├── .gitignore ├── CQL ├── README.md ├── atari │ ├── CONTRIBUTING.md │ ├── LICENSE │ ├── batch_rl │ │ ├── __init__.py │ │ ├── baselines │ │ │ ├── __init__.py │ │ │ ├── agents │ │ │ │ ├── __init__.py │ │ │ │ ├── dqn_agent.py │ │ │ │ ├── quantile_agent.py │ │ │ │ └── random_agent.py │ │ │ ├── configs │ │ │ │ ├── dqn.gin │ │ │ │ ├── quantile.gin │ │ │ │ └── random.gin │ │ │ ├── replay_memory │ │ │ │ ├── __init__.py │ │ │ │ ├── logged_prioritized_replay_buffer.py │ │ │ │ └── logged_replay_buffer.py │ │ │ ├── run_experiment.py │ │ │ └── train.py │ │ ├── fixed_replay │ │ │ ├── __init__.py │ │ │ ├── agents │ │ │ │ ├── __init__.py │ │ │ │ ├── dqn_agent.py │ │ │ │ ├── multi_head_dqn_agent.py │ │ │ │ ├── multi_network_dqn_agent.py │ │ │ │ ├── quantile_agent.py │ │ │ │ └── rainbow_agent.py │ │ │ ├── configs │ │ │ │ ├── c51.gin │ │ │ │ ├── dqn.gin │ │ │ │ ├── multi_head_dqn.gin │ │ │ │ ├── quantile.gin │ │ │ │ ├── quantile_asterix.gin │ │ │ │ ├── quantile_breakout.gin │ │ │ │ ├── quantile_qbert.gin │ │ │ │ ├── quantile_seaquest.gin │ │ │ │ └── rem.gin │ │ │ ├── replay_memory │ │ │ │ └── fixed_replay_buffer.py │ │ │ ├── run_experiment.py │ │ │ └── train.py │ │ ├── multi_head │ │ │ ├── __init__.py │ │ │ ├── atari_helpers.py │ │ │ ├── multi_head_dqn_agent.py │ │ │ ├── multi_network_dqn_agent.py │ │ │ └── quantile_agent.py │ │ └── tests │ │ │ ├── atari_init_test.py │ │ │ └── fixed_replay_runner_test.py │ └── online │ │ ├── configs │ │ ├── c51.gin │ │ ├── dqn.gin │ │ ├── quantile.gin │ │ └── rem.gin │ │ └── train.py └── d4rl │ ├── .condarc │ ├── .gitignore │ ├── LICENSE │ ├── README.md │ ├── docs │ ├── HER.md │ ├── RIG.md │ ├── SkewFit.md │ ├── TDMs.md │ ├── goal_based_envs.md │ └── images │ │ ├── FetchReach-v1_HER-TD3.png │ │ ├── SawyerReachXYZEnv-v0_HER-TD3.png │ │ ├── her_dqn.png │ │ ├── her_td3_sawyer_reacher.png │ │ ├── skewfit_door.png │ │ ├── skewfit_pickup.png │ │ └── skewfit_pusher.png │ ├── environment │ ├── docker │ │ ├── Dockerfile │ │ └── vendor │ │ │ ├── 10_nvidia.json │ │ │ ├── Xdummy │ │ │ └── Xdummy-entrypoint │ ├── linux-cpu-env.yml │ ├── linux-gpu-env.yml │ └── mac-env.yml │ ├── examples │ ├── cql_antmaze_new.py │ ├── cql_mujoco_new.py │ ├── ddpg.py │ ├── doodad │ │ ├── ec2_example.py │ │ └── gcp_example.py │ ├── dqn_and_double_dqn.py │ ├── her │ │ ├── her_dqn_gridworld.py │ │ ├── her_sac_gym_fetch_reach.py │ │ └── her_td3_multiworld_sawyer_reach.py │ ├── sac.py │ ├── skewfit │ │ ├── sawyer_door.py │ │ ├── sawyer_pickup.py │ │ └── sawyer_push.py │ └── td3.py │ ├── rlkit │ ├── __init__.py │ ├── core │ │ ├── __init__.py │ │ ├── batch_rl_algorithm.py │ │ ├── eval_util.py │ │ ├── logging.py │ │ ├── online_rl_algorithm.py │ │ ├── rl_algorithm.py │ │ ├── serializable.py │ │ ├── tabulate.py │ │ └── trainer.py │ ├── data_management │ │ ├── __init__.py │ │ ├── env_replay_buffer.py │ │ ├── normalizer.py │ │ ├── obs_dict_replay_buffer.py │ │ ├── online_vae_replay_buffer.py │ │ ├── path_builder.py │ │ ├── replay_buffer.py │ │ ├── shared_obs_dict_replay_buffer.py │ │ └── simple_replay_buffer.py │ ├── envs │ │ ├── ant.py │ │ ├── assets │ │ │ ├── low_gear_ratio_ant.xml │ │ │ └── reacher_7dof.xml │ │ ├── env_utils.py │ │ ├── goal_generation │ │ │ └── pickup_goal_dataset.py │ │ ├── mujoco_env.py │ │ ├── mujoco_image_env.py │ │ ├── vae_wrapper.py │ │ └── wrappers.py │ ├── exploration_strategies │ │ ├── __init__.py │ │ ├── base.py │ │ ├── epsilon_greedy.py │ │ ├── gaussian_and_epsilon_strategy.py │ │ ├── gaussian_strategy.py │ │ └── ou_strategy.py │ ├── launchers │ │ ├── __init__.py │ │ ├── conf.py │ │ ├── launcher_util.py │ │ └── skewfit_experiments.py │ ├── policies │ │ ├── __init__.py │ │ ├── argmax.py │ │ ├── base.py │ │ └── simple.py │ ├── pythonplusplus.py │ ├── samplers │ │ ├── __init__.py │ │ ├── data_collector │ │ │ ├── __init__.py │ │ │ ├── base.py │ │ │ ├── path_collector.py │ │ │ ├── step_collector.py │ │ │ └── vae_env.py │ │ ├── rollout_functions.py │ │ └── util.py │ ├── torch │ │ ├── __init__.py │ │ ├── conv_networks.py │ │ ├── core.py │ │ ├── data.py │ │ ├── data_management │ │ │ ├── __init__.py │ │ │ └── normalizer.py │ │ ├── ddpg │ │ │ ├── __init__.py │ │ │ └── ddpg.py │ │ ├── distributions.py │ │ ├── dqn │ │ │ ├── __init__.py │ │ │ ├── double_dqn.py │ │ │ └── dqn.py │ │ ├── her │ │ │ ├── __init__.py │ │ │ └── her.py │ │ ├── modules.py │ │ ├── networks.py │ │ ├── pytorch_util.py │ │ ├── sac │ │ │ ├── __init__.py │ │ │ ├── cql.py │ │ │ ├── policies.py │ │ │ └── sac.py │ │ ├── skewfit │ │ │ ├── online_vae_algorithm.py │ │ │ └── video_gen.py │ │ ├── td3 │ │ │ ├── __init__.py │ │ │ └── td3.py │ │ ├── torch_rl_algorithm.py │ │ └── vae │ │ │ ├── conv_vae.py │ │ │ ├── vae_base.py │ │ │ ├── vae_schedules.py │ │ │ └── vae_trainer.py │ └── util │ │ ├── hyperparameter.py │ │ ├── io.py │ │ ├── ml_util.py │ │ └── video.py │ ├── scripts │ ├── run_experiment_from_doodad.py │ ├── run_goal_conditioned_policy.py │ └── run_policy.py │ └── setup.py ├── README.md ├── bash ├── train_reverse_bc.sh ├── train_reverse_model.sh ├── train_romi_bcq.sh └── train_romi_cql.sh ├── continuous_bcq ├── BCQ.py ├── ForwardBC.py ├── ReverseBC.py └── replay_buffer.py ├── environment └── requirements.txt ├── mopo ├── .gitignore ├── .gitmodules ├── LICENSE ├── README.md ├── environment │ ├── gpu-env.yml │ └── requirements.txt ├── examples │ ├── __init__.py │ ├── config │ │ ├── __init__.py │ │ └── d4rl │ │ │ ├── base.py │ │ │ ├── base_mopo.py │ │ │ ├── halfcheetah_medium.py │ │ │ ├── halfcheetah_medium_expert.py │ │ │ ├── halfcheetah_mixed.py │ │ │ ├── halfcheetah_random.py │ │ │ ├── hopper_medium.py │ │ │ ├── hopper_medium_expert.py │ │ │ ├── hopper_mixed.py │ │ │ ├── hopper_random.py │ │ │ ├── walker2d_medium.py │ │ │ ├── walker2d_medium_expert.py │ │ │ ├── walker2d_mixed.py │ │ │ └── walker2d_random.py │ ├── development │ │ ├── __init__.py │ │ ├── base.py │ │ ├── main.py │ │ ├── simulate_policy.py │ │ ├── simulate_policy_with_state.py │ │ └── variants.py │ ├── instrument.py │ └── utils.py ├── mopo │ ├── __init__.py │ ├── algorithms │ │ ├── __init__.py │ │ └── mopo.py │ ├── env │ │ ├── __init__.py │ │ ├── ant.py │ │ └── humanoid.py │ ├── models │ │ ├── __init__.py │ │ ├── bnn.py │ │ ├── constructor.py │ │ ├── fake_env.py │ │ ├── fc.py │ │ └── utils.py │ ├── off_policy │ │ ├── __init__.py │ │ └── loader.py │ ├── parallel │ │ ├── __init__.py │ │ ├── parallel_env.py │ │ ├── parallel_hopper.py │ │ └── test.py │ ├── scripts │ │ ├── __init__.py │ │ ├── console_scripts.py │ │ └── train_model_offline.py │ ├── static │ │ ├── __init__.py │ │ ├── ant.py │ │ ├── antangle.py │ │ ├── antmaze.py │ │ ├── halfcheetah.py │ │ ├── halfcheetahjump.py │ │ ├── halfcheetahvel.py │ │ ├── halfcheetahveljump.py │ │ ├── hopper.py │ │ ├── humanoid.py │ │ ├── maze2d.py │ │ ├── pendulum.py │ │ ├── point2denv.py │ │ ├── point2dwallenv.py │ │ └── walker2d.py │ └── utils │ │ ├── __init__.py │ │ ├── filesystem.py │ │ ├── logging.py │ │ ├── visualization.py │ │ └── writer.py ├── plots │ └── .gitkeep ├── run.sh ├── setup.py └── softlearning │ ├── __init__.py │ ├── algorithms │ ├── __init__.py │ ├── rl_algorithm.py │ ├── sac.py │ ├── sql.py │ └── utils.py │ ├── distributions │ ├── __init__.py │ ├── real_nvp_flow.py │ └── squash_bijector.py │ ├── environments │ ├── __init__.py │ ├── adapters │ │ ├── __init__.py │ │ ├── gym_adapter.py │ │ └── softlearning_env.py │ ├── dm_control │ │ └── __init__.py │ ├── gym │ │ ├── __init__.py │ │ ├── mujoco │ │ │ ├── __init__.py │ │ │ ├── image_pusher_2d.py │ │ │ └── pusher_2d.py │ │ ├── multi_goal.py │ │ ├── robotics │ │ │ └── __init__.py │ │ └── wrappers │ │ │ ├── __init__.py │ │ │ └── normalize_action.py │ ├── helpers.py │ └── utils.py │ ├── misc │ ├── __init__.py │ ├── kernel.py │ ├── plotter.py │ └── utils.py │ ├── models │ ├── __init__.py │ ├── feedforward.py │ └── utils.py │ ├── policies │ ├── __init__.py │ ├── base_policy.py │ ├── gaussian_policy.py │ ├── uniform_policy.py │ └── utils.py │ ├── preprocessors │ ├── __init__.py │ ├── convnet.py │ └── utils.py │ ├── replay_pools │ ├── __init__.py │ ├── extra_policy_info_replay_pool.py │ ├── flexible_replay_pool.py │ ├── replay_pool.py │ ├── simple_replay_pool.py │ ├── trajectory_replay_pool.py │ ├── union_pool.py │ └── utils.py │ ├── samplers │ ├── __init__.py │ ├── base_sampler.py │ ├── dummy_sampler.py │ ├── explore_sampler.py │ ├── extra_policy_info_sampler.py │ ├── remote_sampler.py │ ├── simple_sampler.py │ └── utils.py │ ├── scripts │ ├── __init__.py │ └── console_scripts.py │ ├── softlearning.md │ ├── utils │ ├── keras.py │ └── numpy.py │ └── value_functions │ ├── __init__.py │ ├── utils.py │ ├── value_function.py │ └── vanilla.py ├── scripts ├── train_bcq.py ├── train_model.py └── train_reverse_bc.py └── utils ├── bc.py ├── dataset_processor.py ├── dataset_utils.py ├── fake_env.py ├── filesystem.py ├── model_utils.py ├── oracle_env.py ├── proportional.py └── sum_tree.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/.gitignore -------------------------------------------------------------------------------- /CQL/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/README.md -------------------------------------------------------------------------------- /CQL/atari/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/CONTRIBUTING.md -------------------------------------------------------------------------------- /CQL/atari/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/LICENSE -------------------------------------------------------------------------------- /CQL/atari/batch_rl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/__init__.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/__init__.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/agents/__init__.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/agents/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/agents/dqn_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/agents/quantile_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/agents/quantile_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/agents/random_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/agents/random_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/configs/dqn.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/configs/dqn.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/configs/quantile.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/configs/quantile.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/configs/random.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/configs/random.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/replay_memory/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/replay_memory/__init__.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/replay_memory/logged_prioritized_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/replay_memory/logged_prioritized_replay_buffer.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/replay_memory/logged_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/replay_memory/logged_replay_buffer.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/run_experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/run_experiment.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/baselines/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/baselines/train.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/__init__.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/agents/__init__.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/agents/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/agents/dqn_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/agents/multi_head_dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/agents/multi_head_dqn_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/agents/multi_network_dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/agents/multi_network_dqn_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/agents/quantile_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/agents/quantile_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/agents/rainbow_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/agents/rainbow_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/configs/c51.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/configs/c51.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/configs/dqn.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/configs/dqn.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/configs/multi_head_dqn.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/configs/multi_head_dqn.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/configs/quantile.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/configs/quantile.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/configs/quantile_asterix.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/configs/quantile_asterix.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/configs/quantile_breakout.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/configs/quantile_breakout.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/configs/quantile_qbert.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/configs/quantile_qbert.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/configs/quantile_seaquest.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/configs/quantile_seaquest.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/configs/rem.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/configs/rem.gin -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/replay_memory/fixed_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/replay_memory/fixed_replay_buffer.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/run_experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/run_experiment.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/fixed_replay/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/fixed_replay/train.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/multi_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/multi_head/__init__.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/multi_head/atari_helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/multi_head/atari_helpers.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/multi_head/multi_head_dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/multi_head/multi_head_dqn_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/multi_head/multi_network_dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/multi_head/multi_network_dqn_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/multi_head/quantile_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/multi_head/quantile_agent.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/tests/atari_init_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/tests/atari_init_test.py -------------------------------------------------------------------------------- /CQL/atari/batch_rl/tests/fixed_replay_runner_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/batch_rl/tests/fixed_replay_runner_test.py -------------------------------------------------------------------------------- /CQL/atari/online/configs/c51.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/online/configs/c51.gin -------------------------------------------------------------------------------- /CQL/atari/online/configs/dqn.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/online/configs/dqn.gin -------------------------------------------------------------------------------- /CQL/atari/online/configs/quantile.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/online/configs/quantile.gin -------------------------------------------------------------------------------- /CQL/atari/online/configs/rem.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/online/configs/rem.gin -------------------------------------------------------------------------------- /CQL/atari/online/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/atari/online/train.py -------------------------------------------------------------------------------- /CQL/d4rl/.condarc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/.condarc -------------------------------------------------------------------------------- /CQL/d4rl/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/.gitignore -------------------------------------------------------------------------------- /CQL/d4rl/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/LICENSE -------------------------------------------------------------------------------- /CQL/d4rl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/README.md -------------------------------------------------------------------------------- /CQL/d4rl/docs/HER.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/HER.md -------------------------------------------------------------------------------- /CQL/d4rl/docs/RIG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/RIG.md -------------------------------------------------------------------------------- /CQL/d4rl/docs/SkewFit.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/SkewFit.md -------------------------------------------------------------------------------- /CQL/d4rl/docs/TDMs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/TDMs.md -------------------------------------------------------------------------------- /CQL/d4rl/docs/goal_based_envs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/goal_based_envs.md -------------------------------------------------------------------------------- /CQL/d4rl/docs/images/FetchReach-v1_HER-TD3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/images/FetchReach-v1_HER-TD3.png -------------------------------------------------------------------------------- /CQL/d4rl/docs/images/SawyerReachXYZEnv-v0_HER-TD3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/images/SawyerReachXYZEnv-v0_HER-TD3.png -------------------------------------------------------------------------------- /CQL/d4rl/docs/images/her_dqn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/images/her_dqn.png -------------------------------------------------------------------------------- /CQL/d4rl/docs/images/her_td3_sawyer_reacher.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/images/her_td3_sawyer_reacher.png -------------------------------------------------------------------------------- /CQL/d4rl/docs/images/skewfit_door.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/images/skewfit_door.png -------------------------------------------------------------------------------- /CQL/d4rl/docs/images/skewfit_pickup.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/images/skewfit_pickup.png -------------------------------------------------------------------------------- /CQL/d4rl/docs/images/skewfit_pusher.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/docs/images/skewfit_pusher.png -------------------------------------------------------------------------------- /CQL/d4rl/environment/docker/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/environment/docker/Dockerfile -------------------------------------------------------------------------------- /CQL/d4rl/environment/docker/vendor/10_nvidia.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/environment/docker/vendor/10_nvidia.json -------------------------------------------------------------------------------- /CQL/d4rl/environment/docker/vendor/Xdummy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/environment/docker/vendor/Xdummy -------------------------------------------------------------------------------- /CQL/d4rl/environment/docker/vendor/Xdummy-entrypoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/environment/docker/vendor/Xdummy-entrypoint -------------------------------------------------------------------------------- /CQL/d4rl/environment/linux-cpu-env.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/environment/linux-cpu-env.yml -------------------------------------------------------------------------------- /CQL/d4rl/environment/linux-gpu-env.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/environment/linux-gpu-env.yml -------------------------------------------------------------------------------- /CQL/d4rl/environment/mac-env.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/environment/mac-env.yml -------------------------------------------------------------------------------- /CQL/d4rl/examples/cql_antmaze_new.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/cql_antmaze_new.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/cql_mujoco_new.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/cql_mujoco_new.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/ddpg.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/doodad/ec2_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/doodad/ec2_example.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/doodad/gcp_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/doodad/gcp_example.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/dqn_and_double_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/dqn_and_double_dqn.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/her/her_dqn_gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/her/her_dqn_gridworld.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/her/her_sac_gym_fetch_reach.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/her/her_sac_gym_fetch_reach.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/her/her_td3_multiworld_sawyer_reach.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/her/her_td3_multiworld_sawyer_reach.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/sac.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/skewfit/sawyer_door.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/skewfit/sawyer_door.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/skewfit/sawyer_pickup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/skewfit/sawyer_pickup.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/skewfit/sawyer_push.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/skewfit/sawyer_push.py -------------------------------------------------------------------------------- /CQL/d4rl/examples/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/examples/td3.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/core/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/core/__init__.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/core/batch_rl_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/core/batch_rl_algorithm.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/core/eval_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/core/eval_util.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/core/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/core/logging.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/core/online_rl_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/core/online_rl_algorithm.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/core/rl_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/core/rl_algorithm.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/core/serializable.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/core/serializable.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/core/tabulate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/core/tabulate.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/core/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/core/trainer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/data_management/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/data_management/env_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/data_management/env_replay_buffer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/data_management/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/data_management/normalizer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/data_management/obs_dict_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/data_management/obs_dict_replay_buffer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/data_management/online_vae_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/data_management/online_vae_replay_buffer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/data_management/path_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/data_management/path_builder.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/data_management/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/data_management/replay_buffer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/data_management/shared_obs_dict_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/data_management/shared_obs_dict_replay_buffer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/data_management/simple_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/data_management/simple_replay_buffer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/envs/ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/envs/ant.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/envs/assets/low_gear_ratio_ant.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/envs/assets/low_gear_ratio_ant.xml -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/envs/assets/reacher_7dof.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/envs/assets/reacher_7dof.xml -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/envs/env_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/envs/env_utils.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/envs/goal_generation/pickup_goal_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/envs/goal_generation/pickup_goal_dataset.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/envs/mujoco_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/envs/mujoco_env.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/envs/mujoco_image_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/envs/mujoco_image_env.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/envs/vae_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/envs/vae_wrapper.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/envs/wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/envs/wrappers.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/exploration_strategies/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/exploration_strategies/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/exploration_strategies/base.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/exploration_strategies/epsilon_greedy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/exploration_strategies/epsilon_greedy.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/exploration_strategies/gaussian_and_epsilon_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/exploration_strategies/gaussian_and_epsilon_strategy.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/exploration_strategies/gaussian_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/exploration_strategies/gaussian_strategy.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/exploration_strategies/ou_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/exploration_strategies/ou_strategy.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/launchers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/launchers/__init__.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/launchers/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/launchers/conf.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/launchers/launcher_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/launchers/launcher_util.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/launchers/skewfit_experiments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/launchers/skewfit_experiments.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/policies/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/policies/argmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/policies/argmax.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/policies/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/policies/base.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/policies/simple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/policies/simple.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/pythonplusplus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/pythonplusplus.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/samplers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/samplers/data_collector/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/samplers/data_collector/__init__.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/samplers/data_collector/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/samplers/data_collector/base.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/samplers/data_collector/path_collector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/samplers/data_collector/path_collector.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/samplers/data_collector/step_collector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/samplers/data_collector/step_collector.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/samplers/data_collector/vae_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/samplers/data_collector/vae_env.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/samplers/rollout_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/samplers/rollout_functions.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/samplers/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/samplers/util.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/conv_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/conv_networks.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/core.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/data.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/data_management/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/data_management/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/data_management/normalizer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/ddpg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/ddpg/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/ddpg/ddpg.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/distributions.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/dqn/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/dqn/double_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/dqn/double_dqn.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/dqn/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/dqn/dqn.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/her/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/her/her.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/her/her.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/modules.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/networks.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/pytorch_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/pytorch_util.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/sac/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/sac/cql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/sac/cql.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/sac/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/sac/policies.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/sac/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/sac/sac.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/skewfit/online_vae_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/skewfit/online_vae_algorithm.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/skewfit/video_gen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/skewfit/video_gen.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/td3/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/td3/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/td3/td3.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/torch_rl_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/torch_rl_algorithm.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/vae/conv_vae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/vae/conv_vae.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/vae/vae_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/vae/vae_base.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/vae/vae_schedules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/vae/vae_schedules.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/torch/vae/vae_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/torch/vae/vae_trainer.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/util/hyperparameter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/util/hyperparameter.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/util/io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/util/io.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/util/ml_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/util/ml_util.py -------------------------------------------------------------------------------- /CQL/d4rl/rlkit/util/video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/rlkit/util/video.py -------------------------------------------------------------------------------- /CQL/d4rl/scripts/run_experiment_from_doodad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/scripts/run_experiment_from_doodad.py -------------------------------------------------------------------------------- /CQL/d4rl/scripts/run_goal_conditioned_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/scripts/run_goal_conditioned_policy.py -------------------------------------------------------------------------------- /CQL/d4rl/scripts/run_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/scripts/run_policy.py -------------------------------------------------------------------------------- /CQL/d4rl/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/CQL/d4rl/setup.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/README.md -------------------------------------------------------------------------------- /bash/train_reverse_bc.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/bash/train_reverse_bc.sh -------------------------------------------------------------------------------- /bash/train_reverse_model.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/bash/train_reverse_model.sh -------------------------------------------------------------------------------- /bash/train_romi_bcq.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/bash/train_romi_bcq.sh -------------------------------------------------------------------------------- /bash/train_romi_cql.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/bash/train_romi_cql.sh -------------------------------------------------------------------------------- /continuous_bcq/BCQ.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/continuous_bcq/BCQ.py -------------------------------------------------------------------------------- /continuous_bcq/ForwardBC.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/continuous_bcq/ForwardBC.py -------------------------------------------------------------------------------- /continuous_bcq/ReverseBC.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/continuous_bcq/ReverseBC.py -------------------------------------------------------------------------------- /continuous_bcq/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/continuous_bcq/replay_buffer.py -------------------------------------------------------------------------------- /environment/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/environment/requirements.txt -------------------------------------------------------------------------------- /mopo/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/.gitignore -------------------------------------------------------------------------------- /mopo/.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/.gitmodules -------------------------------------------------------------------------------- /mopo/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/LICENSE -------------------------------------------------------------------------------- /mopo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/README.md -------------------------------------------------------------------------------- /mopo/environment/gpu-env.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/environment/gpu-env.yml -------------------------------------------------------------------------------- /mopo/environment/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/environment/requirements.txt -------------------------------------------------------------------------------- /mopo/examples/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/examples/config/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/__init__.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/base.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/base_mopo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/base_mopo.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/halfcheetah_medium.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/halfcheetah_medium.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/halfcheetah_medium_expert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/halfcheetah_medium_expert.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/halfcheetah_mixed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/halfcheetah_mixed.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/halfcheetah_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/halfcheetah_random.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/hopper_medium.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/hopper_medium.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/hopper_medium_expert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/hopper_medium_expert.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/hopper_mixed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/hopper_mixed.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/hopper_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/hopper_random.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/walker2d_medium.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/walker2d_medium.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/walker2d_medium_expert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/walker2d_medium_expert.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/walker2d_mixed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/walker2d_mixed.py -------------------------------------------------------------------------------- /mopo/examples/config/d4rl/walker2d_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/config/d4rl/walker2d_random.py -------------------------------------------------------------------------------- /mopo/examples/development/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/development/__init__.py -------------------------------------------------------------------------------- /mopo/examples/development/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/development/base.py -------------------------------------------------------------------------------- /mopo/examples/development/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/development/main.py -------------------------------------------------------------------------------- /mopo/examples/development/simulate_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/development/simulate_policy.py -------------------------------------------------------------------------------- /mopo/examples/development/simulate_policy_with_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/development/simulate_policy_with_state.py -------------------------------------------------------------------------------- /mopo/examples/development/variants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/development/variants.py -------------------------------------------------------------------------------- /mopo/examples/instrument.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/instrument.py -------------------------------------------------------------------------------- /mopo/examples/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/examples/utils.py -------------------------------------------------------------------------------- /mopo/mopo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/mopo/algorithms/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/mopo/algorithms/mopo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/algorithms/mopo.py -------------------------------------------------------------------------------- /mopo/mopo/env/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/env/__init__.py -------------------------------------------------------------------------------- /mopo/mopo/env/ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/env/ant.py -------------------------------------------------------------------------------- /mopo/mopo/env/humanoid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/env/humanoid.py -------------------------------------------------------------------------------- /mopo/mopo/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/mopo/models/bnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/models/bnn.py -------------------------------------------------------------------------------- /mopo/mopo/models/constructor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/models/constructor.py -------------------------------------------------------------------------------- /mopo/mopo/models/fake_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/models/fake_env.py -------------------------------------------------------------------------------- /mopo/mopo/models/fc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/models/fc.py -------------------------------------------------------------------------------- /mopo/mopo/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/models/utils.py -------------------------------------------------------------------------------- /mopo/mopo/off_policy/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/mopo/off_policy/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/off_policy/loader.py -------------------------------------------------------------------------------- /mopo/mopo/parallel/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/mopo/parallel/parallel_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/parallel/parallel_env.py -------------------------------------------------------------------------------- /mopo/mopo/parallel/parallel_hopper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/parallel/parallel_hopper.py -------------------------------------------------------------------------------- /mopo/mopo/parallel/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/parallel/test.py -------------------------------------------------------------------------------- /mopo/mopo/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/mopo/scripts/console_scripts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/scripts/console_scripts.py -------------------------------------------------------------------------------- /mopo/mopo/scripts/train_model_offline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/scripts/train_model_offline.py -------------------------------------------------------------------------------- /mopo/mopo/static/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/__init__.py -------------------------------------------------------------------------------- /mopo/mopo/static/ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/ant.py -------------------------------------------------------------------------------- /mopo/mopo/static/antangle.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/antangle.py -------------------------------------------------------------------------------- /mopo/mopo/static/antmaze.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/antmaze.py -------------------------------------------------------------------------------- /mopo/mopo/static/halfcheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/halfcheetah.py -------------------------------------------------------------------------------- /mopo/mopo/static/halfcheetahjump.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/halfcheetahjump.py -------------------------------------------------------------------------------- /mopo/mopo/static/halfcheetahvel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/halfcheetahvel.py -------------------------------------------------------------------------------- /mopo/mopo/static/halfcheetahveljump.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/halfcheetahveljump.py -------------------------------------------------------------------------------- /mopo/mopo/static/hopper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/hopper.py -------------------------------------------------------------------------------- /mopo/mopo/static/humanoid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/humanoid.py -------------------------------------------------------------------------------- /mopo/mopo/static/maze2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/maze2d.py -------------------------------------------------------------------------------- /mopo/mopo/static/pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/pendulum.py -------------------------------------------------------------------------------- /mopo/mopo/static/point2denv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/point2denv.py -------------------------------------------------------------------------------- /mopo/mopo/static/point2dwallenv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/point2dwallenv.py -------------------------------------------------------------------------------- /mopo/mopo/static/walker2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/static/walker2d.py -------------------------------------------------------------------------------- /mopo/mopo/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/utils/__init__.py -------------------------------------------------------------------------------- /mopo/mopo/utils/filesystem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/utils/filesystem.py -------------------------------------------------------------------------------- /mopo/mopo/utils/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/utils/logging.py -------------------------------------------------------------------------------- /mopo/mopo/utils/visualization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/utils/visualization.py -------------------------------------------------------------------------------- /mopo/mopo/utils/writer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/mopo/utils/writer.py -------------------------------------------------------------------------------- /mopo/plots/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/run.sh -------------------------------------------------------------------------------- /mopo/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/setup.py -------------------------------------------------------------------------------- /mopo/softlearning/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/algorithms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/algorithms/__init__.py -------------------------------------------------------------------------------- /mopo/softlearning/algorithms/rl_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/algorithms/rl_algorithm.py -------------------------------------------------------------------------------- /mopo/softlearning/algorithms/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/algorithms/sac.py -------------------------------------------------------------------------------- /mopo/softlearning/algorithms/sql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/algorithms/sql.py -------------------------------------------------------------------------------- /mopo/softlearning/algorithms/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/algorithms/utils.py -------------------------------------------------------------------------------- /mopo/softlearning/distributions/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/distributions/__init__.py -------------------------------------------------------------------------------- /mopo/softlearning/distributions/real_nvp_flow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/distributions/real_nvp_flow.py -------------------------------------------------------------------------------- /mopo/softlearning/distributions/squash_bijector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/distributions/squash_bijector.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/environments/adapters/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/adapters/__init__.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/adapters/gym_adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/adapters/gym_adapter.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/adapters/softlearning_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/adapters/softlearning_env.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/dm_control/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/dm_control/__init__.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/gym/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/gym/__init__.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/gym/mujoco/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/environments/gym/mujoco/image_pusher_2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/gym/mujoco/image_pusher_2d.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/gym/mujoco/pusher_2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/gym/mujoco/pusher_2d.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/gym/multi_goal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/gym/multi_goal.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/gym/robotics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/environments/gym/wrappers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/gym/wrappers/__init__.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/gym/wrappers/normalize_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/gym/wrappers/normalize_action.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/helpers.py -------------------------------------------------------------------------------- /mopo/softlearning/environments/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/environments/utils.py -------------------------------------------------------------------------------- /mopo/softlearning/misc/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/misc/kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/misc/kernel.py -------------------------------------------------------------------------------- /mopo/softlearning/misc/plotter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/misc/plotter.py -------------------------------------------------------------------------------- /mopo/softlearning/misc/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/misc/utils.py -------------------------------------------------------------------------------- /mopo/softlearning/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/models/feedforward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/models/feedforward.py -------------------------------------------------------------------------------- /mopo/softlearning/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/models/utils.py -------------------------------------------------------------------------------- /mopo/softlearning/policies/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/policies/base_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/policies/base_policy.py -------------------------------------------------------------------------------- /mopo/softlearning/policies/gaussian_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/policies/gaussian_policy.py -------------------------------------------------------------------------------- /mopo/softlearning/policies/uniform_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/policies/uniform_policy.py -------------------------------------------------------------------------------- /mopo/softlearning/policies/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/policies/utils.py -------------------------------------------------------------------------------- /mopo/softlearning/preprocessors/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/preprocessors/convnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/preprocessors/convnet.py -------------------------------------------------------------------------------- /mopo/softlearning/preprocessors/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/preprocessors/utils.py -------------------------------------------------------------------------------- /mopo/softlearning/replay_pools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/replay_pools/__init__.py -------------------------------------------------------------------------------- /mopo/softlearning/replay_pools/extra_policy_info_replay_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/replay_pools/extra_policy_info_replay_pool.py -------------------------------------------------------------------------------- /mopo/softlearning/replay_pools/flexible_replay_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/replay_pools/flexible_replay_pool.py -------------------------------------------------------------------------------- /mopo/softlearning/replay_pools/replay_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/replay_pools/replay_pool.py -------------------------------------------------------------------------------- /mopo/softlearning/replay_pools/simple_replay_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/replay_pools/simple_replay_pool.py -------------------------------------------------------------------------------- /mopo/softlearning/replay_pools/trajectory_replay_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/replay_pools/trajectory_replay_pool.py -------------------------------------------------------------------------------- /mopo/softlearning/replay_pools/union_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/replay_pools/union_pool.py -------------------------------------------------------------------------------- /mopo/softlearning/replay_pools/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/replay_pools/utils.py -------------------------------------------------------------------------------- /mopo/softlearning/samplers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/samplers/__init__.py -------------------------------------------------------------------------------- /mopo/softlearning/samplers/base_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/samplers/base_sampler.py -------------------------------------------------------------------------------- /mopo/softlearning/samplers/dummy_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/samplers/dummy_sampler.py -------------------------------------------------------------------------------- /mopo/softlearning/samplers/explore_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/samplers/explore_sampler.py -------------------------------------------------------------------------------- /mopo/softlearning/samplers/extra_policy_info_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/samplers/extra_policy_info_sampler.py -------------------------------------------------------------------------------- /mopo/softlearning/samplers/remote_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/samplers/remote_sampler.py -------------------------------------------------------------------------------- /mopo/softlearning/samplers/simple_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/samplers/simple_sampler.py -------------------------------------------------------------------------------- /mopo/softlearning/samplers/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/samplers/utils.py -------------------------------------------------------------------------------- /mopo/softlearning/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/scripts/console_scripts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/scripts/console_scripts.py -------------------------------------------------------------------------------- /mopo/softlearning/softlearning.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/softlearning.md -------------------------------------------------------------------------------- /mopo/softlearning/utils/keras.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/utils/keras.py -------------------------------------------------------------------------------- /mopo/softlearning/utils/numpy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/utils/numpy.py -------------------------------------------------------------------------------- /mopo/softlearning/value_functions/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mopo/softlearning/value_functions/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/value_functions/utils.py -------------------------------------------------------------------------------- /mopo/softlearning/value_functions/value_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/value_functions/value_function.py -------------------------------------------------------------------------------- /mopo/softlearning/value_functions/vanilla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/mopo/softlearning/value_functions/vanilla.py -------------------------------------------------------------------------------- /scripts/train_bcq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/scripts/train_bcq.py -------------------------------------------------------------------------------- /scripts/train_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/scripts/train_model.py -------------------------------------------------------------------------------- /scripts/train_reverse_bc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/scripts/train_reverse_bc.py -------------------------------------------------------------------------------- /utils/bc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/utils/bc.py -------------------------------------------------------------------------------- /utils/dataset_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/utils/dataset_processor.py -------------------------------------------------------------------------------- /utils/dataset_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/utils/dataset_utils.py -------------------------------------------------------------------------------- /utils/fake_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/utils/fake_env.py -------------------------------------------------------------------------------- /utils/filesystem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/utils/filesystem.py -------------------------------------------------------------------------------- /utils/model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/utils/model_utils.py -------------------------------------------------------------------------------- /utils/oracle_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/utils/oracle_env.py -------------------------------------------------------------------------------- /utils/proportional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/utils/proportional.py -------------------------------------------------------------------------------- /utils/sum_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wenzhe-li/romi/HEAD/utils/sum_tree.py --------------------------------------------------------------------------------