during our import-time sanity checks 7 | # that verify that our dependencies are actually present. 8 | from .colorize import colorize 9 | from .ezpickle import EzPickle 10 | from .reraise import reraise 11 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/atomic_write.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/atomic_write.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/atomic_write.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/atomic_write.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/closer.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/closer.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/closer.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/closer.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/colorize.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/colorize.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/colorize.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/colorize.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/ezpickle.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/ezpickle.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/ezpickle.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/ezpickle.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/json_utils.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/json_utils.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/json_utils.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/json_utils.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/reraise.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/reraise.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/reraise.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/reraise.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/reraise_impl_py3.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/reraise_impl_py3.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/reraise_impl_py3.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/reraise_impl_py3.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/seeding.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/seeding.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/seeding.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/__pycache__/seeding.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/colorize.py: -------------------------------------------------------------------------------- 1 | """A set of common utilities used within the environments. These are 2 | not intended as API functions, and will not remain stable over time. 3 | """ 4 | 5 | color2num = dict( 6 | gray=30, 7 | red=31, 8 | green=32, 9 | yellow=33, 10 | blue=34, 11 | magenta=35, 12 | cyan=36, 13 | white=37, 14 | crimson=38 15 | ) 16 | 17 | 18 | def colorize(string, color, bold=False, highlight = False): 19 | """Return string surrounded by appropriate terminal color codes to 20 | print colorized text. Valid colors: gray, red, green, yellow, 21 | blue, magenta, cyan, white, crimson 22 | """ 23 | 24 | # Import six here so that `utils` has no import-time dependencies. 25 | # We want this since we use `utils` during our import-time sanity checks 26 | # that verify that our dependencies (including six) are actually present. 27 | import six 28 | 29 | attr = [] 30 | num = color2num[color] 31 | if highlight: num += 10 32 | attr.append(six.u(str(num))) 33 | if bold: attr.append(six.u('1')) 34 | attrs = six.u(';').join(attr) 35 | return six.u('\x1b[%sm%s\x1b[0m') % (attrs, string) 36 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/ezpickle.py: -------------------------------------------------------------------------------- 1 | class EzPickle(object): 2 | """Objects that are pickled and unpickled via their constructor 3 | arguments. 4 | 5 | Example usage: 6 | 7 | class Dog(Animal, EzPickle): 8 | def __init__(self, furcolor, tailkind="bushy"): 9 | Animal.__init__() 10 | EzPickle.__init__(furcolor, tailkind) 11 | ... 12 | 13 | When this object is unpickled, a new Dog will be constructed by passing the provided 14 | furcolor and tailkind into the constructor. However, philosophers are still not sure 15 | whether it is still the same dog. 16 | 17 | This is generally needed only for environments which wrap C/C++ code, such as MuJoCo 18 | and Atari. 19 | """ 20 | def __init__(self, *args, **kwargs): 21 | self._ezpickle_args = args 22 | self._ezpickle_kwargs = kwargs 23 | def __getstate__(self): 24 | return {"_ezpickle_args" : self._ezpickle_args, "_ezpickle_kwargs": self._ezpickle_kwargs} 25 | def __setstate__(self, d): 26 | out = type(self)(*d["_ezpickle_args"], **d["_ezpickle_kwargs"]) 27 | self.__dict__.update(out.__dict__) 28 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/json_utils.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | def json_encode_np(obj): 4 | """ 5 | JSON can't serialize numpy types, so convert to pure python 6 | """ 7 | if isinstance(obj, np.ndarray): 8 | return list(obj) 9 | elif isinstance(obj, np.float32): 10 | return float(obj) 11 | elif isinstance(obj, np.float64): 12 | return float(obj) 13 | elif isinstance(obj, np.int32): 14 | return int(obj) 15 | elif isinstance(obj, np.int64): 16 | return int(obj) 17 | else: 18 | return obj 19 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/reraise_impl_py2.py: -------------------------------------------------------------------------------- 1 | def reraise_impl(e, traceback): 2 | raise e.__class__, e, traceback 3 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/reraise_impl_py3.py: -------------------------------------------------------------------------------- 1 | # http://stackoverflow.com/a/33822606 -- `from None` disables Python 3' 2 | # semi-smart exception chaining, which we don't want in this case. 3 | def reraise_impl(e, traceback): 4 | raise e.with_traceback(traceback) from None 5 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/tests/test_atexit.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym.utils.closer import Closer 2 | 3 | class Closeable(object): 4 | close_called = False 5 | def close(self): 6 | self.close_called = True 7 | 8 | def test_register_unregister(): 9 | registry = Closer(atexit_register=False) 10 | c1 = Closeable() 11 | c2 = Closeable() 12 | 13 | assert not c1.close_called 14 | assert not c2.close_called 15 | registry.register(c1) 16 | id2 = registry.register(c2) 17 | 18 | registry.unregister(id2) 19 | registry.close() 20 | assert c1.close_called 21 | assert not c2.close_called 22 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/utils/tests/test_seeding.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym import error 2 | from rand_param_envs.gym.utils import seeding 3 | 4 | def test_invalid_seeds(): 5 | for seed in [-1, 'test']: 6 | try: 7 | seeding.np_random(seed) 8 | except error.Error: 9 | pass 10 | else: 11 | assert False, 'Invalid seed {} passed validation'.format(seed) 12 | 13 | def test_valid_seeds(): 14 | for seed in [0, 1]: 15 | random, seed1 = seeding.np_random(seed) 16 | assert seed == seed1 17 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/version.py: -------------------------------------------------------------------------------- 1 | VERSION = '0.7.4' 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__init__.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs.gym import error 2 | from rand_param_envs.gym.wrappers.frame_skipping import SkipWrapper 3 | from rand_param_envs.gym.wrappers.monitoring import Monitor 4 | from rand_param_envs.gym.wrappers.time_limit import TimeLimit 5 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/frame_skipping.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/frame_skipping.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/frame_skipping.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/frame_skipping.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/monitoring.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/monitoring.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/monitoring.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/monitoring.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/time_limit.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/time_limit.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/time_limit.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/__pycache__/time_limit.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/frame_skipping.py: -------------------------------------------------------------------------------- 1 | from rand_param_envs import gym 2 | 3 | __all__ = ['SkipWrapper'] 4 | 5 | def SkipWrapper(repeat_count): 6 | class SkipWrapper(gym.Wrapper): 7 | """ 8 | Generic common frame skipping wrapper 9 | Will perform action for `x` additional steps 10 | """ 11 | def __init__(self, env): 12 | super(SkipWrapper, self).__init__(env) 13 | self.repeat_count = repeat_count 14 | self.stepcount = 0 15 | 16 | def _step(self, action): 17 | done = False 18 | total_reward = 0 19 | current_step = 0 20 | while current_step < (self.repeat_count + 1) and not done: 21 | self.stepcount += 1 22 | obs, reward, done, info = self.env.step(action) 23 | total_reward += reward 24 | current_step += 1 25 | if 'skip.stepcount' in info: 26 | raise gym.error.Error('Key "skip.stepcount" already in info. Make sure you are not stacking ' \ 27 | 'the SkipWrapper wrappers.') 28 | info['skip.stepcount'] = self.stepcount 29 | return obs, total_reward, done, info 30 | 31 | def _reset(self): 32 | self.stepcount = 0 33 | return self.env.reset() 34 | 35 | return SkipWrapper 36 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/gym/wrappers/tests/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/.ruby-version: -------------------------------------------------------------------------------- 1 | ruby-2.1.0 2 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/Gemfile: -------------------------------------------------------------------------------- 1 | source 'https://rubygems.org' 2 | 3 | gem 'pry' 4 | gem 'activesupport' 5 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/Gemfile.lock: -------------------------------------------------------------------------------- 1 | GEM 2 | remote: https://rubygems.org/ 3 | specs: 4 | activesupport (4.1.8) 5 | i18n (~> 0.6, >= 0.6.9) 6 | json (~> 1.7, >= 1.7.7) 7 | minitest (~> 5.1) 8 | thread_safe (~> 0.1) 9 | tzinfo (~> 1.1) 10 | coderay (1.1.0) 11 | i18n (0.7.0) 12 | json (1.8.1) 13 | method_source (0.8.2) 14 | minitest (5.5.1) 15 | pry (0.10.1) 16 | coderay (~> 1.1.0) 17 | method_source (~> 0.8.1) 18 | slop (~> 3.4) 19 | slop (3.6.0) 20 | thread_safe (0.3.4) 21 | tzinfo (1.2.2) 22 | thread_safe (~> 0.1) 23 | 24 | PLATFORMS 25 | ruby 26 | 27 | DEPENDENCIES 28 | activesupport 29 | pry 30 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__init__.py: -------------------------------------------------------------------------------- 1 | from .config import init_config, get_key_path 2 | #init_config() 3 | 4 | from .mjviewer import MjViewer 5 | from .mjcore import MjModel 6 | from .mjcore import register_license 7 | from .mjconstants import * 8 | from .platname_targdir import targdir 9 | 10 | register_license(get_key_path()) 11 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/config.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/config.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/config.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/config.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/error.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/error.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/error.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/error.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/glfw.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/glfw.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjconstants.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjconstants.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjconstants.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjconstants.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjcore.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjcore.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjcore.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjcore.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjlib.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjlib.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjlib.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjlib.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjtypes.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjtypes.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjtypes.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjtypes.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjviewer.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjviewer.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjviewer.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/mjviewer.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/platname_targdir.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/platname_targdir.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/util.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/util.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/util.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/__pycache__/util.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/error.py: -------------------------------------------------------------------------------- 1 | class Error(Exception): 2 | pass 3 | 4 | class MujocoDependencyError(Error): 5 | pass 6 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/gen_binding.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | parent_path=$( cd "$(dirname "${BASH_SOURCE}")" ; pwd -P ) 3 | mujoco_path=$MUJOCO_PY_BUNDLE_PATH/osx/mujoco 4 | rm /tmp/code_gen_mujoco.h 5 | cat $mujoco_path/mjdata.h >> /tmp/code_gen_mujoco.h && \ 6 | cat $mujoco_path/mjmodel.h >> /tmp/code_gen_mujoco.h && \ 7 | cat $mujoco_path/mjrender.h >> /tmp/code_gen_mujoco.h && \ 8 | cat $mujoco_path/mjvisualize.h >> /tmp/code_gen_mujoco.h && \ 9 | ruby $parent_path/codegen.rb /tmp/code_gen_mujoco.h $mujoco_path/mjxmacro.h > $parent_path/mjtypes.py 10 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/mjconstants.py: -------------------------------------------------------------------------------- 1 | MOUSE_ROTATE_V = 1 2 | MOUSE_ROTATE_H = 2 3 | MOUSE_MOVE_V = 3 4 | MOUSE_MOVE_H = 4 5 | MOUSE_ZOOM = 5 6 | 7 | mjOBJ_BODY = 1 8 | mjOBJ_JOINT = 2 9 | 10 | mjJNT_FREE = 0 11 | mjJNT_BALL = 1 12 | mjJNT_SLIDE = 2 13 | mjJNT_HINGE = 3 14 | 15 | # mjtCatBit - geom categories 16 | mjCAT_STATIC = 1 17 | mjCAT_DYNAMIC = 2 18 | mjCAT_DECOR = 4 19 | mjCAT_ALL = 7 20 | 21 | # mjtPertBit - mouse perturbation 22 | mjPERT_TRANSLATE = 1 23 | mjPERT_ROTATE = 2 24 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/mjextra.py: -------------------------------------------------------------------------------- 1 | def append_objects(cur, extra): 2 | for i in range(cur.ngeom, cur.ngeom + extra.ngeom): 3 | cur.geoms[i] = extra.geoms[i - cur.ngeom] 4 | cur.ngeom = cur.ngeom + extra.ngeom 5 | if cur.ngeom > cur.maxgeom: 6 | raise ValueError("buffer limit exceeded!") 7 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rand_param_envs/mujoco_py/platname_targdir.py: -------------------------------------------------------------------------------- 1 | import sys 2 | if sys.platform.startswith("darwin"): 3 | platname = "osx" 4 | elif sys.platform.startswith("linux"): 5 | platname = "linux" 6 | elif sys.platform.startswith("windows"): 7 | platname = "win" 8 | targdir = "mujoco_%s"%platname 9 | 10 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/core/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | General classes, functions, utilities that are used throughout rlkit. 3 | """ -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/eval_util.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/eval_util.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/logger.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/logger.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/rl_algorithm.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/rl_algorithm.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/serializable.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/serializable.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/tabulate.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/tabulate.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/util.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/core/__pycache__/util.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/core/util.py: -------------------------------------------------------------------------------- 1 | class Wrapper(object): 2 | """ 3 | Mixin for deferring attributes to a wrapped, inner object. 4 | """ 5 | 6 | def __init__(self, inner): 7 | self.inner = inner 8 | 9 | def __getattr__(self, attr): 10 | """ 11 | Dispatch attributes by their status as magic, members, or missing. 12 | - magic is handled by the standard getattr 13 | - existing attributes are returned 14 | - missing attributes are deferred to the inner object. 15 | """ 16 | # don't make magic any more magical 17 | is_magic = attr.startswith('__') and attr.endswith('__') 18 | if is_magic: 19 | return super().__getattr__(attr) 20 | try: 21 | # try to return the attribute... 22 | return self.__dict__[attr] 23 | except: 24 | # ...and defer to the inner dataset if it's not here 25 | return getattr(self.inner, attr) 26 | 27 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/data_management/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/data_management/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/env_replay_buffer.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/env_replay_buffer.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/normalizer.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/normalizer.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/path_builder.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/path_builder.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/replay_buffer.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/replay_buffer.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/simple_replay_buffer.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/data_management/__pycache__/simple_replay_buffer.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__init__.py: -------------------------------------------------------------------------------- 1 | import os 2 | import importlib 3 | 4 | 5 | ENVS = {} 6 | 7 | 8 | def register_env(name): 9 | """Registers a env by name for instantiation in rlkit.""" 10 | 11 | def register_env_fn(fn): 12 | if name in ENVS: 13 | raise ValueError("Cannot register duplicate env {}".format(name)) 14 | if not callable(fn): 15 | raise TypeError("env {} must be callable".format(name)) 16 | ENVS[name] = fn 17 | return fn 18 | 19 | return register_env_fn 20 | 21 | 22 | # automatically import any envs in the envs/ directory 23 | for file in os.listdir(os.path.dirname(__file__)): 24 | if file.endswith('.py') and not file.startswith('_') and not file.startswith('walker') and not file.startswith('hopper'): 25 | module = file[:file.find('.py')] 26 | importlib.import_module('rlkit.envs.' + module) 27 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant_dir.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant_dir.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant_goal.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant_goal.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant_multitask_base.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant_multitask_base.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant_multitask_base.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ant_multitask_base.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/fetch_pickandplace.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/fetch_pickandplace.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/fetch_push.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/fetch_push.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/fetch_reach.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/fetch_reach.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/fetch_slide.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/fetch_slide.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah_damping.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah_damping.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah_dir.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah_dir.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah_mass.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah_mass.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah_vel.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/half_cheetah_vel.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/humanoid_dir.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/humanoid_dir.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ml1.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ml1.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ml10.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ml10.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ml45.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/ml45.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/mujoco_env.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/mujoco_env.cpython-35.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/mujoco_env.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/mujoco_env.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/nwalker_vel.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/nwalker_vel.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/point_robot.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/point_robot.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/reacher_goal.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/reacher_goal.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/sparse_point_robot.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/sparse_point_robot.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/walker_rand_params_wrapper.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/walker_rand_params_wrapper.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/wrappers.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/envs/__pycache__/wrappers.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/ant_multitask_base.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | from rlkit.envs.ant import AntEnv 4 | # from gym.envs.mujoco.ant import AntEnv 5 | 6 | class MultitaskAntEnv(AntEnv): 7 | def __init__(self, task={}, n_tasks=2, **kwargs): 8 | self._task = task 9 | self.tasks = self.sample_tasks(n_tasks) 10 | self._goal = self.tasks[0]['goal'] 11 | super(MultitaskAntEnv, self).__init__(**kwargs) 12 | 13 | """ 14 | def step(self, action): 15 | xposbefore = self.sim.data.qpos[0] 16 | self.do_simulation(action, self.frame_skip) 17 | xposafter = self.sim.data.qpos[0] 18 | 19 | forward_vel = (xposafter - xposbefore) / self.dt 20 | forward_reward = -1.0 * abs(forward_vel - self._goal_vel) 21 | ctrl_cost = 0.5 * 1e-1 * np.sum(np.square(action)) 22 | 23 | observation = self._get_obs() 24 | reward = forward_reward - ctrl_cost 25 | done = False 26 | infos = dict(reward_forward=forward_reward, 27 | reward_ctrl=-ctrl_cost, task=self._task) 28 | return (observation, reward, done, infos) 29 | """ 30 | 31 | 32 | def get_all_task_idx(self): 33 | return range(len(self.tasks)) 34 | 35 | def reset_task(self, idx): 36 | self._task = self.tasks[idx] 37 | self._goal = self._task['goal'] # assume parameterization of task by single vector 38 | self.reset() 39 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/half_cheetah.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from gym.envs.mujoco import HalfCheetahEnv as HalfCheetahEnv_ 3 | 4 | class HalfCheetahEnv(HalfCheetahEnv_): 5 | def _get_obs(self): 6 | return np.concatenate([ 7 | self.sim.data.qpos.flat[1:], 8 | self.sim.data.qvel.flat, 9 | self.get_body_com("torso").flat, 10 | ]).astype(np.float32).flatten() 11 | 12 | def viewer_setup(self): 13 | camera_id = self.model.camera_name2id('track') 14 | self.viewer.cam.type = 2 15 | self.viewer.cam.fixedcamid = camera_id 16 | self.viewer.cam.distance = self.model.stat.extent * 0.35 17 | # Hide the overlay 18 | self.viewer._hide_overlay = True 19 | 20 | def render(self, mode='human'): 21 | if mode == 'rgb_array': 22 | self._get_viewer().render() 23 | # window size used for old mujoco-py: 24 | width, height = 500, 500 25 | data = self._get_viewer().read_pixels(width, height, depth=False) 26 | return data 27 | elif mode == 'human': 28 | self._get_viewer().render() 29 | 30 | 31 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/hopper_rand_params_wrapper.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from rand_param_envs.hopper_rand_params import HopperRandParamsEnv 3 | 4 | from . import register_env 5 | 6 | 7 | @register_env('hopper-rand-params') 8 | class HopperRandParamsWrappedEnv(HopperRandParamsEnv): 9 | def __init__(self, n_tasks=2, randomize_tasks=True): 10 | super(HopperRandParamsWrappedEnv, self).__init__() 11 | self.tasks = self.sample_tasks(n_tasks) 12 | self.reset_task(0) 13 | 14 | def get_all_task_idx(self): 15 | return range(len(self.tasks)) 16 | 17 | def reset_task(self, idx): 18 | self._task = self.tasks[idx] 19 | self._goal = idx 20 | self.set_task(self._task) 21 | self.reset() 22 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/envs/walker_rand_params_wrapper.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from rand_param_envs.walker2d_rand_params import Walker2DRandParamsEnv 3 | 4 | from . import register_env 5 | 6 | 7 | @register_env('walker-rand-params') 8 | class WalkerRandParamsWrappedEnv(Walker2DRandParamsEnv): 9 | def __init__(self, n_tasks=2, randomize_tasks=True): 10 | super(WalkerRandParamsWrappedEnv, self).__init__() 11 | self.tasks = self.sample_tasks(n_tasks) 12 | self.reset_task(0) 13 | 14 | def get_all_task_idx(self): 15 | return range(len(self.tasks)) 16 | 17 | def reset_task(self, idx): 18 | self._task = self.tasks[idx] 19 | self._goal = idx 20 | self.set_task(self._task) 21 | self.reset() 22 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/launchers/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | This module contains 'launchers', which are self-contained functions that take 3 | one dictionary and run a full experiment. The dictionary configures the 4 | experiment. 5 | 6 | It is important that the functions are completely self-contained (i.e. they 7 | import their own modules) so that they can be serialized. 8 | """ 9 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/launchers/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/launchers/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/launchers/__pycache__/config.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/launchers/__pycache__/config.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/launchers/__pycache__/launcher_util.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/launchers/__pycache__/launcher_util.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/launchers/config.py: -------------------------------------------------------------------------------- 1 | # Change this 2 | LOCAL_LOG_DIR = 'output' 3 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/policies/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/policies/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/policies/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/policies/__pycache__/base.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/policies/__pycache__/base.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/policies/argmax.py: -------------------------------------------------------------------------------- 1 | """ 2 | Torch argmax policy 3 | """ 4 | import numpy as np 5 | import rlkit.torch.pytorch_util as ptu 6 | from rlkit.policies.base import SerializablePolicy 7 | from rlkit.torch.core import PyTorchModule 8 | 9 | 10 | class ArgmaxDiscretePolicy(PyTorchModule, SerializablePolicy): 11 | def __init__(self, qf): 12 | self.save_init_params(locals()) 13 | super().__init__() 14 | self.qf = qf 15 | 16 | def get_action(self, obs): 17 | obs = np.expand_dims(obs, axis=0) 18 | obs = ptu.from_numpy(obs).float() 19 | q_values = self.qf(obs).squeeze(0) 20 | q_values_np = ptu.get_numpy(q_values) 21 | return q_values_np.argmax(), {} 22 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/policies/base.py: -------------------------------------------------------------------------------- 1 | import abc 2 | 3 | 4 | class Policy(object, metaclass=abc.ABCMeta): 5 | """ 6 | General policy interface. 7 | """ 8 | @abc.abstractmethod 9 | def get_action(self, observation): 10 | """ 11 | 12 | :param observation: 13 | :return: action, debug_dictionary 14 | """ 15 | pass 16 | 17 | def reset(self): 18 | pass 19 | 20 | 21 | class ExplorationPolicy(Policy, metaclass=abc.ABCMeta): 22 | def set_num_steps_total(self, t): 23 | pass 24 | 25 | 26 | class SerializablePolicy(Policy, metaclass=abc.ABCMeta): 27 | """ 28 | Policy that can be serialized. 29 | """ 30 | def get_param_values(self): 31 | return None 32 | 33 | def set_param_values(self, values): 34 | pass 35 | 36 | """ 37 | Parameters should be passed as np arrays in the two functions below. 38 | """ 39 | def get_param_values_np(self): 40 | return None 41 | 42 | def set_param_values_np(self, values): 43 | pass 44 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/policies/simple.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | from rlkit.policies.base import SerializablePolicy 4 | 5 | 6 | class RandomPolicy(SerializablePolicy): 7 | """ 8 | Policy that always outputs zero. 9 | """ 10 | 11 | def __init__(self, action_space): 12 | self.action_space = action_space 13 | 14 | def get_action(self, obs): 15 | return self.action_space.sample(), {} 16 | -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/samplers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/samplers/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/samplers/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/samplers/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/samplers/__pycache__/in_place.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/samplers/__pycache__/in_place.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/samplers/__pycache__/util.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/samplers/__pycache__/util.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/core.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/core.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/distributions.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/distributions.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/modules.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/modules.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/networks.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/networks.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/pytorch_util.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/__pycache__/pytorch_util.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/data_management/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/data_management/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/data_management/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/data_management/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/data_management/__pycache__/normalizer.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/data_management/__pycache__/normalizer.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/sac/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/sac/__init__.py -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/sac/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/sac/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/sac/__pycache__/agent.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/sac/__pycache__/agent.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/sac/__pycache__/policies.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/sac/__pycache__/policies.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Environment_Representation/ccm/rlkit/torch/sac/__pycache__/sac.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Environment_Representation/ccm/rlkit/torch/sac/__pycache__/sac.cpython-36.pyc -------------------------------------------------------------------------------- /RL_with_Other_Representations/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Other_Representations/.gitkeep -------------------------------------------------------------------------------- /RL_with_Other_Representations/README.md: -------------------------------------------------------------------------------- 1 | # RL with Other Representation 2 | 3 | As we have already proposed a taxonomy which contains four major categories. 4 | We use this repo to contain the works on representation in RL which cannot be exactly divided into the four major categories. 5 | 6 | A finer taxnomy may be proposed if the number of works contained in this category grows to a certain scale. 7 | 8 | ## An Overall View of Research Works in This Repo 9 | 10 | This repo will be constantly updated to include new researches made by TJU-RL-Lab. 11 | (The development of this repo is in progress at present.) 12 | 13 | | Method | Is Contained | Is ReadME Prepared | Author | Publication | Link | 14 | | ------ | --- | --- | ------ | ------ | ------ | 15 | | [VDFP](./VDFP) | ✅ | ✅ | Hongyao Tang | AAAI 2021 | https://ojs.aaai.org/index.php/AAAI/article/view/17182 | 16 | 17 | 18 | ## Installation 19 | 20 | The algorithms in this repo are all implemented **python 3.5** (and versions above). **Tensorflow 1.x** and **PyTorch** are the main DL code frameworks we adopt in this repo with different choices in different algorithms. 21 | 22 | Note that the algorithms contained in this repo may not use all the same environments. Please check the README of specific algorithms for detailed installation guidance. 23 | 24 | 25 | -------------------------------------------------------------------------------- /RL_with_Other_Representations/VDFP/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Other_Representations/VDFP/.gitkeep -------------------------------------------------------------------------------- /RL_with_Other_Representations/VDFP/assets/VDFP_framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Other_Representations/VDFP/assets/VDFP_framework.png -------------------------------------------------------------------------------- /RL_with_Policy_Representation/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Policy_Representation/.gitkeep -------------------------------------------------------------------------------- /RL_with_Policy_Representation/Policy-based_RL_with_PeVFA/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Policy_Representation/Policy-based_RL_with_PeVFA/.gitkeep -------------------------------------------------------------------------------- /RL_with_Policy_Representation/Policy-based_RL_with_PeVFA/PPO-PeVFA/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Policy_Representation/Policy-based_RL_with_PeVFA/PPO-PeVFA/.gitkeep -------------------------------------------------------------------------------- /RL_with_Policy_Representation/Policy-based_RL_with_PeVFA/PPO-PeVFA/networks/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Policy_Representation/Policy-based_RL_with_PeVFA/PPO-PeVFA/networks/.gitkeep -------------------------------------------------------------------------------- /RL_with_Policy_Representation/Value-based_RL_with_PeVFA/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_Policy_Representation/Value-based_RL_with_PeVFA/.gitkeep -------------------------------------------------------------------------------- /RL_with_State_Representation/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/RL_with_State_Representation/.gitkeep -------------------------------------------------------------------------------- /assets/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/.gitkeep -------------------------------------------------------------------------------- /assets/Ecology_of_SSRL.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/Ecology_of_SSRL.png -------------------------------------------------------------------------------- /assets/alg_framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/alg_framework.png -------------------------------------------------------------------------------- /assets/ar_readme_figs/ar_framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/ar_readme_figs/ar_framework.png -------------------------------------------------------------------------------- /assets/er_readme_figs/ER_framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/er_readme_figs/ER_framework.png -------------------------------------------------------------------------------- /assets/hyar_results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/hyar_results.png -------------------------------------------------------------------------------- /assets/pandr_results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/pandr_results.png -------------------------------------------------------------------------------- /assets/pevfa_results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/pevfa_results.png -------------------------------------------------------------------------------- /assets/pr_readme_figs/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/pr_readme_figs/.gitkeep -------------------------------------------------------------------------------- /assets/pr_readme_figs/GPI_with_PeVFA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/pr_readme_figs/GPI_with_PeVFA.png -------------------------------------------------------------------------------- /assets/pr_readme_figs/policy_generalization.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/pr_readme_figs/policy_generalization.png -------------------------------------------------------------------------------- /assets/sr_readme_figs/sr_framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TJU-DRL-LAB/self-supervised-rl/ece95621b8c49f154f96cf7d395b95362a3b3d4e/assets/sr_readme_figs/sr_framework.png --------------------------------------------------------------------------------