Index

A

A2C (class in pytorchrl.agent.algorithms.on_policy.a2c), [1] acting_step() (pytorchrl.agent.algorithms.base.Algorithm method) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS method), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG method), [1] (pytorchrl.agent.algorithms.off_policy.ddqn.DDQN method), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO method), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 method), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C method), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO method), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO method), [1] Action (pytorchrl.DataTransition property) Actor (class in pytorchrl.agent.actors.base) actor (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer attribute), [1] (pytorchrl.scheme.base.worker.Worker attribute) (pytorchrl.scheme.collection.c_worker.CWorker attribute) (pytorchrl.scheme.gradients.g_worker.GWorker attribute) actor_initial_states() (pytorchrl.agent.actors.base.Actor method) (pytorchrl.agent.actors.model_based_planner_actor.ModelBasedPlannerActor method), [1] (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor method), [1] (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor method), [1] actor_version (pytorchrl.scheme.collection.c_worker.CWorker attribute) (pytorchrl.scheme.gradients.g_worker.GWorker property) (pytorchrl.scheme.updates.u_worker.UWorker property) add_workers() (pytorchrl.scheme.base.worker_set.WorkerSet method) after_gradients() (pytorchrl.agent.storages.base.Storage method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.ere_buffer.EREBuffer method), [1] (pytorchrl.agent.storages.off_policy.per_buffer.PERBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1]

algo (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer attribute), [1] (pytorchrl.scheme.collection.c_worker.CWorker attribute) (pytorchrl.scheme.gradients.g_worker.GWorker attribute) Algorithm (class in pytorchrl.agent.algorithms.base) angle_normalize() (in module pytorchrl.agent.actors.reward_functions.gym_reward_functions) anneal_parameters() (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] apply_gradients() (pytorchrl.agent.algorithms.base.Algorithm method) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS method), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG method), [1] (pytorchrl.agent.algorithms.off_policy.ddqn.DDQN method), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO method), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 method), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C method), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO method), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO method), [1] (pytorchrl.scheme.gradients.g_worker.GWorker method) as_remote() (pytorchrl.scheme.base.worker.Worker class method) atari_test_env_factory() (in module pytorchrl.envs.atari.atari_env_factory) atari_train_env_factory() (in module pytorchrl.envs.atari.atari_env_factory) AttractionKL (class in pytorchrl.agent.algorithms.policy_loss_addons.kv_similarity) average_gradients() (in module pytorchrl.scheme.utils)

B

BasicObstacleEnv (class in pytorchrl.envs.obstacle_tower.wrappers) BasicObstacleEnvTest (class in pytorchrl.envs.obstacle_tower.wrappers) before_gradients() (pytorchrl.agent.storages.base.Storage method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.per_buffer.PERBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] (pytorchrl.agent.storages.on_policy.vtrace_buffer.VTraceBuffer method), [1]

box_is_placed() (in module pytorchrl.envs.obstacle_tower.utils) box_location() (in module pytorchrl.envs.obstacle_tower.utils) broadcast_interval (pytorchrl.scheme.gradients.g_worker.CollectorThread attribute) broadcast_message() (in module pytorchrl.scheme.utils) broadcast_new_weights() (pytorchrl.scheme.gradients.g_worker.CollectorThread method) bt() (in module pytorchrl.agent.algorithms.utils) btr() (in module pytorchrl.agent.algorithms.utils) burn_in_recurrent_states() (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor method), [1]

C

calculate_target_entropy() (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] cartpole() (in module pytorchrl.agent.actors.reward_functions.gym_reward_functions) (pytorchrl.agent.actors.reward_functions.gym_reward_functions method) CartPoleActionWrapper (class in pytorchrl.envs.common) Categorical (class in pytorchrl.agent.actors.distributions.categorical), [1] center_crop() (in module pytorchrl.envs.habitat.utils) check_demo_buffer_capacity() (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] check_dynamics_weights() (pytorchrl.agent.actors.world_models.world_model.WorldModel static method), [1] check_message() (in module pytorchrl.scheme.utils) cleanup_log_dir() (in module pytorchrl.utils) clear_mpi_env_vars() (in module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base) clip_grad_norm_() (in module pytorchrl.utils) ClipRewardEnv (class in pytorchrl.envs.atari.wrappers) close() (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvWrapper method) close_extras() (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env.SubprocVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase method) closed (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase attribute) CloudpickleWrapper (class in pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base) CNN (class in pytorchrl.agent.actors.feature_extractors.cnn) col_communication (pytorchrl.scheme.gradients.g_worker.GWorker attribute) col_fraction_workers (pytorchrl.scheme.updates.u_worker.UpdaterThread attribute) col_workers (pytorchrl.scheme.gradients.g_worker.GWorker attribute) collect_data() (pytorchrl.scheme.collection.c_worker.CWorker method) collect_train_data() (pytorchrl.scheme.collection.c_worker.CWorker method) collector (pytorchrl.scheme.gradients.g_worker.GWorker attribute) CollectorThread (class in pytorchrl.scheme.gradients.g_worker) compress_data_to_send (pytorchrl.scheme.collection.c_worker.CWorker attribute) compress_grads_to_send (pytorchrl.scheme.gradients.g_worker.GWorker attribute) compute_advantages() (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] compute_gradients() (pytorchrl.agent.algorithms.base.Algorithm method) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS method), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG method), [1] (pytorchrl.agent.algorithms.off_policy.ddqn.DDQN method), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO method), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 method), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C method), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO method), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO method), [1] (pytorchrl.scheme.gradients.g_worker.GWorker method) compute_loss() (pytorchrl.agent.algorithms.off_policy.ddqn.DDQN method), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C method), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO method), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO method), [1] compute_loss_alpha() (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] compute_loss_pi() (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG method), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO method), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 method), [1]

compute_loss_q() (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG method), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO method), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 method), [1] compute_loss_term() (pytorchrl.agent.algorithms.policy_loss_addons.base.PolicyLossAddOn method) (pytorchrl.agent.algorithms.policy_loss_addons.kv_similarity.AttractionKL method) (pytorchrl.agent.algorithms.policy_loss_addons.kv_similarity.RepulsionKL method) compute_returns() (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS method), [1] (pytorchrl.agent.storages.on_policy.gae_buffer.GAEBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] compute_vtrace() (pytorchrl.agent.storages.on_policy.vtrace_buffer.VTraceBuffer method), [1] copy_obs_dict() (in module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.util) copy_single_tensor() (pytorchrl.agent.storages.off_policy.her_buffer.HERBuffer method), [1] count() (pytorchrl.envs.atari.wrappers.LazyFrames method) create_critic() (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor method), [1] (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor method), [1] create_dynamics() (pytorchrl.agent.actors.world_models.world_model.WorldModel method), [1] create_factory() (pytorchrl.agent.actors.base.Actor class method) (pytorchrl.agent.actors.model_based_planner_actor.ModelBasedPlannerActor class method), [1] (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor class method), [1] (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor class method), [1] (pytorchrl.agent.algorithms.base.Algorithm class method) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM class method), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM class method), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS class method), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG class method), [1] (pytorchrl.agent.algorithms.off_policy.ddqn.DDQN class method), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO class method), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC class method), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 class method), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C class method), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO class method), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO class method), [1] (pytorchrl.agent.env.vec_env.VecEnv class method), [1] (pytorchrl.agent.storages.base.Storage class method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer class method), [1] (pytorchrl.agent.storages.off_policy.ere_buffer.EREBuffer class method), [1] (pytorchrl.agent.storages.off_policy.her_buffer.HERBuffer class method), [1] (pytorchrl.agent.storages.off_policy.nstep_buffer.NStepReplayBuffer class method), [1] (pytorchrl.agent.storages.off_policy.per_buffer.PERBuffer class method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer class method), [1] (pytorchrl.agent.storages.on_policy.gae_buffer.GAEBuffer class method), [1] (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer class method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer class method), [1] (pytorchrl.scheme.collection.c_worker_set.CWorkerSet class method) (pytorchrl.scheme.gradients.g_worker_set.GWorkerSet class method) create_policy() (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor method), [1] (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor method), [1] create_world_dynamics_model() (pytorchrl.agent.actors.model_based_planner_actor.ModelBasedPlannerActor method), [1] CWorker (class in pytorchrl.scheme.collection.c_worker) CWorkerSet (class in pytorchrl.scheme.collection.c_worker_set)

D

DataTransition (class in pytorchrl) DDPG (class in pytorchrl.agent.algorithms.off_policy.ddpg), [1] DDQN (class in pytorchrl.agent.algorithms.off_policy.ddqn), [1] decentralized_update_execution (pytorchrl.scheme.updates.u_worker.UpdaterThread attribute) default_feature_extractor() (in module pytorchrl.agent.actors.feature_extractors) DelayedReward (class in pytorchrl.envs.common) demos_data_fields (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer attribute), [1] Deterministic (class in pytorchrl.agent.actors.distributions.deterministic) DeterministicMB (class in pytorchrl.agent.actors.distributions.deterministic) device (pytorchrl.agent.env.vector_wrappers.VecPyTorch attribute) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer attribute), [1] (pytorchrl.scheme.collection.c_worker.CWorker attribute) DiagGaussian (class in pytorchrl.agent.actors.distributions.gaussian), [1]

DiagGaussianEnsemble (class in pytorchrl.agent.actors.distributions.gaussian) dict_to_obs() (in module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.util) DictNet (class in pytorchrl.agent.actors.feature_extractors.dictnet) dim0_reshape() (in module pytorchrl.agent.storages.model_based.mb_buffer) (in module pytorchrl.agent.storages.off_policy.ere_buffer) (in module pytorchrl.agent.storages.off_policy.nstep_buffer) (in module pytorchrl.agent.storages.off_policy.per_buffer) (in module pytorchrl.agent.storages.off_policy.replay_buffer) discrete_version (pytorchrl.agent.algorithms.off_policy.mpo.MPO property), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC property), [1] Done (pytorchrl.DataTransition property) done (pytorchrl.scheme.collection.c_worker.CWorker attribute) done() (pytorchrl.learner.Learner method), [1] DummyVecEnv (class in pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.dummy_vec_env)

E

EnsembleFC (class in pytorchrl.agent.actors.feature_extractors.ensemble_layer) EnvironmentInformation (pytorchrl.DataTransition property) envs_test (pytorchrl.scheme.collection.c_worker.CWorker attribute) envs_train (pytorchrl.scheme.collection.c_worker.CWorker attribute) EpisodicLifeEnv (class in pytorchrl.envs.atari.wrappers) EREBuffer (class in pytorchrl.agent.storages.off_policy.ere_buffer), [1] evaluate() (pytorchrl.scheme.collection.c_worker.CWorker method)

evaluate_actions() (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor method), [1] (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor method), [1] evaluate_pred() (pytorchrl.agent.actors.distributions.categorical.Categorical method), [1] (pytorchrl.agent.actors.distributions.deterministic.Deterministic method) (pytorchrl.agent.actors.distributions.gaussian.DiagGaussian method), [1] (pytorchrl.agent.actors.distributions.squashed_gaussian.SquashedGaussian method), [1] EXT (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor attribute) extra_repr() (pytorchrl.agent.actors.feature_extractors.ensemble_layer.EnsembleFC method)

F

f (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor attribute) find_free_port() (in module pytorchrl.scheme.base.utils) (pytorchrl.scheme.base.worker.Worker method) FireResetEnv (class in pytorchrl.envs.atari.wrappers) fit() (pytorchrl.agent.actors.world_models.utils.StandardScaler method) FixupCNN (class in pytorchrl.agent.actors.feature_extractors.fixup_cnn) FixupResidualModule (class in pytorchrl.agent.actors.feature_extractors.fixup_cnn) forward() (pytorchrl.agent.actors.distributions.categorical.Categorical method), [1] (pytorchrl.agent.actors.distributions.deterministic.Deterministic method) (pytorchrl.agent.actors.distributions.deterministic.DeterministicMB method) (pytorchrl.agent.actors.distributions.gaussian.DiagGaussian method), [1] (pytorchrl.agent.actors.distributions.gaussian.DiagGaussianEnsemble method) (pytorchrl.agent.actors.distributions.squashed_gaussian.SquashedGaussian method), [1] (pytorchrl.agent.actors.feature_extractors.cnn.CNN method) (pytorchrl.agent.actors.feature_extractors.dictnet.DictNet method) (pytorchrl.agent.actors.feature_extractors.ensemble_layer.EnsembleFC method) (pytorchrl.agent.actors.feature_extractors.fixup_cnn.FixupCNN method) (pytorchrl.agent.actors.feature_extractors.fixup_cnn.FixupResidualModule method) (pytorchrl.agent.actors.feature_extractors.mlp.MLP method) (pytorchrl.agent.actors.memory_networks.gru_net.GruNet method) (pytorchrl.agent.actors.utils.Scale method) (pytorchrl.agent.actors.utils.Unscale method)

fraction_samples (pytorchrl.scheme.collection.c_worker.CWorker attribute) frame() (pytorchrl.envs.atari.wrappers.LazyFrames method) FrameSkip (class in pytorchrl.envs.common) FrameStack (class in pytorchrl.envs.common)

G

GAEBuffer (class in pytorchrl.agent.storages.on_policy.gae_buffer), [1] gamma (pytorchrl.agent.algorithms.base.Algorithm property) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS property), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG property), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO property), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC property), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 property), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C property), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO property), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO property), [1] gaussian_kl() (in module pytorchrl.agent.algorithms.utils) generate_batches() (pytorchrl.agent.storages.base.Storage method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.ere_buffer.EREBuffer method), [1] (pytorchrl.agent.storages.off_policy.nstep_buffer.NStepReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.per_buffer.PERBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] get_action() (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor method), [1] (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor method), [1] get_agent_components() (pytorchrl.scheme.scheme.Scheme method), [1] get_all_buffer_data() (pytorchrl.agent.storages.base.Storage method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] get_data() (pytorchrl.scheme.gradients.g_worker.GWorker method) get_data_slice() (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] get_dist() (in module pytorchrl.agent.actors.distributions) get_episode_lengths() (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor method) get_episode_rewards() (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor method) get_episode_times() (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor method) get_feature_extractor() (in module pytorchrl.agent.actors.feature_extractors)

get_gain() (in module pytorchrl.agent.actors.feature_extractors.utils) get_gradients() (in module pytorchrl.agent.algorithms.utils) get_grads() (pytorchrl.scheme.gradients.g_worker.GWorker method) get_host() (pytorchrl.scheme.base.worker.Worker static method) get_images() (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.dummy_vec_env.DummyVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env.SubprocVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvWrapper method) get_initial_recurrent_state() (pytorchrl.agent.actors.memory_networks.gru_net.GruNet method) get_memory_network() (in module pytorchrl.agent.actors.memory_networks) get_metrics() (pytorchrl.learner.Learner method), [1] get_monitor_files() (in module pytorchrl.agent.env.openai_baselines_dependencies.Monitor) get_node_ip() (pytorchrl.scheme.base.worker.Worker method) get_noise() (in module pytorchrl.agent.actors.noise) get_num_channels_obs() (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] get_pred_trajectories() (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM method), [1] get_prediction() (pytorchrl.agent.actors.model_based_planner_actor.ModelBasedPlannerActor method), [1] get_priority() (pytorchrl.agent.storages.off_policy.per_buffer.PERBuffer method), [1] get_q_scores() (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor method), [1] get_reward_function() (in module pytorchrl.agent.actors.reward_functions) get_sequence_priority() (pytorchrl.agent.storages.off_policy.per_buffer.PERBuffer method), [1] get_total_steps() (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor method) get_updated_action_log_probs() (pytorchrl.agent.storages.on_policy.vtrace_buffer.VTraceBuffer method), [1] get_value() (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor method), [1] get_value_specific_net() (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor method), [1] get_viewer() (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase method) get_weights() (pytorchrl.scheme.base.worker.Worker method) grad_communication (pytorchrl.scheme.updates.u_worker.UpdaterThread attribute) (pytorchrl.scheme.updates.u_worker.UWorker attribute) grad_execution (pytorchrl.scheme.updates.u_worker.UpdaterThread attribute) (pytorchrl.scheme.updates.u_worker.UWorker attribute) grad_workers (pytorchrl.scheme.updates.u_worker.UWorker attribute) GruNet (class in pytorchrl.agent.actors.memory_networks.gru_net) GWorker (class in pytorchrl.scheme.gradients.g_worker) GWorkerSet (class in pytorchrl.scheme.gradients.g_worker_set)

H

halfcheetah_bullet() (in module pytorchrl.agent.actors.reward_functions.pybullet_reward_functions) (pytorchrl.agent.actors.reward_functions.pybullet_reward_functions method) halfcheetah_mujoco() (in module pytorchrl.agent.actors.reward_functions.gym_reward_functions) (pytorchrl.agent.actors.reward_functions.gym_reward_functions method)

handle_end_of_episode() (pytorchrl.agent.storages.off_policy.her_buffer.HERBuffer method), [1] HERBuffer (class in pytorchrl.agent.storages.off_policy.her_buffer), [1] high (pytorchrl.agent.actors.utils.Scale attribute) (pytorchrl.agent.actors.utils.Unscale attribute)

I

imdownscale() (in module pytorchrl.envs.atari.utils) index_worker (pytorchrl.scheme.base.worker.Worker attribute) (pytorchrl.scheme.collection.c_worker.CWorker attribute) (pytorchrl.scheme.gradients.g_worker.CollectorThread attribute) (pytorchrl.scheme.gradients.g_worker.GWorker attribute) init() (in module pytorchrl.agent.actors.utils) init_tensors() (pytorchrl.agent.storages.base.Storage method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] inqueue (pytorchrl.scheme.gradients.g_worker.GWorker attribute) insert_data_slice() (pytorchrl.agent.storages.base.Storage method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] insert_single_tensor_slice() (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1]

insert_transition() (pytorchrl.agent.storages.base.Storage method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.her_buffer.HERBuffer method), [1] (pytorchrl.agent.storages.off_policy.nstep_buffer.NStepReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.per_buffer.PERBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] inverse_transform() (pytorchrl.agent.actors.world_models.utils.StandardScaler method) inverted_pendulum_mujoco() (in module pytorchrl.agent.actors.reward_functions.gym_reward_functions) (pytorchrl.agent.actors.reward_functions.gym_reward_functions method) is_recurrent (pytorchrl.agent.actors.base.Actor property) (pytorchrl.agent.actors.model_based_planner_actor.ModelBasedPlannerActor property), [1] (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor property), [1] (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor property), [1] iter (pytorchrl.scheme.collection.c_worker.CWorker attribute) (pytorchrl.scheme.gradients.g_worker.GWorker attribute)

L

LazyFrames (class in pytorchrl.envs.atari.wrappers) Learner (class in pytorchrl.learner), [1] load_baselines_results() (in module pytorchrl.agent.env.openai_baselines_dependencies.load_baselines_results) load_demo() (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] load_initial_demos() (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] load_results() (in module pytorchrl.agent.env.openai_baselines_dependencies.Monitor) load_supplementary_demos() (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] LoadFromFile (class in pytorchrl.utils)

LoadMonitorResultsError local_worker (pytorchrl.scheme.gradients.g_worker.CollectorThread attribute) (pytorchrl.scheme.gradients.g_worker.GWorker attribute) (pytorchrl.scheme.updates.u_worker.UpdaterThread attribute) (pytorchrl.scheme.updates.u_worker.UWorker attribute) local_worker() (pytorchrl.scheme.base.worker_set.WorkerSet method) low (pytorchrl.agent.actors.utils.Scale attribute) (pytorchrl.agent.actors.utils.Unscale attribute)

M

make_atari() (in module pytorchrl.envs.atari.wrappers) make_env() (in module pytorchrl.agent.env.make_env) MaxAndSkipEnv (class in pytorchrl.envs.atari.wrappers) MBReplayBuffer (class in pytorchrl.agent.storages.model_based.mb_buffer), [1] metadata (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase attribute) mini_batch_size (pytorchrl.agent.algorithms.base.Algorithm property) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS property), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG property), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO property), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC property), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 property), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C property), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO property), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO property), [1] MLP (class in pytorchrl.agent.actors.feature_extractors.mlp) ModelBasedPlannerActor (class in pytorchrl.agent.actors.model_based_planner_actor), [1] module pytorchrl pytorchrl.agent pytorchrl.agent.actors pytorchrl.agent.actors.base pytorchrl.agent.actors.distributions pytorchrl.agent.actors.distributions.categorical pytorchrl.agent.actors.distributions.deterministic pytorchrl.agent.actors.distributions.gaussian pytorchrl.agent.actors.distributions.squashed_gaussian pytorchrl.agent.actors.feature_extractors pytorchrl.agent.actors.feature_extractors.cnn pytorchrl.agent.actors.feature_extractors.dictnet pytorchrl.agent.actors.feature_extractors.ensemble_layer pytorchrl.agent.actors.feature_extractors.fixup_cnn pytorchrl.agent.actors.feature_extractors.mlp pytorchrl.agent.actors.feature_extractors.utils pytorchrl.agent.actors.memory_networks pytorchrl.agent.actors.memory_networks.gru_net pytorchrl.agent.actors.model_based_planner_actor pytorchrl.agent.actors.noise pytorchrl.agent.actors.noise.gaussian pytorchrl.agent.actors.noise.nonoise pytorchrl.agent.actors.noise.ou pytorchrl.agent.actors.off_policy_actor pytorchrl.agent.actors.on_policy_actor pytorchrl.agent.actors.reward_functions pytorchrl.agent.actors.reward_functions.gym_reward_functions pytorchrl.agent.actors.reward_functions.pybullet_reward_functions pytorchrl.agent.actors.utils pytorchrl.agent.actors.world_models pytorchrl.agent.actors.world_models.utils pytorchrl.agent.actors.world_models.world_model pytorchrl.agent.algorithms pytorchrl.agent.algorithms.base pytorchrl.agent.algorithms.model_based pytorchrl.agent.algorithms.model_based.mpc_cem pytorchrl.agent.algorithms.model_based.mpc_pddm pytorchrl.agent.algorithms.model_based.mpc_rs pytorchrl.agent.algorithms.off_policy pytorchrl.agent.algorithms.off_policy.ddpg pytorchrl.agent.algorithms.off_policy.ddqn pytorchrl.agent.algorithms.off_policy.mpo pytorchrl.agent.algorithms.off_policy.sac pytorchrl.agent.algorithms.off_policy.td3 pytorchrl.agent.algorithms.on_policy pytorchrl.agent.algorithms.on_policy.a2c pytorchrl.agent.algorithms.on_policy.ppo pytorchrl.agent.algorithms.on_policy.rnd_ppo pytorchrl.agent.algorithms.policy_loss_addons pytorchrl.agent.algorithms.policy_loss_addons.base pytorchrl.agent.algorithms.policy_loss_addons.kv_similarity pytorchrl.agent.algorithms.utils pytorchrl.agent.env pytorchrl.agent.env.env_wrappers pytorchrl.agent.env.make_env pytorchrl.agent.env.openai_baselines_dependencies pytorchrl.agent.env.openai_baselines_dependencies.load_baselines_results pytorchrl.agent.env.openai_baselines_dependencies.Monitor pytorchrl.agent.env.openai_baselines_dependencies.vec_envs pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.dummy_vec_env pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.util pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base pytorchrl.agent.env.vec_env pytorchrl.agent.env.vector_wrappers pytorchrl.agent.storages pytorchrl.agent.storages.base pytorchrl.agent.storages.model_based pytorchrl.agent.storages.model_based.mb_buffer pytorchrl.agent.storages.off_policy pytorchrl.agent.storages.off_policy.ere_buffer pytorchrl.agent.storages.off_policy.her_buffer pytorchrl.agent.storages.off_policy.nstep_buffer pytorchrl.agent.storages.off_policy.per_buffer pytorchrl.agent.storages.off_policy.replay_buffer pytorchrl.agent.storages.on_policy pytorchrl.agent.storages.on_policy.gae_buffer pytorchrl.agent.storages.on_policy.ppod_buffer pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer pytorchrl.agent.storages.on_policy.vtrace_buffer pytorchrl.envs pytorchrl.envs.animal_olympics pytorchrl.envs.atari pytorchrl.envs.atari.atari_env_factory pytorchrl.envs.atari.utils pytorchrl.envs.atari.wrappers pytorchrl.envs.common pytorchrl.envs.habitat pytorchrl.envs.habitat.utils pytorchrl.envs.mujoco pytorchrl.envs.mujoco.mujoco_env_factory pytorchrl.envs.obstacle_tower pytorchrl.envs.obstacle_tower.utils pytorchrl.envs.obstacle_tower.wrappers pytorchrl.learner pytorchrl.scheme pytorchrl.scheme.base pytorchrl.scheme.base.utils pytorchrl.scheme.base.worker pytorchrl.scheme.base.worker_set pytorchrl.scheme.collection pytorchrl.scheme.collection.c_worker pytorchrl.scheme.collection.c_worker_set pytorchrl.scheme.gradients pytorchrl.scheme.gradients.g_worker pytorchrl.scheme.gradients.g_worker_set pytorchrl.scheme.scheme pytorchrl.scheme.updates pytorchrl.scheme.updates.u_worker pytorchrl.scheme.utils pytorchrl.utils

Monitor (class in pytorchrl.agent.env.openai_baselines_dependencies.Monitor) MontezumaEmbeddingsEnv (class in pytorchrl.envs.atari.wrappers) MontezumaVisitedRoomEnv (class in pytorchrl.envs.atari.wrappers) MPC_CEM (class in pytorchrl.agent.algorithms.model_based.mpc_cem), [1] MPC_PDDM (class in pytorchrl.agent.algorithms.model_based.mpc_pddm), [1] MPC_RS (class in pytorchrl.agent.algorithms.model_based.mpc_rs), [1] MPO (class in pytorchrl.agent.algorithms.off_policy.mpo), [1] mujoco_test_env_factory() (in module pytorchrl.envs.mujoco.mujoco_env_factory) mujoco_train_env_factory() (in module pytorchrl.envs.mujoco.mujoco_env_factory)

N

NextDone (pytorchrl.DataTransition property) NextObservation (pytorchrl.DataTransition property) NextRecurrentHiddenStates (pytorchrl.DataTransition property) NoNoise (class in pytorchrl.agent.actors.noise.nonoise) NoopResetEnv (class in pytorchrl.envs.atari.wrappers) Normal (class in pytorchrl.agent.actors.noise.gaussian), [1] normalize_int_rewards() (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] NStepReplayBuffer (class in pytorchrl.agent.storages.off_policy.nstep_buffer), [1] num_envs (pytorchrl.agent.env.vector_wrappers.VecPyTorch attribute) num_epochs (pytorchrl.agent.algorithms.base.Algorithm property) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS property), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG property), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO property), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC property), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 property), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C property), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO property), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO property), [1] num_mini_batch (pytorchrl.agent.algorithms.base.Algorithm property) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS property), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG property), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO property), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC property), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 property), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C property), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO property), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO property), [1]

num_outputs (pytorchrl.agent.actors.memory_networks.gru_net.GruNet property) num_sent_since_broadcast (pytorchrl.scheme.gradients.g_worker.CollectorThread attribute) num_test_episodes (pytorchrl.agent.algorithms.base.Algorithm property) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS property), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG property), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO property), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC property), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 property), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C property), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO property), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO property), [1] num_workers (pytorchrl.scheme.base.worker_set.WorkerSet attribute) (pytorchrl.scheme.collection.c_worker_set.CWorkerSet attribute) (pytorchrl.scheme.gradients.g_worker.CollectorThread attribute) (pytorchrl.scheme.gradients.g_worker_set.GWorkerSet attribute) (pytorchrl.scheme.updates.u_worker.UpdaterThread attribute) (pytorchrl.scheme.updates.u_worker.UWorker attribute)

O

obs (pytorchrl.scheme.collection.c_worker.CWorker attribute) obs_space_info() (in module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.util) obs_to_dict() (in module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.util) Observation (pytorchrl.DataTransition property) observation() (pytorchrl.agent.env.env_wrappers.TransposeImagesIfRequired method) (pytorchrl.envs.atari.wrappers.ScaledFloatFrame method) (pytorchrl.envs.atari.wrappers.WarpFrame method)

OffPolicyActor (class in pytorchrl.agent.actors.off_policy_actor), [1] on_policy_data_fields (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer attribute), [1] OnPolicyActor (class in pytorchrl.agent.actors.on_policy_actor), [1] OUNoise (class in pytorchrl.agent.actors.noise.ou), [1] outqueue (pytorchrl.scheme.updates.u_worker.UpdaterThread attribute)

P

pack() (in module pytorchrl.scheme.utils) partially_load_checkpoint() (in module pytorchrl.agent.actors.utils) pendulum() (in module pytorchrl.agent.actors.reward_functions.gym_reward_functions) (pytorchrl.agent.actors.reward_functions.gym_reward_functions method) PERBuffer (class in pytorchrl.agent.storages.off_policy.per_buffer), [1] PitfallEmbeddingsEnv (class in pytorchrl.envs.atari.wrappers) place_location() (in module pytorchrl.envs.obstacle_tower.utils) PolicyLossAddOn (class in pytorchrl.agent.algorithms.policy_loss_addons.base) PPO (class in pytorchrl.agent.algorithms.on_policy.ppo), [1] PPODBuffer (class in pytorchrl.agent.storages.on_policy.ppod_buffer), [1] predict_given_reward() (pytorchrl.agent.actors.world_models.world_model.WorldModel method), [1] predict_learned_reward() (pytorchrl.agent.actors.world_models.world_model.WorldModel method), [1] print_info() (pytorchrl.learner.Learner method), [1] print_worker_info() (pytorchrl.scheme.base.worker.Worker method) process() (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvObservationWrapper method) pytorchrl module pytorchrl.agent module pytorchrl.agent.actors module pytorchrl.agent.actors.base module pytorchrl.agent.actors.distributions module pytorchrl.agent.actors.distributions.categorical module pytorchrl.agent.actors.distributions.deterministic module pytorchrl.agent.actors.distributions.gaussian module pytorchrl.agent.actors.distributions.squashed_gaussian module pytorchrl.agent.actors.feature_extractors module pytorchrl.agent.actors.feature_extractors.cnn module pytorchrl.agent.actors.feature_extractors.dictnet module pytorchrl.agent.actors.feature_extractors.ensemble_layer module pytorchrl.agent.actors.feature_extractors.fixup_cnn module pytorchrl.agent.actors.feature_extractors.mlp module pytorchrl.agent.actors.feature_extractors.utils module pytorchrl.agent.actors.memory_networks module pytorchrl.agent.actors.memory_networks.gru_net module pytorchrl.agent.actors.model_based_planner_actor module pytorchrl.agent.actors.noise module pytorchrl.agent.actors.noise.gaussian module pytorchrl.agent.actors.noise.nonoise module pytorchrl.agent.actors.noise.ou module pytorchrl.agent.actors.off_policy_actor module pytorchrl.agent.actors.on_policy_actor module pytorchrl.agent.actors.reward_functions module pytorchrl.agent.actors.reward_functions.gym_reward_functions module pytorchrl.agent.actors.reward_functions.pybullet_reward_functions module pytorchrl.agent.actors.utils module pytorchrl.agent.actors.world_models module pytorchrl.agent.actors.world_models.utils module pytorchrl.agent.actors.world_models.world_model module pytorchrl.agent.algorithms module pytorchrl.agent.algorithms.base module pytorchrl.agent.algorithms.model_based module pytorchrl.agent.algorithms.model_based.mpc_cem module pytorchrl.agent.algorithms.model_based.mpc_pddm module pytorchrl.agent.algorithms.model_based.mpc_rs module pytorchrl.agent.algorithms.off_policy module pytorchrl.agent.algorithms.off_policy.ddpg module pytorchrl.agent.algorithms.off_policy.ddqn module pytorchrl.agent.algorithms.off_policy.mpo module pytorchrl.agent.algorithms.off_policy.sac module pytorchrl.agent.algorithms.off_policy.td3 module pytorchrl.agent.algorithms.on_policy module pytorchrl.agent.algorithms.on_policy.a2c module pytorchrl.agent.algorithms.on_policy.ppo module pytorchrl.agent.algorithms.on_policy.rnd_ppo module pytorchrl.agent.algorithms.policy_loss_addons module pytorchrl.agent.algorithms.policy_loss_addons.base module pytorchrl.agent.algorithms.policy_loss_addons.kv_similarity module pytorchrl.agent.algorithms.utils module

pytorchrl.agent.env module pytorchrl.agent.env.env_wrappers module pytorchrl.agent.env.make_env module pytorchrl.agent.env.openai_baselines_dependencies module pytorchrl.agent.env.openai_baselines_dependencies.load_baselines_results module pytorchrl.agent.env.openai_baselines_dependencies.Monitor module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.dummy_vec_env module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.util module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base module pytorchrl.agent.env.vec_env module pytorchrl.agent.env.vector_wrappers module pytorchrl.agent.storages module pytorchrl.agent.storages.base module pytorchrl.agent.storages.model_based module pytorchrl.agent.storages.model_based.mb_buffer module pytorchrl.agent.storages.off_policy module pytorchrl.agent.storages.off_policy.ere_buffer module pytorchrl.agent.storages.off_policy.her_buffer module pytorchrl.agent.storages.off_policy.nstep_buffer module pytorchrl.agent.storages.off_policy.per_buffer module pytorchrl.agent.storages.off_policy.replay_buffer module pytorchrl.agent.storages.on_policy module pytorchrl.agent.storages.on_policy.gae_buffer module pytorchrl.agent.storages.on_policy.ppod_buffer module pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer module pytorchrl.agent.storages.on_policy.vtrace_buffer module pytorchrl.envs module pytorchrl.envs.animal_olympics module pytorchrl.envs.atari module pytorchrl.envs.atari.atari_env_factory module pytorchrl.envs.atari.utils module pytorchrl.envs.atari.wrappers module pytorchrl.envs.common module pytorchrl.envs.habitat module pytorchrl.envs.habitat.utils module pytorchrl.envs.mujoco module pytorchrl.envs.mujoco.mujoco_env_factory module pytorchrl.envs.obstacle_tower module pytorchrl.envs.obstacle_tower.utils module pytorchrl.envs.obstacle_tower.wrappers module pytorchrl.learner module pytorchrl.scheme module pytorchrl.scheme.base module pytorchrl.scheme.base.utils module pytorchrl.scheme.base.worker module pytorchrl.scheme.base.worker_set module pytorchrl.scheme.collection module pytorchrl.scheme.collection.c_worker module pytorchrl.scheme.collection.c_worker_set module pytorchrl.scheme.gradients module pytorchrl.scheme.gradients.g_worker module pytorchrl.scheme.gradients.g_worker_set module pytorchrl.scheme.scheme module pytorchrl.scheme.updates module pytorchrl.scheme.updates.u_worker module pytorchrl.scheme.utils module pytorchrl.utils module

Q

queue (pytorchrl.scheme.gradients.g_worker.CollectorThread attribute)

R

ray_get_and_free() (in module pytorchrl.scheme.utils) recurrent_hidden_state_size (pytorchrl.agent.actors.base.Actor property) (pytorchrl.agent.actors.memory_networks.gru_net.GruNet property) (pytorchrl.agent.actors.model_based_planner_actor.ModelBasedPlannerActor property), [1] (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor property), [1] (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor property), [1] RecurrentHiddenStates (pytorchrl.DataTransition property) ReducedActionEnv (class in pytorchrl.envs.obstacle_tower.wrappers) reinitialize_dynamics_model() (pytorchrl.agent.actors.world_models.world_model.WorldModel method), [1] remote_config (pytorchrl.scheme.base.worker_set.WorkerSet attribute) (pytorchrl.scheme.collection.c_worker_set.CWorkerSet attribute) (pytorchrl.scheme.gradients.g_worker_set.GWorkerSet attribute) remote_workers (pytorchrl.scheme.gradients.g_worker.CollectorThread attribute) (pytorchrl.scheme.gradients.g_worker.GWorker attribute) (pytorchrl.scheme.updates.u_worker.UpdaterThread attribute) (pytorchrl.scheme.updates.u_worker.UWorker attribute) remote_workers() (pytorchrl.scheme.base.worker_set.WorkerSet method) render() (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.dummy_vec_env.DummyVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvWrapper method) replace_agent_component() (pytorchrl.scheme.collection.c_worker.CWorker method) ReplayBuffer (class in pytorchrl.agent.storages.off_policy.replay_buffer), [1] RepulsionKL (class in pytorchrl.agent.algorithms.policy_loss_addons.kv_similarity) reset() (pytorchrl.agent.actors.noise.gaussian.Normal method), [1] (pytorchrl.agent.actors.noise.nonoise.NoNoise method) (pytorchrl.agent.actors.noise.ou.OUNoise method), [1] (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.dummy_vec_env.DummyVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env.SubprocVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvObservationWrapper method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvWrapper method) (pytorchrl.agent.env.vector_wrappers.VecPyTorch method) (pytorchrl.agent.storages.base.Storage method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] (pytorchrl.envs.atari.wrappers.ClipRewardEnv method) (pytorchrl.envs.atari.wrappers.EpisodicLifeEnv method) (pytorchrl.envs.atari.wrappers.FireResetEnv method) (pytorchrl.envs.atari.wrappers.MaxAndSkipEnv method) (pytorchrl.envs.atari.wrappers.MontezumaEmbeddingsEnv method) (pytorchrl.envs.atari.wrappers.MontezumaVisitedRoomEnv method) (pytorchrl.envs.atari.wrappers.NoopResetEnv method) (pytorchrl.envs.atari.wrappers.PitfallEmbeddingsEnv method) (pytorchrl.envs.atari.wrappers.ScaleRewardEnv method) (pytorchrl.envs.atari.wrappers.StickyActionEnv method) (pytorchrl.envs.atari.wrappers.TimeLimit method) (pytorchrl.envs.common.DelayedReward method) (pytorchrl.envs.common.FrameSkip method) (pytorchrl.envs.common.FrameStack method) (pytorchrl.envs.common.SparseReward method) (pytorchrl.envs.obstacle_tower.wrappers.BasicObstacleEnv method) (pytorchrl.envs.obstacle_tower.wrappers.BasicObstacleEnvTest method) (pytorchrl.envs.obstacle_tower.wrappers.RewardShapeObstacleEnv method)

reset_parameters() (pytorchrl.agent.actors.feature_extractors.ensemble_layer.EnsembleFC method) reset_single_env() (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.dummy_vec_env.DummyVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env.SubprocVecEnv method) (pytorchrl.agent.env.vector_wrappers.VecPyTorch method) reset_state() (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor method) ResultsWriter (class in pytorchrl.agent.env.openai_baselines_dependencies.Monitor) Reward (pytorchrl.DataTransition property) RewardShapeObstacleEnv (class in pytorchrl.envs.obstacle_tower.wrappers) rhs (pytorchrl.scheme.collection.c_worker.CWorker attribute) RND_PPO (class in pytorchrl.agent.algorithms.on_policy.rnd_ppo), [1] run() (pytorchrl.scheme.gradients.g_worker.CollectorThread method) (pytorchrl.scheme.updates.u_worker.UpdaterThread method) RunningMeanStd (class in pytorchrl.utils)

S

SAC (class in pytorchrl.agent.algorithms.off_policy.sac), [1] sample() (pytorchrl.agent.actors.noise.gaussian.Normal method), [1] (pytorchrl.agent.actors.noise.nonoise.NoNoise method) (pytorchrl.agent.actors.noise.ou.OUNoise method), [1] sample_actions() (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM method), [1] sample_demo() (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] save_argparse() (in module pytorchrl.utils) save_demos() (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] save_model() (pytorchrl.learner.Learner method), [1] (pytorchrl.scheme.gradients.g_worker.GWorker method) (pytorchrl.scheme.updates.u_worker.UWorker method) Scale (class in pytorchrl.agent.actors.utils) scale_image() (in module pytorchrl.envs.habitat.utils) ScaledFloatFrame (class in pytorchrl.envs.atari.wrappers) ScaleRewardEnv (class in pytorchrl.envs.atari.wrappers) Scheme (class in pytorchrl.scheme.scheme), [1] select_k_best() (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM method), [1] set_gradients() (in module pytorchrl.agent.algorithms.utils) set_weights() (pytorchrl.agent.algorithms.base.Algorithm method) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS method), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG method), [1] (pytorchrl.agent.algorithms.off_policy.ddqn.DDQN method), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO method), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 method), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C method), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO method), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO method), [1] (pytorchrl.scheme.collection.c_worker.CWorker method) (pytorchrl.scheme.gradients.g_worker.GWorker method) setup() (pytorchrl.agent.algorithms.policy_loss_addons.base.PolicyLossAddOn method) (pytorchrl.agent.algorithms.policy_loss_addons.kv_similarity.AttractionKL method) (pytorchrl.agent.algorithms.policy_loss_addons.kv_similarity.RepulsionKL method) setup_torch_data_parallel() (pytorchrl.scheme.base.worker.Worker method) should_broadcast() (pytorchrl.scheme.gradients.g_worker.CollectorThread method) size (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer attribute), [1] SparseReward (class in pytorchrl.envs.common) SquashedGaussian (class in pytorchrl.agent.actors.distributions.squashed_gaussian), [1] StandardScaler (class in pytorchrl.agent.actors.world_models.utils) start_steps (pytorchrl.agent.algorithms.base.Algorithm property) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS property), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG property), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO property), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC property), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 property), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C property), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO property), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO property), [1] step() (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase method) (pytorchrl.envs.atari.wrappers.ClipRewardEnv method) (pytorchrl.envs.atari.wrappers.EpisodicLifeEnv method) (pytorchrl.envs.atari.wrappers.FireResetEnv method) (pytorchrl.envs.atari.wrappers.MaxAndSkipEnv method) (pytorchrl.envs.atari.wrappers.MontezumaEmbeddingsEnv method) (pytorchrl.envs.atari.wrappers.MontezumaVisitedRoomEnv method) (pytorchrl.envs.atari.wrappers.NoopResetEnv method) (pytorchrl.envs.atari.wrappers.PitfallEmbeddingsEnv method) (pytorchrl.envs.atari.wrappers.ScaleRewardEnv method) (pytorchrl.envs.atari.wrappers.StickyActionEnv method) (pytorchrl.envs.atari.wrappers.TimeLimit method) (pytorchrl.envs.common.CartPoleActionWrapper method) (pytorchrl.envs.common.DelayedReward method) (pytorchrl.envs.common.FrameSkip method) (pytorchrl.envs.common.FrameStack method) (pytorchrl.envs.common.SparseReward method) (pytorchrl.envs.obstacle_tower.wrappers.BasicObstacleEnv method) (pytorchrl.envs.obstacle_tower.wrappers.BasicObstacleEnvTest method) (pytorchrl.envs.obstacle_tower.wrappers.RewardShapeObstacleEnv method) (pytorchrl.learner.Learner method), [1] (pytorchrl.scheme.gradients.g_worker.CollectorThread method) (pytorchrl.scheme.gradients.g_worker.GWorker method) (pytorchrl.scheme.updates.u_worker.UpdaterThread method) (pytorchrl.scheme.updates.u_worker.UWorker method)

step_async() (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.dummy_vec_env.DummyVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env.SubprocVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvWrapper method) (pytorchrl.agent.env.vector_wrappers.VecPyTorch method) step_wait() (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.dummy_vec_env.DummyVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env.SubprocVecEnv method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvObservationWrapper method) (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvWrapper method) (pytorchrl.agent.env.vector_wrappers.VecPyTorch method) StickyActionEnv (class in pytorchrl.envs.atari.wrappers) stop() (pytorchrl.learner.Learner method), [1] (pytorchrl.scheme.base.worker_set.WorkerSet method) (pytorchrl.scheme.collection.c_worker.CWorker method) (pytorchrl.scheme.gradients.g_worker.GWorker method) (pytorchrl.scheme.updates.u_worker.UWorker method) stopped (pytorchrl.scheme.gradients.g_worker.CollectorThread attribute) (pytorchrl.scheme.updates.u_worker.UpdaterThread attribute) Storage (class in pytorchrl.agent.storages.base) storage (pytorchrl.scheme.collection.c_worker.CWorker attribute) (pytorchrl.scheme.gradients.g_worker.GWorker attribute) storage_tensors (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer attribute), [1] (pytorchrl.agent.storages.off_policy.ere_buffer.EREBuffer attribute), [1] (pytorchrl.agent.storages.off_policy.her_buffer.HERBuffer attribute), [1] (pytorchrl.agent.storages.off_policy.nstep_buffer.NStepReplayBuffer attribute), [1] (pytorchrl.agent.storages.off_policy.per_buffer.PERBuffer attribute), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer attribute), [1] (pytorchrl.agent.storages.on_policy.gae_buffer.GAEBuffer attribute), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer attribute), [1] (pytorchrl.agent.storages.on_policy.vtrace_buffer.VTraceBuffer attribute), [1] SubprocVecEnv (class in pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env) sync_weights() (pytorchrl.scheme.updates.u_worker.UpdaterThread method)

T

TD3 (class in pytorchrl.agent.algorithms.off_policy.td3), [1] terminate_worker() (pytorchrl.scheme.base.worker.Worker method) test_every (pytorchrl.agent.algorithms.base.Algorithm property) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS property), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG property), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO property), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC property), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 property), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C property), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO property), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO property), [1] tile_images() (in module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.util) TimeLimit (class in pytorchrl.envs.atari.wrappers) track_potential_demos() (pytorchrl.agent.storages.on_policy.ppod_buffer.PPODBuffer method), [1] training (pytorchrl.agent.actors.base.Actor attribute) (pytorchrl.agent.actors.distributions.categorical.Categorical attribute), [1] (pytorchrl.agent.actors.distributions.deterministic.Deterministic attribute) (pytorchrl.agent.actors.distributions.deterministic.DeterministicMB attribute) (pytorchrl.agent.actors.distributions.gaussian.DiagGaussian attribute), [1] (pytorchrl.agent.actors.distributions.gaussian.DiagGaussianEnsemble attribute) (pytorchrl.agent.actors.distributions.squashed_gaussian.SquashedGaussian attribute), [1] (pytorchrl.agent.actors.feature_extractors.cnn.CNN attribute) (pytorchrl.agent.actors.feature_extractors.dictnet.DictNet attribute) (pytorchrl.agent.actors.feature_extractors.ensemble_layer.EnsembleFC attribute) (pytorchrl.agent.actors.feature_extractors.fixup_cnn.FixupCNN attribute) (pytorchrl.agent.actors.feature_extractors.fixup_cnn.FixupResidualModule attribute) (pytorchrl.agent.actors.feature_extractors.mlp.MLP attribute) (pytorchrl.agent.actors.memory_networks.gru_net.GruNet attribute) (pytorchrl.agent.actors.model_based_planner_actor.ModelBasedPlannerActor attribute), [1] (pytorchrl.agent.actors.off_policy_actor.OffPolicyActor attribute), [1] (pytorchrl.agent.actors.on_policy_actor.OnPolicyActor attribute), [1] (pytorchrl.agent.actors.utils.Scale attribute) (pytorchrl.agent.actors.utils.Unscale attribute) (pytorchrl.agent.actors.world_models.world_model.WorldModel attribute), [1]

training_step() (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS method), [1] transform() (pytorchrl.agent.actors.world_models.utils.StandardScaler method) TransposeImagesIfRequired (class in pytorchrl.agent.env.env_wrappers) try_load_from_checkpoint() (pytorchrl.agent.actors.base.Actor method)

U

unpack() (in module pytorchrl.scheme.utils) Unscale (class in pytorchrl.agent.actors.utils) unwrapped (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase property) update() (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor method) (pytorchrl.utils.RunningMeanStd method) update_algo_parameter() (pytorchrl.agent.algorithms.off_policy.ddqn.DDQN method), [1] update_algorithm_parameter() (pytorchrl.agent.algorithms.base.Algorithm method) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM method), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS method), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG method), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO method), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 method), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C method), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO method), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO method), [1] (pytorchrl.learner.Learner method), [1] (pytorchrl.scheme.collection.c_worker.CWorker method) (pytorchrl.scheme.gradients.g_worker.GWorker method) (pytorchrl.scheme.updates.u_worker.UWorker method) update_epsilon() (pytorchrl.agent.algorithms.off_policy.ddqn.DDQN method), [1] update_eta() (pytorchrl.agent.storages.off_policy.ere_buffer.EREBuffer method), [1] update_every (pytorchrl.agent.algorithms.base.Algorithm property) (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM property), [1] (pytorchrl.agent.algorithms.model_based.mpc_rs.MPC_RS property), [1] (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG property), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO property), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC property), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 property), [1] (pytorchrl.agent.algorithms.on_policy.a2c.A2C property), [1] (pytorchrl.agent.algorithms.on_policy.ppo.PPO property), [1] (pytorchrl.agent.algorithms.on_policy.rnd_ppo.RND_PPO property), [1] (pytorchrl.scheme.collection.c_worker.CWorker attribute)

update_from_moments() (pytorchrl.utils.RunningMeanStd method) update_gaussians() (pytorchrl.agent.algorithms.model_based.mpc_cem.MPC_CEM method), [1] update_mu() (pytorchrl.agent.algorithms.model_based.mpc_pddm.MPC_PDDM method), [1] update_storage_parameter() (pytorchrl.agent.storages.base.Storage method) (pytorchrl.agent.storages.model_based.mb_buffer.MBReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.nstep_buffer.NStepReplayBuffer method), [1] (pytorchrl.agent.storages.off_policy.replay_buffer.ReplayBuffer method), [1] (pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer.VanillaOnPolicyBuffer method), [1] (pytorchrl.scheme.collection.c_worker.CWorker method) update_target_networks() (pytorchrl.agent.algorithms.off_policy.ddpg.DDPG method), [1] (pytorchrl.agent.algorithms.off_policy.ddqn.DDQN method), [1] (pytorchrl.agent.algorithms.off_policy.mpo.MPO method), [1] (pytorchrl.agent.algorithms.off_policy.sac.SAC method), [1] (pytorchrl.agent.algorithms.off_policy.td3.TD3 method), [1] update_worker() (pytorchrl.scheme.scheme.Scheme method), [1] updater (pytorchrl.scheme.updates.u_worker.UWorker attribute) UpdaterThread (class in pytorchrl.scheme.updates.u_worker) used_capacity (pytorchrl.agent.storages.on_policy.gae_buffer.GAEBuffer property), [1] UWorker (class in pytorchrl.scheme.updates.u_worker)

V

VanillaOnPolicyBuffer (class in pytorchrl.agent.storages.on_policy.vanilla_on_policy_buffer), [1] VecEnv (class in pytorchrl.agent.env.vec_env), [1] VecEnvBase (class in pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base) VecEnvObservationWrapper (class in pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base)

VecEnvWrapper (class in pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base) VecPyTorch (class in pytorchrl.agent.env.vector_wrappers) viewer (pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.vec_env_base.VecEnvBase attribute) VTraceBuffer (class in pytorchrl.agent.storages.on_policy.vtrace_buffer), [1]

W

WarpFrame (class in pytorchrl.envs.atari.wrappers) Worker (class in pytorchrl.scheme.base.worker) worker() (in module pytorchrl.agent.env.openai_baselines_dependencies.vec_envs.subproc_vec_env) worker_class (pytorchrl.scheme.base.worker_set.WorkerSet attribute) (pytorchrl.scheme.collection.c_worker_set.CWorkerSet attribute) (pytorchrl.scheme.gradients.g_worker_set.GWorkerSet attribute)

worker_params (pytorchrl.scheme.base.worker_set.WorkerSet attribute) (pytorchrl.scheme.collection.c_worker_set.CWorkerSet attribute) (pytorchrl.scheme.gradients.g_worker_set.GWorkerSet attribute) WorkerSet (class in pytorchrl.scheme.base.worker_set) WorldModel (class in pytorchrl.agent.actors.world_models.world_model), [1] wrap_deepmind() (in module pytorchrl.envs.atari.wrappers) write_row() (pytorchrl.agent.env.openai_baselines_dependencies.Monitor.ResultsWriter method)