├── .flake8 ├── .github ├── auto_assign.yml └── workflows │ └── auto_assign.yml ├── .gitignore ├── .pfnci ├── config.pbtxt ├── hint.pbtxt ├── lint.sh ├── run.sh └── script.sh ├── CONTRIBUTING.md ├── LICENSE ├── MANIFEST.in ├── README.md ├── assets ├── PFRL.png ├── boxing.gif ├── grasping.gif └── humanoid.gif ├── docs ├── Makefile ├── action_values.rst ├── agents.rst ├── conf.py ├── experiments.rst ├── explorers.rst ├── index.rst ├── install.rst ├── make.bat ├── nn.rst ├── policies.rst ├── q_functions.rst ├── reference.rst └── replay_buffers.rst ├── examples ├── README.md ├── atari │ ├── README.md │ ├── reproduction │ │ ├── a3c │ │ │ ├── README.md │ │ │ └── train_a3c.py │ │ ├── dqn │ │ │ ├── README.md │ │ │ └── train_dqn.py │ │ ├── iqn │ │ │ ├── README.md │ │ │ └── train_iqn.py │ │ └── rainbow │ │ │ ├── README.md │ │ │ └── train_rainbow.py │ ├── train_a2c_ale.py │ ├── train_acer_ale.py │ ├── train_categorical_dqn_ale.py │ ├── train_dqn_ale.py │ ├── train_dqn_batch_ale.py │ ├── train_drqn_ale.py │ └── train_ppo_ale.py ├── atlas │ ├── README.md │ ├── assets │ │ ├── atlas.gif │ │ └── learningcurve.png │ └── train_soft_actor_critic_atlas.py ├── grasping │ ├── README.md │ ├── assets │ │ └── learningcurve.png │ └── train_dqn_batch_grasping.py ├── gym │ ├── README.md │ ├── train_categorical_dqn_gym.py │ ├── train_dqn_gym.py │ └── train_reinforce_gym.py ├── mujoco │ ├── README.md │ └── reproduction │ │ ├── ddpg │ │ ├── README.md │ │ ├── assets │ │ │ ├── Ant-v2.png │ │ │ ├── HalfCheetah-v2.png │ │ │ ├── Hopper-v2.png │ │ │ ├── InvertedDoublePendulum-v2.png │ │ │ ├── InvertedPendulum-v2.png │ │ │ ├── Reacher-v2.png │ │ │ └── Walker2d-v2.png │ │ └── train_ddpg.py │ │ ├── ppo │ │ ├── README.md │ │ ├── assets │ │ │ ├── HalfCheetah-v2.png │ │ │ ├── Hopper-v2.png │ │ │ ├── Swimmer-v2.png │ │ │ └── Walker2d-v2.png │ │ └── train_ppo.py │ │ ├── soft_actor_critic │ │ ├── README.md │ │ ├── assets │ │ │ ├── Ant-v2.png │ │ │ ├── HalfCheetah-v2.png │ │ │ ├── Hopper-v2.png │ │ │ ├── Humanoid-v2.png │ │ │ └── Walker2d-v2.png │ │ └── train_soft_actor_critic.py │ │ ├── td3 │ │ ├── README.md │ │ ├── assets │ │ │ ├── Ant-v2.png │ │ │ ├── HalfCheetah-v2.png │ │ │ ├── Hopper-v2.png │ │ │ ├── InvertedDoublePendulum-v2.png │ │ │ ├── InvertedPendulum-v2.png │ │ │ ├── Reacher-v2.png │ │ │ └── Walker2d-v2.png │ │ └── train_td3.py │ │ └── trpo │ │ ├── README.md │ │ ├── assets │ │ ├── HalfCheetah-v2.png │ │ ├── Hopper-v2.png │ │ ├── Swimmer-v2.png │ │ └── Walker2d-v2.png │ │ └── train_trpo.py ├── optuna │ ├── README.md │ ├── assets │ │ └── optimization_history.png │ └── optuna_dqn_obs1d.py ├── quickstart │ └── quickstart.ipynb └── slimevolley │ ├── README.md │ ├── assets │ ├── learningcurve.png │ └── slimevolley.gif │ └── train_rainbow.py ├── examples_tests ├── atari │ ├── reproduction │ │ ├── test_dqn.sh │ │ ├── test_iqn.sh │ │ └── test_rainbow.sh │ ├── test_a2c.sh │ ├── test_acer.sh │ ├── test_categorical_dqn.sh │ ├── test_dqn.sh │ ├── test_dqn_batch.sh │ ├── test_drqn.sh │ └── test_ppo.sh ├── atlas │ └── test_soft_actor_critic.sh ├── grasping │ └── test_dqn.sh ├── gym │ ├── test_categorical_dqn.sh │ ├── test_dqn.sh │ └── test_reinforce.sh ├── mujoco │ └── reproduction │ │ ├── test_ddpg.sh │ │ ├── test_ppo.sh │ │ ├── test_soft_actor_critic.sh │ │ ├── test_td3.sh │ │ └── test_trpo.sh ├── optuna │ └── test_optuna_dqn_obs1d.sh └── slimevolley │ └── test_rainbow.sh ├── pfrl ├── __init__.py ├── action_value.py ├── agent.py ├── agents │ ├── __init__.py │ ├── a2c.py │ ├── a3c.py │ ├── acer.py │ ├── al.py │ ├── categorical_double_dqn.py │ ├── categorical_dqn.py │ ├── ddpg.py │ ├── double_dqn.py │ ├── double_pal.py │ ├── dpp.py │ ├── dqn.py │ ├── iqn.py │ ├── pal.py │ ├── ppo.py │ ├── reinforce.py │ ├── soft_actor_critic.py │ ├── state_q_function_actor.py │ ├── td3.py │ └── trpo.py ├── collections │ ├── __init__.py │ ├── persistent_collections.py │ ├── prioritized.py │ └── random_access_queue.py ├── distributions │ ├── __init__.py │ └── delta.py ├── env.py ├── envs │ ├── __init__.py │ ├── abc.py │ ├── multiprocess_vector_env.py │ └── serial_vector_env.py ├── experiments │ ├── __init__.py │ ├── evaluation_hooks.py │ ├── evaluator.py │ ├── hooks.py │ ├── prepare_output_dir.py │ ├── train_agent.py │ ├── train_agent_async.py │ └── train_agent_batch.py ├── explorer.py ├── explorers │ ├── __init__.py │ ├── additive_gaussian.py │ ├── additive_ou.py │ ├── boltzmann.py │ ├── epsilon_greedy.py │ └── greedy.py ├── functions │ ├── __init__.py │ ├── bound_by_tanh.py │ └── lower_triangular_matrix.py ├── initializers │ ├── __init__.py │ ├── chainer_default.py │ └── lecun_normal.py ├── nn │ ├── __init__.py │ ├── atari_cnn.py │ ├── bound_by_tanh.py │ ├── branched.py │ ├── concat_obs_and_action.py │ ├── empirical_normalization.py │ ├── lmbda.py │ ├── mlp.py │ ├── mlp_bn.py │ ├── noisy_chain.py │ ├── noisy_linear.py │ ├── recurrent.py │ ├── recurrent_branched.py │ └── recurrent_sequential.py ├── optimizers │ ├── __init__.py │ └── rmsprop_eps_inside_sqrt.py ├── policies │ ├── __init__.py │ ├── deterministic_policy.py │ ├── gaussian_policy.py │ └── softmax_policy.py ├── policy.py ├── q_function.py ├── q_functions │ ├── __init__.py │ ├── dueling_dqn.py │ ├── state_action_q_functions.py │ └── state_q_functions.py ├── replay_buffer.py ├── replay_buffers │ ├── __init__.py │ ├── episodic.py │ ├── persistent.py │ ├── prioritized.py │ ├── prioritized_episodic.py │ └── replay_buffer.py ├── testing.py ├── utils │ ├── __init__.py │ ├── ask_yes_no.py │ ├── async_.py │ ├── batch_states.py │ ├── clip_l2_grad_norm.py │ ├── conjugate_gradient.py │ ├── contexts.py │ ├── copy_param.py │ ├── env_modifiers.py │ ├── is_return_code_zero.py │ ├── mode_of_distribution.py │ ├── pretrained_models.py │ ├── random.py │ ├── random_seed.py │ ├── recurrent.py │ ├── reward_filter.py │ └── stoppable_thread.py └── wrappers │ ├── __init__.py │ ├── atari_wrappers.py │ ├── cast_observation.py │ ├── continuing_time_limit.py │ ├── monitor.py │ ├── normalize_action_space.py │ ├── randomize_action.py │ ├── render.py │ ├── scale_reward.py │ └── vector_frame_stack.py ├── pytest.ini ├── readthedocs.yml ├── requirements-dev.txt ├── requirements.txt ├── setup.cfg ├── setup.py ├── test_examples.sh ├── tests ├── agents_tests │ ├── basetest_ddpg.py │ ├── basetest_dqn_like.py │ ├── basetest_training.py │ ├── test_a2c.py │ ├── test_a3c.py │ ├── test_acer.py │ ├── test_al.py │ ├── test_categorical_dqn.py │ ├── test_ddpg.py │ ├── test_double_categorical_dqn.py │ ├── test_double_dqn.py │ ├── test_double_pal.py │ ├── test_dpp.py │ ├── test_dqn.py │ ├── test_iqn.py │ ├── test_pal.py │ ├── test_ppo.py │ ├── test_reinforce.py │ ├── test_soft_actor_critic.py │ ├── test_td3.py │ └── test_trpo.py ├── collections_tests │ ├── test_persistent_collections.py │ ├── test_prioritized.py │ └── test_random_access_queue.py ├── envs_tests │ └── test_vector_envs.py ├── experiments_tests │ ├── test_evaluation_hooks.py │ ├── test_evaluator.py │ ├── test_hooks.py │ ├── test_prepare_output_dir.py │ ├── test_train_agent.py │ ├── test_train_agent_async.py │ └── test_train_agent_batch.py ├── explorers_tests │ ├── test_additive_gaussian.py │ ├── test_additive_ou.py │ ├── test_boltzmann.py │ └── test_epsilon_greedy.py ├── functions_tests │ └── test_lower_triangular_matrix.py ├── misc_tests │ └── tests_persistent_collections.py ├── nn_tests │ ├── test_branched.py │ ├── test_empirical_normalization.py │ ├── test_lmbda.py │ ├── test_mlp_bn.py │ ├── test_noisy_chain.py │ ├── test_noisy_linear.py │ ├── test_recurrent_branched.py │ └── test_recurrent_sequential.py ├── q_functions_tests │ ├── basetest_state_action_q_function.py │ └── test_state_action_q_function.py ├── replay_buffers_test │ ├── test_persistent_replay_buffer.py │ └── test_replay_buffer.py ├── test_action_value.py ├── test_agent.py ├── test_testing.py ├── utils_tests │ ├── test_async.py │ ├── test_batch_states.py │ ├── test_clip_l2_grad_norm.py │ ├── test_conjugate_gradient.py │ ├── test_contexts.py │ ├── test_copy_param.py │ ├── test_is_return_code_zero.py │ ├── test_mode_of_distribution.py │ ├── test_pretrained_models.py │ ├── test_random.py │ ├── test_random_seed.py │ ├── test_recurrent.py │ └── test_stoppable_thread.py └── wrappers_tests │ ├── test_atari_wrappers.py │ ├── test_cast_observation.py │ ├── test_continuing_time_limit.py │ ├── test_monitor.py │ ├── test_randomize_action.py │ ├── test_render.py │ ├── test_scale_reward.py │ └── test_vector_frame_stack.py └── tools └── plot_scores.py /.flake8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/.flake8 -------------------------------------------------------------------------------- /.github/auto_assign.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/.github/auto_assign.yml -------------------------------------------------------------------------------- /.github/workflows/auto_assign.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/.github/workflows/auto_assign.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/.gitignore -------------------------------------------------------------------------------- /.pfnci/config.pbtxt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/.pfnci/config.pbtxt -------------------------------------------------------------------------------- /.pfnci/hint.pbtxt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/.pfnci/hint.pbtxt -------------------------------------------------------------------------------- /.pfnci/lint.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/.pfnci/lint.sh -------------------------------------------------------------------------------- /.pfnci/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/.pfnci/run.sh -------------------------------------------------------------------------------- /.pfnci/script.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/.pfnci/script.sh -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/LICENSE -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/MANIFEST.in -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/README.md -------------------------------------------------------------------------------- /assets/PFRL.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/assets/PFRL.png -------------------------------------------------------------------------------- /assets/boxing.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/assets/boxing.gif -------------------------------------------------------------------------------- /assets/grasping.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/assets/grasping.gif -------------------------------------------------------------------------------- /assets/humanoid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/assets/humanoid.gif -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/action_values.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/action_values.rst -------------------------------------------------------------------------------- /docs/agents.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/agents.rst -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/conf.py -------------------------------------------------------------------------------- /docs/experiments.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/experiments.rst -------------------------------------------------------------------------------- /docs/explorers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/explorers.rst -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/index.rst -------------------------------------------------------------------------------- /docs/install.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/install.rst -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/make.bat -------------------------------------------------------------------------------- /docs/nn.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/nn.rst -------------------------------------------------------------------------------- /docs/policies.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/policies.rst -------------------------------------------------------------------------------- /docs/q_functions.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/q_functions.rst -------------------------------------------------------------------------------- /docs/reference.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/reference.rst -------------------------------------------------------------------------------- /docs/replay_buffers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/docs/replay_buffers.rst -------------------------------------------------------------------------------- /examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/README.md -------------------------------------------------------------------------------- /examples/atari/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/README.md -------------------------------------------------------------------------------- /examples/atari/reproduction/a3c/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/reproduction/a3c/README.md -------------------------------------------------------------------------------- /examples/atari/reproduction/a3c/train_a3c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/reproduction/a3c/train_a3c.py -------------------------------------------------------------------------------- /examples/atari/reproduction/dqn/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/reproduction/dqn/README.md -------------------------------------------------------------------------------- /examples/atari/reproduction/dqn/train_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/reproduction/dqn/train_dqn.py -------------------------------------------------------------------------------- /examples/atari/reproduction/iqn/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/reproduction/iqn/README.md -------------------------------------------------------------------------------- /examples/atari/reproduction/iqn/train_iqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/reproduction/iqn/train_iqn.py -------------------------------------------------------------------------------- /examples/atari/reproduction/rainbow/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/reproduction/rainbow/README.md -------------------------------------------------------------------------------- /examples/atari/reproduction/rainbow/train_rainbow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/reproduction/rainbow/train_rainbow.py -------------------------------------------------------------------------------- /examples/atari/train_a2c_ale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/train_a2c_ale.py -------------------------------------------------------------------------------- /examples/atari/train_acer_ale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/train_acer_ale.py -------------------------------------------------------------------------------- /examples/atari/train_categorical_dqn_ale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/train_categorical_dqn_ale.py -------------------------------------------------------------------------------- /examples/atari/train_dqn_ale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/train_dqn_ale.py -------------------------------------------------------------------------------- /examples/atari/train_dqn_batch_ale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/train_dqn_batch_ale.py -------------------------------------------------------------------------------- /examples/atari/train_drqn_ale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/train_drqn_ale.py -------------------------------------------------------------------------------- /examples/atari/train_ppo_ale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atari/train_ppo_ale.py -------------------------------------------------------------------------------- /examples/atlas/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atlas/README.md -------------------------------------------------------------------------------- /examples/atlas/assets/atlas.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atlas/assets/atlas.gif -------------------------------------------------------------------------------- /examples/atlas/assets/learningcurve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atlas/assets/learningcurve.png -------------------------------------------------------------------------------- /examples/atlas/train_soft_actor_critic_atlas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/atlas/train_soft_actor_critic_atlas.py -------------------------------------------------------------------------------- /examples/grasping/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/grasping/README.md -------------------------------------------------------------------------------- /examples/grasping/assets/learningcurve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/grasping/assets/learningcurve.png -------------------------------------------------------------------------------- /examples/grasping/train_dqn_batch_grasping.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/grasping/train_dqn_batch_grasping.py -------------------------------------------------------------------------------- /examples/gym/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/gym/README.md -------------------------------------------------------------------------------- /examples/gym/train_categorical_dqn_gym.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/gym/train_categorical_dqn_gym.py -------------------------------------------------------------------------------- /examples/gym/train_dqn_gym.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/gym/train_dqn_gym.py -------------------------------------------------------------------------------- /examples/gym/train_reinforce_gym.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/gym/train_reinforce_gym.py -------------------------------------------------------------------------------- /examples/mujoco/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/README.md -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ddpg/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ddpg/README.md -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ddpg/assets/Ant-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ddpg/assets/Ant-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ddpg/assets/HalfCheetah-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ddpg/assets/HalfCheetah-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ddpg/assets/Hopper-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ddpg/assets/Hopper-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ddpg/assets/InvertedDoublePendulum-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ddpg/assets/InvertedDoublePendulum-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ddpg/assets/InvertedPendulum-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ddpg/assets/InvertedPendulum-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ddpg/assets/Reacher-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ddpg/assets/Reacher-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ddpg/assets/Walker2d-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ddpg/assets/Walker2d-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ddpg/train_ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ddpg/train_ddpg.py -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ppo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ppo/README.md -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ppo/assets/HalfCheetah-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ppo/assets/HalfCheetah-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ppo/assets/Hopper-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ppo/assets/Hopper-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ppo/assets/Swimmer-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ppo/assets/Swimmer-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ppo/assets/Walker2d-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ppo/assets/Walker2d-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/ppo/train_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/ppo/train_ppo.py -------------------------------------------------------------------------------- /examples/mujoco/reproduction/soft_actor_critic/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/soft_actor_critic/README.md -------------------------------------------------------------------------------- /examples/mujoco/reproduction/soft_actor_critic/assets/Ant-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/soft_actor_critic/assets/Ant-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/soft_actor_critic/assets/HalfCheetah-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/soft_actor_critic/assets/HalfCheetah-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/soft_actor_critic/assets/Hopper-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/soft_actor_critic/assets/Hopper-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/soft_actor_critic/assets/Humanoid-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/soft_actor_critic/assets/Humanoid-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/soft_actor_critic/assets/Walker2d-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/soft_actor_critic/assets/Walker2d-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/soft_actor_critic/train_soft_actor_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/soft_actor_critic/train_soft_actor_critic.py -------------------------------------------------------------------------------- /examples/mujoco/reproduction/td3/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/td3/README.md -------------------------------------------------------------------------------- /examples/mujoco/reproduction/td3/assets/Ant-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/td3/assets/Ant-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/td3/assets/HalfCheetah-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/td3/assets/HalfCheetah-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/td3/assets/Hopper-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/td3/assets/Hopper-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/td3/assets/InvertedDoublePendulum-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/td3/assets/InvertedDoublePendulum-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/td3/assets/InvertedPendulum-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/td3/assets/InvertedPendulum-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/td3/assets/Reacher-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/td3/assets/Reacher-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/td3/assets/Walker2d-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/td3/assets/Walker2d-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/td3/train_td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/td3/train_td3.py -------------------------------------------------------------------------------- /examples/mujoco/reproduction/trpo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/trpo/README.md -------------------------------------------------------------------------------- /examples/mujoco/reproduction/trpo/assets/HalfCheetah-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/trpo/assets/HalfCheetah-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/trpo/assets/Hopper-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/trpo/assets/Hopper-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/trpo/assets/Swimmer-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/trpo/assets/Swimmer-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/trpo/assets/Walker2d-v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/trpo/assets/Walker2d-v2.png -------------------------------------------------------------------------------- /examples/mujoco/reproduction/trpo/train_trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/mujoco/reproduction/trpo/train_trpo.py -------------------------------------------------------------------------------- /examples/optuna/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/optuna/README.md -------------------------------------------------------------------------------- /examples/optuna/assets/optimization_history.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/optuna/assets/optimization_history.png -------------------------------------------------------------------------------- /examples/optuna/optuna_dqn_obs1d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/optuna/optuna_dqn_obs1d.py -------------------------------------------------------------------------------- /examples/quickstart/quickstart.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/quickstart/quickstart.ipynb -------------------------------------------------------------------------------- /examples/slimevolley/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/slimevolley/README.md -------------------------------------------------------------------------------- /examples/slimevolley/assets/learningcurve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/slimevolley/assets/learningcurve.png -------------------------------------------------------------------------------- /examples/slimevolley/assets/slimevolley.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/slimevolley/assets/slimevolley.gif -------------------------------------------------------------------------------- /examples/slimevolley/train_rainbow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples/slimevolley/train_rainbow.py -------------------------------------------------------------------------------- /examples_tests/atari/reproduction/test_dqn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/reproduction/test_dqn.sh -------------------------------------------------------------------------------- /examples_tests/atari/reproduction/test_iqn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/reproduction/test_iqn.sh -------------------------------------------------------------------------------- /examples_tests/atari/reproduction/test_rainbow.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/reproduction/test_rainbow.sh -------------------------------------------------------------------------------- /examples_tests/atari/test_a2c.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/test_a2c.sh -------------------------------------------------------------------------------- /examples_tests/atari/test_acer.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/test_acer.sh -------------------------------------------------------------------------------- /examples_tests/atari/test_categorical_dqn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/test_categorical_dqn.sh -------------------------------------------------------------------------------- /examples_tests/atari/test_dqn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/test_dqn.sh -------------------------------------------------------------------------------- /examples_tests/atari/test_dqn_batch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/test_dqn_batch.sh -------------------------------------------------------------------------------- /examples_tests/atari/test_drqn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/test_drqn.sh -------------------------------------------------------------------------------- /examples_tests/atari/test_ppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atari/test_ppo.sh -------------------------------------------------------------------------------- /examples_tests/atlas/test_soft_actor_critic.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/atlas/test_soft_actor_critic.sh -------------------------------------------------------------------------------- /examples_tests/grasping/test_dqn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/grasping/test_dqn.sh -------------------------------------------------------------------------------- /examples_tests/gym/test_categorical_dqn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/gym/test_categorical_dqn.sh -------------------------------------------------------------------------------- /examples_tests/gym/test_dqn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/gym/test_dqn.sh -------------------------------------------------------------------------------- /examples_tests/gym/test_reinforce.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/gym/test_reinforce.sh -------------------------------------------------------------------------------- /examples_tests/mujoco/reproduction/test_ddpg.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/mujoco/reproduction/test_ddpg.sh -------------------------------------------------------------------------------- /examples_tests/mujoco/reproduction/test_ppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/mujoco/reproduction/test_ppo.sh -------------------------------------------------------------------------------- /examples_tests/mujoco/reproduction/test_soft_actor_critic.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/mujoco/reproduction/test_soft_actor_critic.sh -------------------------------------------------------------------------------- /examples_tests/mujoco/reproduction/test_td3.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/mujoco/reproduction/test_td3.sh -------------------------------------------------------------------------------- /examples_tests/mujoco/reproduction/test_trpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/mujoco/reproduction/test_trpo.sh -------------------------------------------------------------------------------- /examples_tests/optuna/test_optuna_dqn_obs1d.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/optuna/test_optuna_dqn_obs1d.sh -------------------------------------------------------------------------------- /examples_tests/slimevolley/test_rainbow.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/examples_tests/slimevolley/test_rainbow.sh -------------------------------------------------------------------------------- /pfrl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/__init__.py -------------------------------------------------------------------------------- /pfrl/action_value.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/action_value.py -------------------------------------------------------------------------------- /pfrl/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agent.py -------------------------------------------------------------------------------- /pfrl/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/__init__.py -------------------------------------------------------------------------------- /pfrl/agents/a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/a2c.py -------------------------------------------------------------------------------- /pfrl/agents/a3c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/a3c.py -------------------------------------------------------------------------------- /pfrl/agents/acer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/acer.py -------------------------------------------------------------------------------- /pfrl/agents/al.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/al.py -------------------------------------------------------------------------------- /pfrl/agents/categorical_double_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/categorical_double_dqn.py -------------------------------------------------------------------------------- /pfrl/agents/categorical_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/categorical_dqn.py -------------------------------------------------------------------------------- /pfrl/agents/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/ddpg.py -------------------------------------------------------------------------------- /pfrl/agents/double_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/double_dqn.py -------------------------------------------------------------------------------- /pfrl/agents/double_pal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/double_pal.py -------------------------------------------------------------------------------- /pfrl/agents/dpp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/dpp.py -------------------------------------------------------------------------------- /pfrl/agents/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/dqn.py -------------------------------------------------------------------------------- /pfrl/agents/iqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/iqn.py -------------------------------------------------------------------------------- /pfrl/agents/pal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/pal.py -------------------------------------------------------------------------------- /pfrl/agents/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/ppo.py -------------------------------------------------------------------------------- /pfrl/agents/reinforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/reinforce.py -------------------------------------------------------------------------------- /pfrl/agents/soft_actor_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/soft_actor_critic.py -------------------------------------------------------------------------------- /pfrl/agents/state_q_function_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/state_q_function_actor.py -------------------------------------------------------------------------------- /pfrl/agents/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/td3.py -------------------------------------------------------------------------------- /pfrl/agents/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/agents/trpo.py -------------------------------------------------------------------------------- /pfrl/collections/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pfrl/collections/persistent_collections.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/collections/persistent_collections.py -------------------------------------------------------------------------------- /pfrl/collections/prioritized.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/collections/prioritized.py -------------------------------------------------------------------------------- /pfrl/collections/random_access_queue.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/collections/random_access_queue.py -------------------------------------------------------------------------------- /pfrl/distributions/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/distributions/__init__.py -------------------------------------------------------------------------------- /pfrl/distributions/delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/distributions/delta.py -------------------------------------------------------------------------------- /pfrl/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/env.py -------------------------------------------------------------------------------- /pfrl/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/envs/__init__.py -------------------------------------------------------------------------------- /pfrl/envs/abc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/envs/abc.py -------------------------------------------------------------------------------- /pfrl/envs/multiprocess_vector_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/envs/multiprocess_vector_env.py -------------------------------------------------------------------------------- /pfrl/envs/serial_vector_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/envs/serial_vector_env.py -------------------------------------------------------------------------------- /pfrl/experiments/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/experiments/__init__.py -------------------------------------------------------------------------------- /pfrl/experiments/evaluation_hooks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/experiments/evaluation_hooks.py -------------------------------------------------------------------------------- /pfrl/experiments/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/experiments/evaluator.py -------------------------------------------------------------------------------- /pfrl/experiments/hooks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/experiments/hooks.py -------------------------------------------------------------------------------- /pfrl/experiments/prepare_output_dir.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/experiments/prepare_output_dir.py -------------------------------------------------------------------------------- /pfrl/experiments/train_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/experiments/train_agent.py -------------------------------------------------------------------------------- /pfrl/experiments/train_agent_async.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/experiments/train_agent_async.py -------------------------------------------------------------------------------- /pfrl/experiments/train_agent_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/experiments/train_agent_batch.py -------------------------------------------------------------------------------- /pfrl/explorer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/explorer.py -------------------------------------------------------------------------------- /pfrl/explorers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/explorers/__init__.py -------------------------------------------------------------------------------- /pfrl/explorers/additive_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/explorers/additive_gaussian.py -------------------------------------------------------------------------------- /pfrl/explorers/additive_ou.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/explorers/additive_ou.py -------------------------------------------------------------------------------- /pfrl/explorers/boltzmann.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/explorers/boltzmann.py -------------------------------------------------------------------------------- /pfrl/explorers/epsilon_greedy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/explorers/epsilon_greedy.py -------------------------------------------------------------------------------- /pfrl/explorers/greedy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/explorers/greedy.py -------------------------------------------------------------------------------- /pfrl/functions/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pfrl/functions/bound_by_tanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/functions/bound_by_tanh.py -------------------------------------------------------------------------------- /pfrl/functions/lower_triangular_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/functions/lower_triangular_matrix.py -------------------------------------------------------------------------------- /pfrl/initializers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/initializers/__init__.py -------------------------------------------------------------------------------- /pfrl/initializers/chainer_default.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/initializers/chainer_default.py -------------------------------------------------------------------------------- /pfrl/initializers/lecun_normal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/initializers/lecun_normal.py -------------------------------------------------------------------------------- /pfrl/nn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/__init__.py -------------------------------------------------------------------------------- /pfrl/nn/atari_cnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/atari_cnn.py -------------------------------------------------------------------------------- /pfrl/nn/bound_by_tanh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/bound_by_tanh.py -------------------------------------------------------------------------------- /pfrl/nn/branched.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/branched.py -------------------------------------------------------------------------------- /pfrl/nn/concat_obs_and_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/concat_obs_and_action.py -------------------------------------------------------------------------------- /pfrl/nn/empirical_normalization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/empirical_normalization.py -------------------------------------------------------------------------------- /pfrl/nn/lmbda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/lmbda.py -------------------------------------------------------------------------------- /pfrl/nn/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/mlp.py -------------------------------------------------------------------------------- /pfrl/nn/mlp_bn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/mlp_bn.py -------------------------------------------------------------------------------- /pfrl/nn/noisy_chain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/noisy_chain.py -------------------------------------------------------------------------------- /pfrl/nn/noisy_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/noisy_linear.py -------------------------------------------------------------------------------- /pfrl/nn/recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/recurrent.py -------------------------------------------------------------------------------- /pfrl/nn/recurrent_branched.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/recurrent_branched.py -------------------------------------------------------------------------------- /pfrl/nn/recurrent_sequential.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/nn/recurrent_sequential.py -------------------------------------------------------------------------------- /pfrl/optimizers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/optimizers/__init__.py -------------------------------------------------------------------------------- /pfrl/optimizers/rmsprop_eps_inside_sqrt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/optimizers/rmsprop_eps_inside_sqrt.py -------------------------------------------------------------------------------- /pfrl/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/policies/__init__.py -------------------------------------------------------------------------------- /pfrl/policies/deterministic_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/policies/deterministic_policy.py -------------------------------------------------------------------------------- /pfrl/policies/gaussian_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/policies/gaussian_policy.py -------------------------------------------------------------------------------- /pfrl/policies/softmax_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/policies/softmax_policy.py -------------------------------------------------------------------------------- /pfrl/policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/policy.py -------------------------------------------------------------------------------- /pfrl/q_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/q_function.py -------------------------------------------------------------------------------- /pfrl/q_functions/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/q_functions/__init__.py -------------------------------------------------------------------------------- /pfrl/q_functions/dueling_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/q_functions/dueling_dqn.py -------------------------------------------------------------------------------- /pfrl/q_functions/state_action_q_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/q_functions/state_action_q_functions.py -------------------------------------------------------------------------------- /pfrl/q_functions/state_q_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/q_functions/state_q_functions.py -------------------------------------------------------------------------------- /pfrl/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/replay_buffer.py -------------------------------------------------------------------------------- /pfrl/replay_buffers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/replay_buffers/__init__.py -------------------------------------------------------------------------------- /pfrl/replay_buffers/episodic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/replay_buffers/episodic.py -------------------------------------------------------------------------------- /pfrl/replay_buffers/persistent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/replay_buffers/persistent.py -------------------------------------------------------------------------------- /pfrl/replay_buffers/prioritized.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/replay_buffers/prioritized.py -------------------------------------------------------------------------------- /pfrl/replay_buffers/prioritized_episodic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/replay_buffers/prioritized_episodic.py -------------------------------------------------------------------------------- /pfrl/replay_buffers/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/replay_buffers/replay_buffer.py -------------------------------------------------------------------------------- /pfrl/testing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/testing.py -------------------------------------------------------------------------------- /pfrl/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/__init__.py -------------------------------------------------------------------------------- /pfrl/utils/ask_yes_no.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/ask_yes_no.py -------------------------------------------------------------------------------- /pfrl/utils/async_.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/async_.py -------------------------------------------------------------------------------- /pfrl/utils/batch_states.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/batch_states.py -------------------------------------------------------------------------------- /pfrl/utils/clip_l2_grad_norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/clip_l2_grad_norm.py -------------------------------------------------------------------------------- /pfrl/utils/conjugate_gradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/conjugate_gradient.py -------------------------------------------------------------------------------- /pfrl/utils/contexts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/contexts.py -------------------------------------------------------------------------------- /pfrl/utils/copy_param.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/copy_param.py -------------------------------------------------------------------------------- /pfrl/utils/env_modifiers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/env_modifiers.py -------------------------------------------------------------------------------- /pfrl/utils/is_return_code_zero.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/is_return_code_zero.py -------------------------------------------------------------------------------- /pfrl/utils/mode_of_distribution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/mode_of_distribution.py -------------------------------------------------------------------------------- /pfrl/utils/pretrained_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/pretrained_models.py -------------------------------------------------------------------------------- /pfrl/utils/random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/random.py -------------------------------------------------------------------------------- /pfrl/utils/random_seed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/random_seed.py -------------------------------------------------------------------------------- /pfrl/utils/recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/recurrent.py -------------------------------------------------------------------------------- /pfrl/utils/reward_filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/reward_filter.py -------------------------------------------------------------------------------- /pfrl/utils/stoppable_thread.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/utils/stoppable_thread.py -------------------------------------------------------------------------------- /pfrl/wrappers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/__init__.py -------------------------------------------------------------------------------- /pfrl/wrappers/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/atari_wrappers.py -------------------------------------------------------------------------------- /pfrl/wrappers/cast_observation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/cast_observation.py -------------------------------------------------------------------------------- /pfrl/wrappers/continuing_time_limit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/continuing_time_limit.py -------------------------------------------------------------------------------- /pfrl/wrappers/monitor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/monitor.py -------------------------------------------------------------------------------- /pfrl/wrappers/normalize_action_space.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/normalize_action_space.py -------------------------------------------------------------------------------- /pfrl/wrappers/randomize_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/randomize_action.py -------------------------------------------------------------------------------- /pfrl/wrappers/render.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/render.py -------------------------------------------------------------------------------- /pfrl/wrappers/scale_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/scale_reward.py -------------------------------------------------------------------------------- /pfrl/wrappers/vector_frame_stack.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pfrl/wrappers/vector_frame_stack.py -------------------------------------------------------------------------------- /pytest.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/pytest.ini -------------------------------------------------------------------------------- /readthedocs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/readthedocs.yml -------------------------------------------------------------------------------- /requirements-dev.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/requirements-dev.txt -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | torch>=1.3.0 2 | gym>=0.9.7 3 | numpy>=1.10.4 4 | filelock 5 | pillow 6 | -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/setup.py -------------------------------------------------------------------------------- /test_examples.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/test_examples.sh -------------------------------------------------------------------------------- /tests/agents_tests/basetest_ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/basetest_ddpg.py -------------------------------------------------------------------------------- /tests/agents_tests/basetest_dqn_like.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/basetest_dqn_like.py -------------------------------------------------------------------------------- /tests/agents_tests/basetest_training.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/basetest_training.py -------------------------------------------------------------------------------- /tests/agents_tests/test_a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_a2c.py -------------------------------------------------------------------------------- /tests/agents_tests/test_a3c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_a3c.py -------------------------------------------------------------------------------- /tests/agents_tests/test_acer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_acer.py -------------------------------------------------------------------------------- /tests/agents_tests/test_al.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_al.py -------------------------------------------------------------------------------- /tests/agents_tests/test_categorical_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_categorical_dqn.py -------------------------------------------------------------------------------- /tests/agents_tests/test_ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_ddpg.py -------------------------------------------------------------------------------- /tests/agents_tests/test_double_categorical_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_double_categorical_dqn.py -------------------------------------------------------------------------------- /tests/agents_tests/test_double_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_double_dqn.py -------------------------------------------------------------------------------- /tests/agents_tests/test_double_pal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_double_pal.py -------------------------------------------------------------------------------- /tests/agents_tests/test_dpp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_dpp.py -------------------------------------------------------------------------------- /tests/agents_tests/test_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_dqn.py -------------------------------------------------------------------------------- /tests/agents_tests/test_iqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_iqn.py -------------------------------------------------------------------------------- /tests/agents_tests/test_pal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_pal.py -------------------------------------------------------------------------------- /tests/agents_tests/test_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_ppo.py -------------------------------------------------------------------------------- /tests/agents_tests/test_reinforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_reinforce.py -------------------------------------------------------------------------------- /tests/agents_tests/test_soft_actor_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_soft_actor_critic.py -------------------------------------------------------------------------------- /tests/agents_tests/test_td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_td3.py -------------------------------------------------------------------------------- /tests/agents_tests/test_trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/agents_tests/test_trpo.py -------------------------------------------------------------------------------- /tests/collections_tests/test_persistent_collections.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/collections_tests/test_persistent_collections.py -------------------------------------------------------------------------------- /tests/collections_tests/test_prioritized.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/collections_tests/test_prioritized.py -------------------------------------------------------------------------------- /tests/collections_tests/test_random_access_queue.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/collections_tests/test_random_access_queue.py -------------------------------------------------------------------------------- /tests/envs_tests/test_vector_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/envs_tests/test_vector_envs.py -------------------------------------------------------------------------------- /tests/experiments_tests/test_evaluation_hooks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/experiments_tests/test_evaluation_hooks.py -------------------------------------------------------------------------------- /tests/experiments_tests/test_evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/experiments_tests/test_evaluator.py -------------------------------------------------------------------------------- /tests/experiments_tests/test_hooks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/experiments_tests/test_hooks.py -------------------------------------------------------------------------------- /tests/experiments_tests/test_prepare_output_dir.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/experiments_tests/test_prepare_output_dir.py -------------------------------------------------------------------------------- /tests/experiments_tests/test_train_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/experiments_tests/test_train_agent.py -------------------------------------------------------------------------------- /tests/experiments_tests/test_train_agent_async.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/experiments_tests/test_train_agent_async.py -------------------------------------------------------------------------------- /tests/experiments_tests/test_train_agent_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/experiments_tests/test_train_agent_batch.py -------------------------------------------------------------------------------- /tests/explorers_tests/test_additive_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/explorers_tests/test_additive_gaussian.py -------------------------------------------------------------------------------- /tests/explorers_tests/test_additive_ou.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/explorers_tests/test_additive_ou.py -------------------------------------------------------------------------------- /tests/explorers_tests/test_boltzmann.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/explorers_tests/test_boltzmann.py -------------------------------------------------------------------------------- /tests/explorers_tests/test_epsilon_greedy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/explorers_tests/test_epsilon_greedy.py -------------------------------------------------------------------------------- /tests/functions_tests/test_lower_triangular_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/functions_tests/test_lower_triangular_matrix.py -------------------------------------------------------------------------------- /tests/misc_tests/tests_persistent_collections.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/nn_tests/test_branched.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/nn_tests/test_branched.py -------------------------------------------------------------------------------- /tests/nn_tests/test_empirical_normalization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/nn_tests/test_empirical_normalization.py -------------------------------------------------------------------------------- /tests/nn_tests/test_lmbda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/nn_tests/test_lmbda.py -------------------------------------------------------------------------------- /tests/nn_tests/test_mlp_bn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/nn_tests/test_mlp_bn.py -------------------------------------------------------------------------------- /tests/nn_tests/test_noisy_chain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/nn_tests/test_noisy_chain.py -------------------------------------------------------------------------------- /tests/nn_tests/test_noisy_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/nn_tests/test_noisy_linear.py -------------------------------------------------------------------------------- /tests/nn_tests/test_recurrent_branched.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/nn_tests/test_recurrent_branched.py -------------------------------------------------------------------------------- /tests/nn_tests/test_recurrent_sequential.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/nn_tests/test_recurrent_sequential.py -------------------------------------------------------------------------------- /tests/q_functions_tests/basetest_state_action_q_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/q_functions_tests/basetest_state_action_q_function.py -------------------------------------------------------------------------------- /tests/q_functions_tests/test_state_action_q_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/q_functions_tests/test_state_action_q_function.py -------------------------------------------------------------------------------- /tests/replay_buffers_test/test_persistent_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/replay_buffers_test/test_persistent_replay_buffer.py -------------------------------------------------------------------------------- /tests/replay_buffers_test/test_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/replay_buffers_test/test_replay_buffer.py -------------------------------------------------------------------------------- /tests/test_action_value.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/test_action_value.py -------------------------------------------------------------------------------- /tests/test_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/test_agent.py -------------------------------------------------------------------------------- /tests/test_testing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/test_testing.py -------------------------------------------------------------------------------- /tests/utils_tests/test_async.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_async.py -------------------------------------------------------------------------------- /tests/utils_tests/test_batch_states.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_batch_states.py -------------------------------------------------------------------------------- /tests/utils_tests/test_clip_l2_grad_norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_clip_l2_grad_norm.py -------------------------------------------------------------------------------- /tests/utils_tests/test_conjugate_gradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_conjugate_gradient.py -------------------------------------------------------------------------------- /tests/utils_tests/test_contexts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_contexts.py -------------------------------------------------------------------------------- /tests/utils_tests/test_copy_param.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_copy_param.py -------------------------------------------------------------------------------- /tests/utils_tests/test_is_return_code_zero.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_is_return_code_zero.py -------------------------------------------------------------------------------- /tests/utils_tests/test_mode_of_distribution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_mode_of_distribution.py -------------------------------------------------------------------------------- /tests/utils_tests/test_pretrained_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_pretrained_models.py -------------------------------------------------------------------------------- /tests/utils_tests/test_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_random.py -------------------------------------------------------------------------------- /tests/utils_tests/test_random_seed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_random_seed.py -------------------------------------------------------------------------------- /tests/utils_tests/test_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_recurrent.py -------------------------------------------------------------------------------- /tests/utils_tests/test_stoppable_thread.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/utils_tests/test_stoppable_thread.py -------------------------------------------------------------------------------- /tests/wrappers_tests/test_atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/wrappers_tests/test_atari_wrappers.py -------------------------------------------------------------------------------- /tests/wrappers_tests/test_cast_observation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/wrappers_tests/test_cast_observation.py -------------------------------------------------------------------------------- /tests/wrappers_tests/test_continuing_time_limit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/wrappers_tests/test_continuing_time_limit.py -------------------------------------------------------------------------------- /tests/wrappers_tests/test_monitor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/wrappers_tests/test_monitor.py -------------------------------------------------------------------------------- /tests/wrappers_tests/test_randomize_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/wrappers_tests/test_randomize_action.py -------------------------------------------------------------------------------- /tests/wrappers_tests/test_render.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/wrappers_tests/test_render.py -------------------------------------------------------------------------------- /tests/wrappers_tests/test_scale_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/wrappers_tests/test_scale_reward.py -------------------------------------------------------------------------------- /tests/wrappers_tests/test_vector_frame_stack.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tests/wrappers_tests/test_vector_frame_stack.py -------------------------------------------------------------------------------- /tools/plot_scores.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pfnet/pfrl/HEAD/tools/plot_scores.py --------------------------------------------------------------------------------