LICENSE
README.md
setup.py
examples/__init__.py
openrl/__init__.py
openrl.egg-info/PKG-INFO
openrl.egg-info/SOURCES.txt
openrl.egg-info/dependency_links.txt
openrl.egg-info/entry_points.txt
openrl.egg-info/requires.txt
openrl.egg-info/top_level.txt
openrl/algorithms/__init__.py
openrl/algorithms/a2c.py
openrl/algorithms/base_algorithm.py
openrl/algorithms/behavior_cloning.py
openrl/algorithms/ddpg.py
openrl/algorithms/dqn.py
openrl/algorithms/gail.py
openrl/algorithms/mat.py
openrl/algorithms/ppo.py
openrl/algorithms/sac.py
openrl/algorithms/vdn.py
openrl/arena/__init__.py
openrl/arena/base_arena.py
openrl/arena/two_player_arena.py
openrl/arena/utils.py
openrl/arena/agents/__init__.py
openrl/arena/agents/base_agent.py
openrl/arena/agents/jidi_agent.py
openrl/arena/agents/local_agent.py
openrl/arena/games/__init__.py
openrl/arena/games/base_game.py
openrl/arena/games/two_player_game.py
openrl/buffers/__init__.py
openrl/buffers/normal_buffer.py
openrl/buffers/offpolicy_buffer.py
openrl/buffers/offpolicy_replay_data.py
openrl/buffers/replay_data.py
openrl/buffers/utils/__init__.py
openrl/buffers/utils/obs_data.py
openrl/buffers/utils/util.py
openrl/cli/__init__.py
openrl/cli/cli.py
openrl/cli/train.py
openrl/configs/__init__.py
openrl/configs/config.py
openrl/configs/utils.py
openrl/datasets/__init__.py
openrl/datasets/expert_dataset.py
openrl/drivers/__init__.py
openrl/drivers/base_driver.py
openrl/drivers/offline_driver.py
openrl/drivers/offpolicy_driver.py
openrl/drivers/onpolicy_driver.py
openrl/drivers/rl_driver.py
openrl/envs/__init__.py
openrl/envs/PettingZoo/__init__.py
openrl/envs/PettingZoo/registration.py
openrl/envs/common/__init__.py
openrl/envs/common/build_envs.py
openrl/envs/common/registration.py
openrl/envs/connect_env/__init__.py
openrl/envs/connect_env/base_connect_env.py
openrl/envs/connect_env/connect3_env.py
openrl/envs/connect_env/connect4_env.py
openrl/envs/connect_env/utils.py
openrl/envs/gridworld/__init__.py
openrl/envs/gridworld/gridworld_env.py
openrl/envs/gym_pybullet_drones/__init__.py
openrl/envs/gymnasium/__init__.py
openrl/envs/mpe/__init__.py
openrl/envs/mpe/core.py
openrl/envs/mpe/mpe_env.py
openrl/envs/mpe/multi_discrete.py
openrl/envs/mpe/multiagent_env.py
openrl/envs/mpe/rendering.py
openrl/envs/mpe/scenario.py
openrl/envs/mpe/scenarios/__init__.py
openrl/envs/mpe/scenarios/simple_spread.py
openrl/envs/nlp/__init__.py
openrl/envs/nlp/daily_dialog_env.py
openrl/envs/nlp/fake_dialog_env.py
openrl/envs/nlp/nlp_env.py
openrl/envs/nlp/utils/__init__.py
openrl/envs/nlp/utils/custom_text_generation_pools.py
openrl/envs/nlp/utils/distribution.py
openrl/envs/nlp/utils/evaluation_utils.py
openrl/envs/nlp/utils/observation.py
openrl/envs/nlp/utils/sampler.py
openrl/envs/nlp/utils/text_generation_pool.py
openrl/envs/nlp/utils/metrics/__init__.py
openrl/envs/nlp/utils/metrics/meteor.py
openrl/envs/offline/__init__.py
openrl/envs/offline/offline_env.py
openrl/envs/snake/__init__.py
openrl/envs/snake/discrete.py
openrl/envs/snake/game.py
openrl/envs/snake/gridgame.py
openrl/envs/snake/observation.py
openrl/envs/snake/snake.py
openrl/envs/snake/snake_pettingzoo.py
openrl/envs/snake/space.py
openrl/envs/super_mario/__init__.py
openrl/envs/super_mario/super_mario_convert.py
openrl/envs/toy_envs/__init__.py
openrl/envs/toy_envs/bit_flipping_env.py
openrl/envs/toy_envs/identity_env.py
openrl/envs/toy_envs/multi_input_envs.py
openrl/envs/vec_env/__init__.py
openrl/envs/vec_env/async_venv.py
openrl/envs/vec_env/base_venv.py
openrl/envs/vec_env/sync_venv.py
openrl/envs/vec_env/utils/__init__.py
openrl/envs/vec_env/utils/numpy_utils.py
openrl/envs/vec_env/utils/share_memory.py
openrl/envs/vec_env/utils/util.py
openrl/envs/vec_env/vec_info/__init__.py
openrl/envs/vec_env/vec_info/base_vec_info.py
openrl/envs/vec_env/vec_info/episode_rewards_info.py
openrl/envs/vec_env/vec_info/nlp_vec_info.py
openrl/envs/vec_env/vec_info/simple_vec_info.py
openrl/envs/vec_env/wrappers/__init__.py
openrl/envs/vec_env/wrappers/base_wrapper.py
openrl/envs/vec_env/wrappers/gen_data.py
openrl/envs/vec_env/wrappers/reward_wrapper.py
openrl/envs/vec_env/wrappers/vec_monitor_wrapper.py
openrl/envs/vec_env/wrappers/zero_reward_wrapper.py
openrl/envs/wrappers/__init__.py
openrl/envs/wrappers/atari_wrappers.py
openrl/envs/wrappers/base_wrapper.py
openrl/envs/wrappers/extra_wrappers.py
openrl/envs/wrappers/flatten.py
openrl/envs/wrappers/image_wrappers.py
openrl/envs/wrappers/mat_wrapper.py
openrl/envs/wrappers/monitor.py
openrl/envs/wrappers/multiagent_wrapper.py
openrl/envs/wrappers/pettingzoo_wrappers.py
openrl/envs/wrappers/util.py
openrl/modules/__init__.py
openrl/modules/base_module.py
openrl/modules/bc_module.py
openrl/modules/ddpg_module.py
openrl/modules/dqn_module.py
openrl/modules/gail_module.py
openrl/modules/model_config.py
openrl/modules/ppo_module.py
openrl/modules/rl_module.py
openrl/modules/sac_module.py
openrl/modules/vdn_module.py
openrl/modules/common/__init__.py
openrl/modules/common/a2c_net.py
openrl/modules/common/base_net.py
openrl/modules/common/bc_net.py
openrl/modules/common/ddpg_net.py
openrl/modules/common/dqn_net.py
openrl/modules/common/gail_net.py
openrl/modules/common/mat_net.py
openrl/modules/common/ppo_net.py
openrl/modules/common/sac_net.py
openrl/modules/common/vdn_net.py
openrl/modules/networks/MAT_network.py
openrl/modules/networks/__init__.py
openrl/modules/networks/base_policy_network.py
openrl/modules/networks/base_value_network.py
openrl/modules/networks/base_value_policy_network.py
openrl/modules/networks/ddpg_network.py
openrl/modules/networks/gail_discriminator.py
openrl/modules/networks/policy_network.py
openrl/modules/networks/policy_value_network.py
openrl/modules/networks/policy_value_network_gpt.py
openrl/modules/networks/policy_value_network_sb3.py
openrl/modules/networks/q_network.py
openrl/modules/networks/sac_network.py
openrl/modules/networks/value_network.py
openrl/modules/networks/vdn_network.py
openrl/modules/networks/utils/__init__.py
openrl/modules/networks/utils/act.py
openrl/modules/networks/utils/attention.py
openrl/modules/networks/utils/cnn.py
openrl/modules/networks/utils/distributed_utils.py
openrl/modules/networks/utils/distributions.py
openrl/modules/networks/utils/mix.py
openrl/modules/networks/utils/mlp.py
openrl/modules/networks/utils/popart.py
openrl/modules/networks/utils/rnn.py
openrl/modules/networks/utils/running_mean_std.py
openrl/modules/networks/utils/transformer_act.py
openrl/modules/networks/utils/util.py
openrl/modules/networks/utils/vdn.py
openrl/modules/networks/utils/nlp/__init__.py
openrl/modules/networks/utils/nlp/base_policy.py
openrl/modules/networks/utils/nlp/causal_policy.py
openrl/modules/utils/__init__.py
openrl/modules/utils/util.py
openrl/modules/utils/valuenorm.py
openrl/rewards/__init__.py
openrl/rewards/base_reward.py
openrl/rewards/gail_reward.py
openrl/rewards/nlp_reward.py
openrl/runners/__init__.py
openrl/runners/common/__init__.py
openrl/runners/common/a2c_agent.py
openrl/runners/common/base_agent.py
openrl/runners/common/bc_agent.py
openrl/runners/common/chat_agent.py
openrl/runners/common/ddpg_agent.py
openrl/runners/common/dqn_agent.py
openrl/runners/common/gail_agent.py
openrl/runners/common/mat_agent.py
openrl/runners/common/ppo_agent.py
openrl/runners/common/rl_agent.py
openrl/runners/common/sac_agent.py
openrl/runners/common/vdn_agent.py
openrl/selfplay/__init__.py
openrl/selfplay/multiplayer_env.py
openrl/selfplay/callbacks/__init__.py
openrl/selfplay/callbacks/base_callback.py
openrl/selfplay/callbacks/selfplay_api.py
openrl/selfplay/callbacks/selfplay_callback.py
openrl/selfplay/opponents/__init__.py
openrl/selfplay/opponents/base_opponent.py
openrl/selfplay/opponents/jidi_opponent.py
openrl/selfplay/opponents/network_opponent.py
openrl/selfplay/opponents/opponent_env.py
openrl/selfplay/opponents/opponent_template.py
openrl/selfplay/opponents/random_opponent.py
openrl/selfplay/opponents/utils.py
openrl/selfplay/sample_strategy/__init__.py
openrl/selfplay/sample_strategy/base_sample_strategy.py
openrl/selfplay/sample_strategy/last_opponent.py
openrl/selfplay/sample_strategy/random_opponent.py
openrl/selfplay/selfplay_api/__init__.py
openrl/selfplay/selfplay_api/base_api.py
openrl/selfplay/selfplay_api/opponent_model.py
openrl/selfplay/selfplay_api/selfplay_api.py
openrl/selfplay/selfplay_api/selfplay_client.py
openrl/selfplay/strategies/__init__.py
openrl/selfplay/strategies/base_strategy.py
openrl/selfplay/strategies/strategies.py
openrl/selfplay/wrappers/__init__.py
openrl/selfplay/wrappers/base_multiplayer_wrapper.py
openrl/selfplay/wrappers/human_opponent_wrapper.py
openrl/selfplay/wrappers/opponent_pool_wrapper.py
openrl/selfplay/wrappers/random_opponent_wrapper.py
openrl/supports/__init__.py
openrl/supports/opendata/__init__.py
openrl/supports/opendata/utils/__init__.py
openrl/supports/opendata/utils/opendata_utils.py
openrl/supports/opengpu/__init__.py
openrl/supports/opengpu/gpu_info.py
openrl/supports/opengpu/manager.py
openrl/utils/__init__.py
openrl/utils/custom_data_structure.py
openrl/utils/evaluation.py
openrl/utils/file_tool.py
openrl/utils/logger.py
openrl/utils/type_aliases.py
openrl/utils/util.py
openrl/utils/callbacks/__init__.py
openrl/utils/callbacks/callbacks.py
openrl/utils/callbacks/callbacks_factory.py
openrl/utils/callbacks/checkpoint_callback.py
openrl/utils/callbacks/eval_callback.py
openrl/utils/callbacks/processbar_callback.py
openrl/utils/callbacks/stop_callback.py
tests/project/test_version.py
tests/test_buffer/test_buffer.py