All modules for which code is available

• openrl.algorithms.a2c
• openrl.algorithms.base_algorithm
• openrl.algorithms.behavior_cloning
• openrl.algorithms.ddpg
• openrl.algorithms.dqn
• openrl.algorithms.gail
• openrl.algorithms.mat
• openrl.algorithms.ppo
• openrl.algorithms.sac
• openrl.algorithms.vdn
• openrl.buffers.normal_buffer
• openrl.buffers.offpolicy_buffer
• openrl.buffers.offpolicy_replay_data
• openrl.buffers.replay_data
• openrl.buffers.utils.obs_data
• openrl.buffers.utils.util
• openrl.cli.cli
• openrl.configs.config
• openrl.configs.utils
• openrl.datasets.expert_dataset
• openrl.drivers.base_driver
• openrl.envs.PettingZoo.registration
• openrl.envs.common.build_envs
• openrl.envs.common.registration
• openrl.envs.connect_env
• openrl.envs.connect_env.base_connect_env
• openrl.envs.connect_env.connect3_env
• openrl.envs.connect_env.connect4_env
• openrl.envs.connect_env.utils
• openrl.envs.gridworld
• openrl.envs.gridworld.gridworld_env
• openrl.envs.gym_pybullet_drones
• openrl.envs.gymnasium
• openrl.envs.mpe
• openrl.envs.mpe.core
• openrl.envs.mpe.mpe_env
• openrl.envs.mpe.multi_discrete
• openrl.envs.mpe.multiagent_env
• openrl.envs.mpe.rendering
• openrl.envs.mpe.scenario
• openrl.envs.mpe.scenarios
• openrl.envs.mpe.scenarios.simple_spread
• openrl.envs.offline
• openrl.envs.offline.offline_env
• openrl.envs.toy_envs.bit_flipping_env
• openrl.envs.toy_envs.identity_env
• openrl.envs.vec_env.async_venv
• openrl.envs.vec_env.base_venv
• openrl.envs.vec_env.sync_venv
• openrl.envs.vec_env.utils.numpy_utils
• openrl.envs.vec_env.utils.share_memory
• openrl.envs.vec_env.utils.util
• openrl.envs.vec_env.vec_info
• openrl.envs.vec_env.vec_info.base_vec_info
• openrl.envs.vec_env.vec_info.episode_rewards_info
• openrl.envs.vec_env.vec_info.nlp_vec_info
• openrl.envs.vec_env.vec_info.simple_vec_info
• openrl.envs.vec_env.wrappers.base_wrapper
• openrl.envs.vec_env.wrappers.gen_data
• openrl.envs.vec_env.wrappers.reward_wrapper
• openrl.envs.vec_env.wrappers.vec_monitor_wrapper
• openrl.envs.vec_env.wrappers.zero_reward_wrapper
• openrl.envs.wrappers.atari_wrappers
• openrl.envs.wrappers.base_wrapper
• openrl.envs.wrappers.extra_wrappers
• openrl.envs.wrappers.flatten
• openrl.envs.wrappers.image_wrappers
• openrl.envs.wrappers.mat_wrapper
• openrl.envs.wrappers.monitor
• openrl.envs.wrappers.multiagent_wrapper
• openrl.envs.wrappers.util
• openrl.modules.base_module
• openrl.modules.bc_module
• openrl.modules.common.a2c_net
• openrl.modules.common.base_net
• openrl.modules.common.bc_net
• openrl.modules.common.ddpg_net
• openrl.modules.common.dqn_net
• openrl.modules.common.gail_net
• openrl.modules.common.mat_net
• openrl.modules.common.ppo_net
• openrl.modules.common.sac_net
• openrl.modules.common.vdn_net
• openrl.modules.ddpg_module
• openrl.modules.dqn_module
• openrl.modules.gail_module
• openrl.modules.model_config
• openrl.modules.networks.MAT_network
• openrl.modules.networks.base_policy_network
• openrl.modules.networks.base_value_network
• openrl.modules.networks.base_value_policy_network
• openrl.modules.networks.ddpg_network
• openrl.modules.networks.gail_discriminator
• openrl.modules.networks.policy_network
• openrl.modules.networks.policy_value_network
• openrl.modules.networks.q_network
• openrl.modules.networks.sac_network
• openrl.modules.networks.utils.act
• openrl.modules.networks.utils.attention
• openrl.modules.networks.utils.cnn
• openrl.modules.networks.utils.distributed_utils
• openrl.modules.networks.utils.distributions
• openrl.modules.networks.utils.mix
• openrl.modules.networks.utils.mlp
• openrl.modules.networks.utils.popart
• openrl.modules.networks.utils.rnn
• openrl.modules.networks.utils.running_mean_std
• openrl.modules.networks.utils.transformer_act
• openrl.modules.networks.utils.util
• openrl.modules.networks.utils.vdn
• openrl.modules.networks.value_network
• openrl.modules.networks.vdn_network
• openrl.modules.ppo_module
• openrl.modules.rl_module
• openrl.modules.sac_module
• openrl.modules.utils.util
• openrl.modules.utils.valuenorm
• openrl.modules.vdn_module
• openrl.rewards
• openrl.rewards.base_reward
• openrl.rewards.gail_reward
• openrl.runners.common.a2c_agent
• openrl.runners.common.base_agent
• openrl.runners.common.bc_agent
• openrl.runners.common.chat_agent
• openrl.runners.common.ddpg_agent
• openrl.runners.common.dqn_agent
• openrl.runners.common.gail_agent
• openrl.runners.common.mat_agent
• openrl.runners.common.ppo_agent
• openrl.runners.common.rl_agent
• openrl.runners.common.sac_agent
• openrl.runners.common.vdn_agent
• openrl.selfplay.callbacks.base_callback
• openrl.selfplay.callbacks.selfplay_callback
• openrl.selfplay.opponents.base_opponent
• openrl.selfplay.opponents.jidi_opponent
• openrl.selfplay.opponents.network_opponent
• openrl.selfplay.opponents.opponent_env
• openrl.selfplay.opponents.opponent_template
• openrl.selfplay.opponents.random_opponent
• openrl.selfplay.opponents.utils
• openrl.selfplay.sample_strategy
• openrl.selfplay.sample_strategy.base_sample_strategy
• openrl.selfplay.sample_strategy.last_opponent
• openrl.selfplay.sample_strategy.random_opponent
• openrl.selfplay.selfplay_api.selfplay_client
• openrl.selfplay.wrappers.base_multiplayer_wrapper
• openrl.selfplay.wrappers.human_opponent_wrapper
• openrl.selfplay.wrappers.opponent_pool_wrapper
• openrl.selfplay.wrappers.random_opponent_wrapper
• openrl.supports.opendata.utils.opendata_utils
• openrl.supports.opengpu.gpu_info
• openrl.supports.opengpu.manager
• openrl.utils.callbacks.callbacks
• openrl.utils.callbacks.callbacks_factory
• openrl.utils.callbacks.checkpoint_callback
• openrl.utils.callbacks.eval_callback
• openrl.utils.callbacks.processbar_callback
• openrl.utils.callbacks.stop_callback
• openrl.utils.custom_data_structure
• openrl.utils.evaluation
• openrl.utils.file_tool
• openrl.utils.logger
• openrl.utils.type_aliases
• openrl.utils.util