Primary symbols
tf_agentstf_agents.agentstf_agents.agents.BehavioralCloningAgenttf_agents.agents.CategoricalDqnAgenttf_agents.agents.CqlSacAgenttf_agents.agents.DdpgAgenttf_agents.agents.DqnAgenttf_agents.agents.PPOAgenttf_agents.agents.PPOClipAgenttf_agents.agents.PPOKLPenaltyAgenttf_agents.agents.ReinforceAgenttf_agents.agents.SacAgenttf_agents.agents.TFAgenttf_agents.agents.Td3Agenttf_agents.agents.behavioral_cloningtf_agents.agents.behavioral_cloning.behavioral_cloning_agenttf_agents.agents.behavioral_cloning.behavioral_cloning_agent.BehavioralCloningAgenttf_agents.agents.behavioral_cloning.behavioral_cloning_agent.BehavioralCloningLossInfotf_agents.agents.categorical_dqntf_agents.agents.categorical_dqn.categorical_dqn_agenttf_agents.agents.categorical_dqn.categorical_dqn_agent.CategoricalDqnAgenttf_agents.agents.categorical_dqn.categorical_dqn_agent.project_distributiontf_agents.agents.cqltf_agents.agents.cql.cql_sac_agenttf_agents.agents.cql.cql_sac_agent.CqlSacAgenttf_agents.agents.cql.cql_sac_agent.CqlSacLossInfotf_agents.agents.data_convertertf_agents.agents.data_converter.AsHalfTransitiontf_agents.agents.data_converter.AsNStepTransitiontf_agents.agents.data_converter.AsTrajectorytf_agents.agents.data_converter.AsTransitiontf_agents.agents.data_converter.DataContexttf_agents.agents.ddpgtf_agents.agents.ddpg.actor_networktf_agents.agents.ddpg.actor_network.ActorNetworktf_agents.agents.ddpg.actor_rnn_networktf_agents.agents.ddpg.actor_rnn_network.ActorRnnNetworktf_agents.agents.ddpg.critic_networktf_agents.agents.ddpg.critic_network.CriticNetworktf_agents.agents.ddpg.critic_rnn_networktf_agents.agents.ddpg.critic_rnn_network.CriticRnnNetworktf_agents.agents.ddpg.ddpg_agenttf_agents.agents.ddpg.ddpg_agent.DdpgAgenttf_agents.agents.ddpg.ddpg_agent.DdpgInfotf_agents.agents.dqntf_agents.agents.dqn.dqn_agenttf_agents.agents.dqn.dqn_agent.DdqnAgenttf_agents.agents.dqn.dqn_agent.DqnAgenttf_agents.agents.dqn.dqn_agent.DqnLossInfotf_agents.agents.dqn.dqn_agent.compute_td_targetstf_agents.agents.ppotf_agents.agents.ppo.ppo_actor_networktf_agents.agents.ppo.ppo_actor_network.PPOActorNetworktf_agents.agents.ppo.ppo_actor_network.tanh_and_scale_to_spectf_agents.agents.ppo.ppo_agenttf_agents.agents.ppo.ppo_agent.PPOAgenttf_agents.agents.ppo.ppo_agent.PPOLossInfotf_agents.agents.ppo.ppo_clip_agenttf_agents.agents.ppo.ppo_clip_agent.PPOClipAgenttf_agents.agents.ppo.ppo_kl_penalty_agenttf_agents.agents.ppo.ppo_kl_penalty_agent.PPOKLPenaltyAgenttf_agents.agents.ppo.ppo_policytf_agents.agents.ppo.ppo_policy.PPOPolicytf_agents.agents.ppo.ppo_utilstf_agents.agents.ppo.ppo_utils.distribution_from_spectf_agents.agents.ppo.ppo_utils.get_distribution_paramstf_agents.agents.ppo.ppo_utils.get_learning_ratetf_agents.agents.ppo.ppo_utils.get_metric_observerstf_agents.agents.ppo.ppo_utils.make_timestep_masktf_agents.agents.ppo.ppo_utils.make_trajectory_masktf_agents.agents.ppo.ppo_utils.nested_kl_divergencetf_agents.agents.reinforcetf_agents.agents.reinforce.reinforce_agenttf_agents.agents.reinforce.reinforce_agent.AdvantageFnTypetf_agents.agents.reinforce.reinforce_agent.ReinforceAgenttf_agents.agents.reinforce.reinforce_agent.ReinforceAgentLossInfotf_agents.agents.sactf_agents.agents.sac.sac_agenttf_agents.agents.sac.sac_agent.SacAgenttf_agents.agents.sac.sac_agent.SacLossInfotf_agents.agents.sac.sac_agent.std_clip_transformtf_agents.agents.td3tf_agents.agents.td3.td3_agenttf_agents.agents.td3.td3_agent.Td3Agenttf_agents.agents.td3.td3_agent.Td3Infotf_agents.agents.tf_agenttf_agents.agents.tf_agent.LossInfotf_agents.agents.tf_agent.TFAgenttf_agents.banditstf_agents.bandits.agentstf_agents.bandits.agents.bernoulli_thompson_sampling_agenttf_agents.bandits.agents.bernoulli_thompson_sampling_agent.BernoulliBanditVariableCollectiontf_agents.bandits.agents.bernoulli_thompson_sampling_agent.BernoulliThompsonSamplingAgenttf_agents.bandits.agents.dropout_thompson_sampling_agenttf_agents.bandits.agents.dropout_thompson_sampling_agent.DropoutThompsonSamplingAgenttf_agents.bandits.agents.examplestf_agents.bandits.agents.exp3_agenttf_agents.bandits.agents.exp3_agent.Exp3Agenttf_agents.bandits.agents.exp3_agent.exp3_update_valuetf_agents.bandits.agents.exp3_agent.selective_sumtf_agents.bandits.agents.exp3_mixture_agenttf_agents.bandits.agents.exp3_mixture_agent.Exp3MixtureAgenttf_agents.bandits.agents.exp3_mixture_agent.Exp3MixtureVariableCollectiontf_agents.bandits.agents.greedy_multi_objective_neural_agenttf_agents.bandits.agents.greedy_multi_objective_neural_agent.GreedyMultiObjectiveNeuralAgenttf_agents.bandits.agents.greedy_reward_prediction_agenttf_agents.bandits.agents.greedy_reward_prediction_agent.GreedyRewardPredictionAgenttf_agents.bandits.agents.lin_ucb_agenttf_agents.bandits.agents.lin_ucb_agent.LinearUCBAgenttf_agents.bandits.agents.linear_bandit_agenttf_agents.bandits.agents.linear_bandit_agent.ExplorationPolicytf_agents.bandits.agents.linear_bandit_agent.LinearBanditAgenttf_agents.bandits.agents.linear_bandit_agent.LinearBanditVariableCollectiontf_agents.bandits.agents.linear_bandit_agent.update_a_and_b_with_forgettingtf_agents.bandits.agents.linear_thompson_sampling_agenttf_agents.bandits.agents.linear_thompson_sampling_agent.LinearThompsonSamplingAgenttf_agents.bandits.agents.mixture_agenttf_agents.bandits.agents.mixture_agent.MixtureAgenttf_agents.bandits.agents.neural_boltzmann_agenttf_agents.bandits.agents.neural_boltzmann_agent.NeuralBoltzmannAgenttf_agents.bandits.agents.neural_epsilon_greedy_agenttf_agents.bandits.agents.neural_epsilon_greedy_agent.NeuralEpsilonGreedyAgenttf_agents.bandits.agents.neural_falcon_agenttf_agents.bandits.agents.neural_falcon_agent.NeuralFalconAgenttf_agents.bandits.agents.neural_linucb_agenttf_agents.bandits.agents.neural_linucb_agent.NeuralLinUCBAgenttf_agents.bandits.agents.neural_linucb_agent.NeuralLinUCBVariableCollectiontf_agents.bandits.agents.ranking_agenttf_agents.bandits.agents.ranking_agent.FeedbackModeltf_agents.bandits.agents.ranking_agent.RankingAgenttf_agents.bandits.agents.ranking_agent.RankingPolicyTypetf_agents.bandits.agents.ranking_agent.compute_score_tensor_for_cascadingtf_agents.bandits.agents.static_mixture_agenttf_agents.bandits.agents.static_mixture_agent.StaticMixtureAgenttf_agents.bandits.agents.utilstf_agents.bandits.agents.utils.build_laplacian_nearest_neighbor_graphtf_agents.bandits.agents.utils.build_laplacian_over_ordinal_integer_actionstf_agents.bandits.agents.utils.compute_pairwise_distancestf_agents.bandits.agents.utils.process_experience_for_neural_agentstf_agents.bandits.agents.utils.sum_reward_weighted_observationstf_agents.bandits.driverstf_agents.bandits.drivers.driver_utilstf_agents.bandits.drivers.driver_utils.trajectory_for_bandittf_agents.bandits.environmentstf_agents.bandits.environments.bandit_py_environmenttf_agents.bandits.environments.bandit_py_environment.BanditPyEnvironmenttf_agents.bandits.environments.bandit_tf_environmenttf_agents.bandits.environments.bandit_tf_environment.BanditTFEnvironmenttf_agents.bandits.environments.bernoulli_action_mask_tf_environmenttf_agents.bandits.environments.bernoulli_action_mask_tf_environment.BernoulliActionMaskTFEnvironmenttf_agents.bandits.environments.bernoulli_py_environmenttf_agents.bandits.environments.bernoulli_py_environment.BernoulliPyEnvironmenttf_agents.bandits.environments.classification_environmenttf_agents.bandits.environments.classification_environment.ClassificationBanditEnvironmenttf_agents.bandits.environments.dataset_utilitiestf_agents.bandits.environments.dataset_utilities.convert_covertype_datasettf_agents.bandits.environments.dataset_utilities.convert_mushroom_csv_to_tf_datasettf_agents.bandits.environments.dataset_utilities.load_movielens_datatf_agents.bandits.environments.dataset_utilities.mushroom_reward_distributiontf_agents.bandits.environments.drifting_linear_environmenttf_agents.bandits.environments.drifting_linear_environment.DriftingLinearDynamicstf_agents.bandits.environments.drifting_linear_environment.DriftingLinearEnvironmenttf_agents.bandits.environments.movielens_per_arm_py_environmenttf_agents.bandits.environments.movielens_per_arm_py_environment.MovieLensPerArmPyEnvironmenttf_agents.bandits.environments.movielens_py_environmenttf_agents.bandits.environments.movielens_py_environment.MovieLensPyEnvironmenttf_agents.bandits.environments.non_stationary_stochastic_environmenttf_agents.bandits.environments.non_stationary_stochastic_environment.EnvironmentDynamicstf_agents.bandits.environments.non_stationary_stochastic_environment.NonStationaryStochasticEnvironmenttf_agents.bandits.environments.piecewise_bernoulli_py_environmenttf_agents.bandits.environments.piecewise_bernoulli_py_environment.PiecewiseBernoulliPyEnvironmenttf_agents.bandits.environments.piecewise_stochastic_environmenttf_agents.bandits.environments.piecewise_stochastic_environment.PiecewiseStationaryDynamicstf_agents.bandits.environments.piecewise_stochastic_environment.PiecewiseStochasticEnvironmenttf_agents.bandits.environments.random_bandit_environmenttf_agents.bandits.environments.random_bandit_environment.RandomBanditEnvironmenttf_agents.bandits.environments.ranking_environmenttf_agents.bandits.environments.ranking_environment.ClickModeltf_agents.bandits.environments.ranking_environment.ExplicitPositionalBiasRankingEnvironmenttf_agents.bandits.environments.ranking_environment.FeedbackModeltf_agents.bandits.environments.ranking_environment.RankingPyEnvironmenttf_agents.bandits.environments.stationary_stochastic_per_arm_py_environmenttf_agents.bandits.environments.stationary_stochastic_per_arm_py_environment.StationaryStochasticPerArmPyEnvironmenttf_agents.bandits.environments.stationary_stochastic_py_environmenttf_agents.bandits.environments.stationary_stochastic_py_environment.StationaryStochasticPyEnvironmenttf_agents.bandits.environments.stationary_stochastic_structured_py_environmenttf_agents.bandits.environments.stationary_stochastic_structured_py_environment.StationaryStochasticStructuredPyEnvironmenttf_agents.bandits.environments.wheel_py_environmenttf_agents.bandits.environments.wheel_py_environment.WheelPyEnvironmenttf_agents.bandits.environments.wheel_py_environment.compute_optimal_actiontf_agents.bandits.environments.wheel_py_environment.compute_optimal_rewardtf_agents.bandits.metricstf_agents.bandits.metrics.tf_metricstf_agents.bandits.metrics.tf_metrics.ConstraintViolationsMetrictf_agents.bandits.metrics.tf_metrics.DistanceFromGreedyMetrictf_agents.bandits.metrics.tf_metrics.RegretMetrictf_agents.bandits.metrics.tf_metrics.SuboptimalArmsMetrictf_agents.bandits.multi_objectivetf_agents.bandits.multi_objective.multi_objective_scalarizertf_agents.bandits.multi_objective.multi_objective_scalarizer.ChebyshevScalarizertf_agents.bandits.multi_objective.multi_objective_scalarizer.HyperVolumeScalarizertf_agents.bandits.multi_objective.multi_objective_scalarizer.HyperVolumeScalarizer.PARAMStf_agents.bandits.multi_objective.multi_objective_scalarizer.LinearScalarizertf_agents.bandits.multi_objective.multi_objective_scalarizer.ScalarFloattf_agents.bandits.multi_objective.multi_objective_scalarizer.Scalarizertf_agents.bandits.multi_objective.multi_objective_scalarizer.ScalarizerTraceTypetf_agents.bandits.networkstf_agents.bandits.networks.global_and_arm_feature_networktf_agents.bandits.networks.global_and_arm_feature_network.GlobalAndArmCommonTowerNetworktf_agents.bandits.networks.global_and_arm_feature_network.GlobalAndArmDotProductNetworktf_agents.bandits.networks.global_and_arm_feature_network.create_feed_forward_common_tower_networktf_agents.bandits.networks.global_and_arm_feature_network.create_feed_forward_dot_product_networktf_agents.bandits.networks.heteroscedastic_q_networktf_agents.bandits.networks.heteroscedastic_q_network.HeteroscedasticQNetworktf_agents.bandits.networks.heteroscedastic_q_network.QBanditNetworkResulttf_agents.bandits.policiestf_agents.bandits.policies.bernoulli_thompson_sampling_policytf_agents.bandits.policies.bernoulli_thompson_sampling_policy.BernoulliThompsonSamplingPolicytf_agents.bandits.policies.boltzmann_reward_prediction_policytf_agents.bandits.policies.boltzmann_reward_prediction_policy.BoltzmannRewardPredictionPolicytf_agents.bandits.policies.categorical_policytf_agents.bandits.policies.categorical_policy.CategoricalPolicytf_agents.bandits.policies.constraintstf_agents.bandits.policies.constraints.AbsoluteConstrainttf_agents.bandits.policies.constraints.BaseConstrainttf_agents.bandits.policies.constraints.InputNetworkConstrainttf_agents.bandits.policies.constraints.NeuralConstrainttf_agents.bandits.policies.constraints.QuantileConstrainttf_agents.bandits.policies.constraints.RelativeConstrainttf_agents.bandits.policies.constraints.RelativeQuantileConstrainttf_agents.bandits.policies.constraints.compute_feasibility_probabilitytf_agents.bandits.policies.constraints.construct_mask_from_multiple_sourcestf_agents.bandits.policies.falcon_reward_prediction_policytf_agents.bandits.policies.falcon_reward_prediction_policy.FalconRewardPredictionPolicytf_agents.bandits.policies.falcon_reward_prediction_policy.get_number_of_trainable_elementstf_agents.bandits.policies.greedy_multi_objective_neural_policytf_agents.bandits.policies.greedy_multi_objective_neural_policy.GreedyMultiObjectiveNeuralPolicytf_agents.bandits.policies.greedy_multi_objective_neural_policy.scalarize_objectivestf_agents.bandits.policies.greedy_reward_prediction_policytf_agents.bandits.policies.greedy_reward_prediction_policy.GreedyRewardPredictionPolicytf_agents.bandits.policies.lin_ucb_policytf_agents.bandits.policies.lin_ucb_policy.LinearUCBPolicytf_agents.bandits.policies.linalgtf_agents.bandits.policies.linalg.conjugate_gradienttf_agents.bandits.policies.linalg.simplified_woodbury_updatetf_agents.bandits.policies.linalg.update_inversetf_agents.bandits.policies.linear_bandit_policytf_agents.bandits.policies.linear_bandit_policy.ExplorationStrategytf_agents.bandits.policies.linear_bandit_policy.LinearBanditPolicytf_agents.bandits.policies.linear_thompson_sampling_policytf_agents.bandits.policies.linear_thompson_sampling_policy.LinearThompsonSamplingPolicytf_agents.bandits.policies.loss_utilstf_agents.bandits.policies.loss_utils.pinball_losstf_agents.bandits.policies.mixture_policytf_agents.bandits.policies.mixture_policy.MixturePolicytf_agents.bandits.policies.neural_linucb_policytf_agents.bandits.policies.neural_linucb_policy.NeuralLinUCBPolicytf_agents.bandits.policies.ranking_policytf_agents.bandits.policies.ranking_policy.CosinePenalizedPlackettLucetf_agents.bandits.policies.ranking_policy.DescendingScoreRankingPolicytf_agents.bandits.policies.ranking_policy.DescendingScoreSamplertf_agents.bandits.policies.ranking_policy.NoPenaltyPlackettLucetf_agents.bandits.policies.ranking_policy.NoPenaltyRankingPolicytf_agents.bandits.policies.ranking_policy.PenalizeCosineDistanceRankingPolicytf_agents.bandits.policies.ranking_policy.PenalizedPlackettLucetf_agents.bandits.policies.ranking_policy.RankingPolicytf_agents.bandits.policies.reward_prediction_base_policytf_agents.bandits.policies.reward_prediction_base_policy.RewardPredictionBasePolicytf_agents.bandits.specstf_agents.bandits.specs.utilstf_agents.distributionstf_agents.distributions.gumbel_softmaxtf_agents.distributions.gumbel_softmax.GumbelSoftmaxtf_agents.distributions.maskedtf_agents.distributions.masked.MaskedCategoricaltf_agents.distributions.reparameterized_samplingtf_agents.distributions.reparameterized_sampling.sampletf_agents.distributions.shifted_categoricaltf_agents.distributions.shifted_categorical.ShiftedCategoricaltf_agents.distributions.tanh_bijector_stabletf_agents.distributions.tanh_bijector_stable.Tanhtf_agents.distributions.utilstf_agents.distributions.utils.DistributionSpecV2tf_agents.distributions.utils.Paramstf_agents.distributions.utils.SquashToSpecNormaltf_agents.distributions.utils.assert_specs_are_compatibletf_agents.distributions.utils.get_parameterstf_agents.distributions.utils.make_from_parameterstf_agents.distributions.utils.merge_to_parameters_from_dicttf_agents.distributions.utils.parameters_to_dicttf_agents.distributions.utils.scale_distribution_to_spectf_agents.driverstf_agents.drivers.drivertf_agents.drivers.driver.Drivertf_agents.drivers.dynamic_episode_drivertf_agents.drivers.dynamic_episode_driver.DynamicEpisodeDrivertf_agents.drivers.dynamic_episode_driver.is_bandit_envtf_agents.drivers.dynamic_step_drivertf_agents.drivers.dynamic_step_driver.DynamicStepDrivertf_agents.drivers.dynamic_step_driver.is_bandit_envtf_agents.drivers.py_drivertf_agents.drivers.py_driver.PyDrivertf_agents.environmentstf_agents.environments.ActionClipWrappertf_agents.environments.ActionDiscretizeWrappertf_agents.environments.ActionOffsetWrappertf_agents.environments.ActionRepeattf_agents.environments.BatchedPyEnvironmenttf_agents.environments.FlattenObservationsWrappertf_agents.environments.GoalReplayEnvWrappertf_agents.environments.HistoryWrappertf_agents.environments.ObservationFilterWrappertf_agents.environments.OneHotActionWrappertf_agents.environments.ParallelPyEnvironmenttf_agents.environments.PerformanceProfilertf_agents.environments.PyEnvironmenttf_agents.environments.PyEnvironmentBaseWrappertf_agents.environments.RandomPyEnvironmenttf_agents.environments.RandomTFEnvironmenttf_agents.environments.RunStatstf_agents.environments.TFEnvironmenttf_agents.environments.TFPyEnvironmenttf_agents.environments.TimeLimittf_agents.environments.TrajectoryReplaytf_agents.environments.batched_py_environmenttf_agents.environments.batched_py_environment.BatchedPyEnvironmenttf_agents.environments.batched_py_environment.unstack_actionstf_agents.environments.gym_wrappertf_agents.environments.gym_wrapper.GymWrappertf_agents.environments.gym_wrapper.spec_from_gym_spacetf_agents.environments.parallel_py_environmenttf_agents.environments.parallel_py_environment.EnvConstructortf_agents.environments.parallel_py_environment.ParallelPyEnvironmenttf_agents.environments.parallel_py_environment.ProcessPyEnvironmenttf_agents.environments.parallel_py_environment.Promisetf_agents.environments.py_environmenttf_agents.environments.py_environment.PyEnvironmenttf_agents.environments.random_py_environmenttf_agents.environments.random_py_environment.RandomPyEnvironmenttf_agents.environments.random_py_environment.RewardFntf_agents.environments.random_tf_environmenttf_agents.environments.random_tf_environment.RandomTFEnvironmenttf_agents.environments.suite_gymtf_agents.environments.suite_gym.TimeLimitWrapperTypetf_agents.environments.suite_gym.loadtf_agents.environments.suite_gym.wrap_envtf_agents.environments.tf_environmenttf_agents.environments.tf_environment.TFEnvironmenttf_agents.environments.tf_py_environmenttf_agents.environments.tf_py_environment.TFPyEnvironmenttf_agents.environments.trajectory_replaytf_agents.environments.trajectory_replay.TrajectoryReplaytf_agents.environments.utilstf_agents.environments.utils.get_tf_envtf_agents.environments.utils.validate_py_environmenttf_agents.environments.validate_py_environmenttf_agents.environments.wrapperstf_agents.environments.wrappers.ActionClipWrappertf_agents.environments.wrappers.ActionDiscretizeWrappertf_agents.environments.wrappers.ActionOffsetWrappertf_agents.environments.wrappers.ActionRepeattf_agents.environments.wrappers.ExtraDisabledActionsWrappertf_agents.environments.wrappers.FixedLengthtf_agents.environments.wrappers.FlattenActionWrappertf_agents.environments.wrappers.FlattenObservationsWrappertf_agents.environments.wrappers.GoalReplayEnvWrappertf_agents.environments.wrappers.HistoryWrappertf_agents.environments.wrappers.ObservationFilterWrappertf_agents.environments.wrappers.OneHotActionWrappertf_agents.environments.wrappers.PerformanceProfilertf_agents.environments.wrappers.PyEnvironmentBaseWrappertf_agents.environments.wrappers.RunStatstf_agents.environments.wrappers.TimeLimittf_agents.evaltf_agents.eval.metric_utilstf_agents.eval.metric_utils.MetricsGrouptf_agents.eval.metric_utils.computetf_agents.eval.metric_utils.compute_summariestf_agents.eval.metric_utils.eager_computetf_agents.eval.metric_utils.log_metricstf_agents.experimentaltf_agents.experimental.distributedtf_agents.experimental.distributed.ReverbVariableContainertf_agents.experimental.distributed.reverb_variable_containertf_agents.experimental.distributed.reverb_variable_container.ReverbVariableContainertf_agents.keras_layerstf_agents.keras_layers.BiasLayertf_agents.keras_layers.DynamicUnrolltf_agents.keras_layers.InnerReshapetf_agents.keras_layers.RNNWrappertf_agents.keras_layers.SquashedOuterWrappertf_agents.keras_layers.bias_layertf_agents.keras_layers.bias_layer.BiasLayertf_agents.keras_layers.dynamic_unroll_layertf_agents.keras_layers.dynamic_unroll_layer.DynamicUnrolltf_agents.keras_layers.inner_reshapetf_agents.keras_layers.inner_reshape.InnerReshapetf_agents.keras_layers.permanent_variable_rate_dropouttf_agents.keras_layers.permanent_variable_rate_dropout.PermanentVariableRateDropouttf_agents.keras_layers.rnn_wrappertf_agents.keras_layers.rnn_wrapper.RNNWrappertf_agents.keras_layers.squashed_outer_wrappertf_agents.keras_layers.squashed_outer_wrapper.SquashedOuterWrappertf_agents.metricstf_agents.metrics.batched_py_metrictf_agents.metrics.batched_py_metric.BatchedPyMetrictf_agents.metrics.export_utilstf_agents.metrics.export_utils.export_metricstf_agents.metrics.py_metrictf_agents.metrics.py_metric.MetricTypetf_agents.metrics.py_metric.PyMetrictf_agents.metrics.py_metric.PyStepMetrictf_agents.metrics.py_metric.run_summariestf_agents.metrics.py_metricstf_agents.metrics.py_metrics.AverageEpisodeLengthMetrictf_agents.metrics.py_metrics.AverageReturnMetrictf_agents.metrics.py_metrics.CounterMetrictf_agents.metrics.py_metrics.EnvironmentStepstf_agents.metrics.py_metrics.NumberOfEpisodestf_agents.metrics.py_metrics.NumpyDequetf_agents.metrics.py_metrics.StreamingMetrictf_agents.metrics.tf_metrictf_agents.metrics.tf_metric.TFHistogramStepMetrictf_agents.metrics.tf_metric.TFMultiMetricStepMetrictf_agents.metrics.tf_metric.TFStepMetrictf_agents.metrics.tf_metricstf_agents.metrics.tf_metrics.AverageEpisodeLengthMetrictf_agents.metrics.tf_metrics.AverageReturnMetrictf_agents.metrics.tf_metrics.AverageReturnMultiMetrictf_agents.metrics.tf_metrics.ChosenActionHistogramtf_agents.metrics.tf_metrics.EnvironmentStepstf_agents.metrics.tf_metrics.MaxReturnMetrictf_agents.metrics.tf_metrics.MinReturnMetrictf_agents.metrics.tf_metrics.NumberOfEpisodestf_agents.metrics.tf_metrics.TFDequetf_agents.metrics.tf_metrics.log_metricstf_agents.metrics.tf_py_metrictf_agents.metrics.tf_py_metric.TFPyMetrictf_agents.networkstf_agents.networks.NestFlattentf_agents.networks.NestMaptf_agents.networks.Networktf_agents.networks.Sequentialtf_agents.networks.actor_distribution_networktf_agents.networks.actor_distribution_network.ActorDistributionNetworktf_agents.networks.actor_distribution_rnn_networktf_agents.networks.actor_distribution_rnn_network.ActorDistributionRnnNetworktf_agents.networks.categorical_projection_networktf_agents.networks.categorical_projection_network.CategoricalProjectionNetworktf_agents.networks.categorical_q_networktf_agents.networks.categorical_q_network.CategoricalQNetworktf_agents.networks.encoding_networktf_agents.networks.encoding_network.EncodingNetworktf_agents.networks.expand_dims_layertf_agents.networks.expand_dims_layer.ExpandDimstf_agents.networks.layer_utilstf_agents.networks.layer_utils.print_summarytf_agents.networks.lstm_encoding_networktf_agents.networks.lstm_encoding_network.LSTMEncodingNetworktf_agents.networks.mask_splitter_networktf_agents.networks.mask_splitter_network.MaskSplitterNetworktf_agents.networks.nest_maptf_agents.networks.nest_map.NestFlattentf_agents.networks.nest_map.NestMaptf_agents.networks.networktf_agents.networks.network.DistributionNetworktf_agents.networks.network.Networktf_agents.networks.network.create_variablestf_agents.networks.network.get_state_spectf_agents.networks.normal_projection_networktf_agents.networks.normal_projection_network.NormalProjectionNetworktf_agents.networks.normal_projection_network.tanh_squash_to_spectf_agents.networks.q_networktf_agents.networks.q_network.QNetworktf_agents.networks.q_network.validate_specstf_agents.networks.q_rnn_networktf_agents.networks.q_rnn_network.QRnnNetworktf_agents.networks.sequentialtf_agents.networks.sequential.Sequentialtf_agents.networks.utilstf_agents.networks.utils.BatchSquashtf_agents.networks.utils.check_single_floating_network_outputtf_agents.networks.utils.clone_initializertf_agents.networks.utils.mlp_layerstf_agents.networks.value_networktf_agents.networks.value_network.ValueNetworktf_agents.networks.value_rnn_networktf_agents.networks.value_rnn_network.ValueRnnNetworktf_agents.policiestf_agents.policies.ActorPolicytf_agents.policies.EpsilonGreedyPolicytf_agents.policies.GreedyPolicytf_agents.policies.PolicySavertf_agents.policies.PyTFEagerPolicytf_agents.policies.SavedModelPyTFEagerPolicytf_agents.policies.TFPolicytf_agents.policies.actor_policytf_agents.policies.actor_policy.ActorPolicytf_agents.policies.async_policy_savertf_agents.policies.async_policy_saver.AsyncPolicySavertf_agents.policies.boltzmann_policytf_agents.policies.boltzmann_policy.BoltzmannPolicytf_agents.policies.categorical_q_policytf_agents.policies.categorical_q_policy.CategoricalQPolicytf_agents.policies.epsilon_greedy_policytf_agents.policies.epsilon_greedy_policy.EpsilonGreedyPolicytf_agents.policies.fixed_policytf_agents.policies.fixed_policy.FixedPolicytf_agents.policies.gaussian_policytf_agents.policies.gaussian_policy.GaussianPolicytf_agents.policies.greedy_policytf_agents.policies.greedy_policy.DeterministicWithLogProbtf_agents.policies.greedy_policy.GreedyPolicytf_agents.policies.ou_noise_policytf_agents.policies.ou_noise_policy.OUNoisePolicytf_agents.policies.policy_savertf_agents.policies.policy_saver.InputFnAndSpecTypetf_agents.policies.policy_saver.InputFnTypetf_agents.policies.policy_saver.PolicySavertf_agents.policies.policy_saver.add_batch_dimtf_agents.policies.policy_saver.rename_spec_with_nest_pathstf_agents.policies.policy_saver.specs_from_collect_data_spectf_agents.policies.py_policytf_agents.policies.py_policy.PyPolicytf_agents.policies.py_tf_eager_policytf_agents.policies.py_tf_eager_policy.PyTFEagerPolicytf_agents.policies.py_tf_eager_policy.PyTFEagerPolicyBasetf_agents.policies.py_tf_eager_policy.SavedModelPyTFEagerPolicytf_agents.policies.py_tf_policytf_agents.policies.py_tf_policy.PyTFPolicytf_agents.policies.q_policytf_agents.policies.q_policy.QPolicytf_agents.policies.random_py_policytf_agents.policies.random_py_policy.RandomPyPolicytf_agents.policies.random_tf_policytf_agents.policies.random_tf_policy.RandomTFPolicytf_agents.policies.scripted_py_policytf_agents.policies.scripted_py_policy.ScriptedPyPolicytf_agents.policies.tf_policytf_agents.policies.tf_policy.TFPolicytf_agents.policies.tf_py_policytf_agents.policies.tf_py_policy.TFPyPolicytf_agents.policies.tf_py_policy.map_tensor_spec_to_dtypes_listtf_agents.policies.utilstf_agents.policies.utils.BanditPolicyTypetf_agents.policies.utils.InfoFieldstf_agents.policies.utils.PerArmPolicyInfotf_agents.policies.utils.PolicyInfotf_agents.policies.utils.bandit_policy_uniform_masktf_agents.policies.utils.check_no_mask_with_arm_featurestf_agents.policies.utils.create_bandit_policy_type_tensor_spectf_agents.policies.utils.create_chosen_arm_features_info_spectf_agents.policies.utils.get_model_indextf_agents.policies.utils.get_num_actions_from_tensor_spectf_agents.policies.utils.has_bandit_policy_typetf_agents.policies.utils.has_chosen_arm_featurestf_agents.policies.utils.masked_argmaxtf_agents.policies.utils.populate_policy_infotf_agents.policies.utils.set_bandit_policy_typetf_agents.replay_bufferstf_agents.replay_buffers.ReverbAddEpisodeObservertf_agents.replay_buffers.ReverbAddTrajectoryObservertf_agents.replay_buffers.ReverbReplayBuffertf_agents.replay_buffers.TFUniformReplayBuffertf_agents.replay_buffers.py_hashed_replay_buffertf_agents.replay_buffers.py_hashed_replay_buffer.FrameBuffertf_agents.replay_buffers.py_hashed_replay_buffer.PyHashedReplayBuffertf_agents.replay_buffers.py_uniform_replay_buffertf_agents.replay_buffers.py_uniform_replay_buffer.PyUniformReplayBuffertf_agents.replay_buffers.replay_buffertf_agents.replay_buffers.replay_buffer.ReplayBuffertf_agents.replay_buffers.reverb_replay_buffertf_agents.replay_buffers.reverb_replay_buffer.ReverbReplayBuffertf_agents.replay_buffers.reverb_replay_buffer.make_reverb_datasettf_agents.replay_buffers.reverb_replay_buffer.truncate_reshape_rows_by_num_stepstf_agents.replay_buffers.reverb_utilstf_agents.replay_buffers.reverb_utils.ReverbAddEpisodeObservertf_agents.replay_buffers.reverb_utils.ReverbAddTrajectoryObservertf_agents.replay_buffers.reverb_utils.ReverbTrajectorySequenceObservertf_agents.replay_buffers.tabletf_agents.replay_buffers.table.Tabletf_agents.replay_buffers.tf_uniform_replay_buffertf_agents.replay_buffers.tf_uniform_replay_buffer.BufferInfotf_agents.replay_buffers.tf_uniform_replay_buffer.TFUniformReplayBuffertf_agents.specstf_agents.specs.ArraySpectf_agents.specs.BoundedArraySpectf_agents.specs.array_spectf_agents.specs.array_spec.ArraySpectf_agents.specs.array_spec.BoundedArraySpectf_agents.specs.array_spec.add_outer_dims_nesttf_agents.specs.array_spec.assert_arrays_spec_nesttf_agents.specs.array_spec.check_arrays_nesttf_agents.specs.array_spec.is_boundedtf_agents.specs.array_spec.is_continuoustf_agents.specs.array_spec.is_discretetf_agents.specs.array_spec.sample_bounded_spectf_agents.specs.array_spec.sample_spec_nesttf_agents.specs.bandit_spec_utilstf_agents.specs.bandit_spec_utils.create_per_arm_observation_spectf_agents.specs.bandit_spec_utils.drop_arm_observationtf_agents.specs.bandit_spec_utils.get_context_dims_from_spectf_agents.specs.distribution_spectf_agents.specs.distribution_spec.DistributionSpectf_agents.specs.distribution_spec.deterministic_distribution_from_spectf_agents.specs.distribution_spec.nested_distributions_from_specstf_agents.specs.from_spectf_agents.specs.is_boundedtf_agents.specs.is_continuoustf_agents.specs.is_discretetf_agents.specs.sample_spec_nesttf_agents.specs.tensor_spectf_agents.specs.tensor_spec.add_outer_dimtf_agents.specs.tensor_spec.add_outer_dims_nesttf_agents.specs.tensor_spec.from_packed_prototf_agents.specs.tensor_spec.from_pbtxt_filetf_agents.specs.tensor_spec.from_prototf_agents.specs.tensor_spec.from_spectf_agents.specs.tensor_spec.is_boundedtf_agents.specs.tensor_spec.is_continuoustf_agents.specs.tensor_spec.is_discretetf_agents.specs.tensor_spec.remove_outer_dims_nesttf_agents.specs.tensor_spec.sample_bounded_spectf_agents.specs.tensor_spec.sample_spec_nesttf_agents.specs.tensor_spec.to_array_spectf_agents.specs.tensor_spec.to_nest_array_spectf_agents.specs.tensor_spec.to_nest_placeholdertf_agents.specs.tensor_spec.to_pbtxt_filetf_agents.specs.tensor_spec.to_placeholdertf_agents.specs.tensor_spec.to_placeholder_with_defaulttf_agents.specs.tensor_spec.to_prototf_agents.specs.tensor_spec.with_dtypetf_agents.specs.tensor_spec.zero_spec_nesttf_agents.specs.zero_spec_nesttf_agents.systemtf_agents.system.defaulttf_agents.system.default.multiprocessing_coretf_agents.system.default.multiprocessing_core.StateSavertf_agents.system.default.multiprocessing_core.enable_interactive_modetf_agents.system.default.multiprocessing_core.handle_maintf_agents.system.default.multiprocessing_core.handle_test_maintf_agents.system.multiprocessingtf_agents.system.multiprocessing.GinStateSavertf_agents.system.multiprocessing.OpenAIGymStateSavertf_agents.system.multiprocessing.get_contexttf_agents.system.system_multiprocessingtf_agents.system.system_multiprocessing.GinStateSavertf_agents.system.system_multiprocessing.OpenAIGymStateSavertf_agents.system.system_multiprocessing.get_contexttf_agents.traintf_agents.train.Actortf_agents.train.Learnertf_agents.train.actortf_agents.train.actor.Actortf_agents.train.actor.collect_metricstf_agents.train.actor.eval_metricstf_agents.train.interval_triggertf_agents.train.interval_trigger.IntervalTriggertf_agents.train.learnertf_agents.train.learner.ExperienceAndSampleInfotf_agents.train.learner.Learnertf_agents.train.step_per_second_trackertf_agents.train.step_per_second_tracker.StepPerSecondTrackertf_agents.train.triggerstf_agents.train.triggers.PolicySavedModelTriggertf_agents.train.triggers.ReverbCheckpointTriggertf_agents.train.triggers.StepPerSecondLogTriggertf_agents.trajectoriestf_agents.trajectories.PolicyInfotf_agents.trajectories.PolicySteptf_agents.trajectories.StepTypetf_agents.trajectories.TimeSteptf_agents.trajectories.Trajectorytf_agents.trajectories.Transitiontf_agents.trajectories.boundarytf_agents.trajectories.firsttf_agents.trajectories.from_transitiontf_agents.trajectories.lasttf_agents.trajectories.midtf_agents.trajectories.policy_steptf_agents.trajectories.policy_step.ActionTypetf_agents.trajectories.policy_step.CommonFieldstf_agents.trajectories.policy_step.PolicyInfotf_agents.trajectories.policy_step.PolicySteptf_agents.trajectories.policy_step.get_log_probabilitytf_agents.trajectories.policy_step.set_log_probabilitytf_agents.trajectories.restarttf_agents.trajectories.single_steptf_agents.trajectories.terminationtf_agents.trajectories.time_steptf_agents.trajectories.time_step.StepTypetf_agents.trajectories.time_step.TimeSteptf_agents.trajectories.time_step.restarttf_agents.trajectories.time_step.terminationtf_agents.trajectories.time_step.time_step_spectf_agents.trajectories.time_step.transitiontf_agents.trajectories.time_step.truncationtf_agents.trajectories.time_step_spectf_agents.trajectories.to_n_step_transitiontf_agents.trajectories.to_transitiontf_agents.trajectories.to_transition_spectf_agents.trajectories.trajectorytf_agents.trajectories.trajectory.Trajectorytf_agents.trajectories.trajectory.Transitiontf_agents.trajectories.trajectory.boundarytf_agents.trajectories.trajectory.experience_to_transitionstf_agents.trajectories.trajectory.firsttf_agents.trajectories.trajectory.from_episodetf_agents.trajectories.trajectory.from_transitiontf_agents.trajectories.trajectory.lasttf_agents.trajectories.trajectory.midtf_agents.trajectories.trajectory.single_steptf_agents.trajectories.trajectory.to_n_step_transitiontf_agents.trajectories.trajectory.to_transitiontf_agents.trajectories.trajectory.to_transition_spectf_agents.trajectories.transitiontf_agents.trajectories.truncationtf_agents.typingtf_agents.typing.typestf_agents.typing.types.Arraytf_agents.typing.types.Booltf_agents.typing.types.ComparatorFntf_agents.typing.types.Floattf_agents.typing.types.FloatOrReturningFloattf_agents.typing.types.GymEnvWrappertf_agents.typing.types.Inttf_agents.typing.types.LookupLayertf_agents.typing.types.LossFntf_agents.typing.types.Nestedtf_agents.typing.types.NestedArraytf_agents.typing.types.NestedArraySpectf_agents.typing.types.NestedBoundedTensorSpectf_agents.typing.types.NestedDistributiontf_agents.typing.types.NestedLayertf_agents.typing.types.NestedNetworktf_agents.typing.types.NestedPlaceHoldertf_agents.typing.types.NestedSpectf_agents.typing.types.NestedSpecTensorOrArraytf_agents.typing.types.NestedTensortf_agents.typing.types.NestedTensorOrArraytf_agents.typing.types.NestedTensorSpectf_agents.typing.types.NestedVariabletf_agents.typing.types.Observertf_agents.typing.types.Optimizertf_agents.typing.types.PyEnvWrappertf_agents.typing.types.Seedtf_agents.typing.types.Shapetf_agents.typing.types.ShapeSequencetf_agents.typing.types.Spectf_agents.typing.types.SpecTensorOrArraytf_agents.typing.types.Splittertf_agents.typing.types.Tensortf_agents.typing.types.TensorOrArraytf_agents.typing.types.TensorSpectf_agents.utilstf_agents.utils.commontf_agents.utils.common.AggregatedLossestf_agents.utils.common.Checkpointertf_agents.utils.common.EagerPeriodicallytf_agents.utils.common.OUProcesstf_agents.utils.common.Periodicallytf_agents.utils.common.aggregate_lossestf_agents.utils.common.assert_members_are_not_overriddentf_agents.utils.common.check_matching_networkstf_agents.utils.common.check_no_shared_variablestf_agents.utils.common.check_tf1_allowedtf_agents.utils.common.clip_to_spectf_agents.utils.common.compute_returnstf_agents.utils.common.convert_q_logits_to_valuestf_agents.utils.common.create_variabletf_agents.utils.common.deduped_network_variablestf_agents.utils.common.discounted_future_sumtf_agents.utils.common.discounted_future_sum_maskedtf_agents.utils.common.element_wise_huber_losstf_agents.utils.common.element_wise_squared_losstf_agents.utils.common.entropytf_agents.utils.common.extract_shared_variablestf_agents.utils.common.functiontf_agents.utils.common.function_in_tf1tf_agents.utils.common.generate_tensor_summariestf_agents.utils.common.get_contiguous_sub_episodestf_agents.utils.common.get_episode_masktf_agents.utils.common.has_eager_been_enabledtf_agents.utils.common.in_legacy_tf1tf_agents.utils.common.index_with_actionstf_agents.utils.common.initialize_uninitialized_variablestf_agents.utils.common.join_scopetf_agents.utils.common.load_spectf_agents.utils.common.log_probabilitytf_agents.utils.common.maybe_copy_target_network_with_checkstf_agents.utils.common.ornstein_uhlenbeck_processtf_agents.utils.common.periodicallytf_agents.utils.common.replicatetf_agents.utils.common.resource_variables_enabledtf_agents.utils.common.safe_has_statetf_agents.utils.common.save_spectf_agents.utils.common.scale_to_spectf_agents.utils.common.set_default_tf_function_parameterstf_agents.utils.common.shift_valuestf_agents.utils.common.soft_device_placementtf_agents.utils.common.soft_variables_updatetf_agents.utils.common.spec_means_and_magnitudestf_agents.utils.common.summarize_scalar_dicttf_agents.utils.common.summarize_tensor_dicttf_agents.utils.common.transpose_batch_timetf_agents.utils.compositetf_agents.utils.composite.expand_dimstf_agents.utils.composite.reshapetf_agents.utils.composite.shapetf_agents.utils.composite.slice_fromtf_agents.utils.composite.slice_totf_agents.utils.composite.squeezetf_agents.utils.eager_utilstf_agents.utils.eager_utils.Futuretf_agents.utils.eager_utils.add_gradients_summariestf_agents.utils.eager_utils.add_variables_summariestf_agents.utils.eager_utils.clip_gradient_normstf_agents.utils.eager_utils.clip_gradient_norms_fntf_agents.utils.eager_utils.create_train_optf_agents.utils.eager_utils.create_train_steptf_agents.utils.eager_utils.dataset_iteratortf_agents.utils.eager_utils.future_in_eager_modetf_agents.utils.eager_utils.get_nexttf_agents.utils.eager_utils.has_self_cls_argtf_agents.utils.eager_utils.is_unboundtf_agents.utils.eager_utils.np_functiontf_agents.utils.example_encodingtf_agents.utils.example_encoding.get_example_decodertf_agents.utils.example_encoding.get_example_encodertf_agents.utils.example_encoding.get_example_serializertf_agents.utils.lazy_loadertf_agents.utils.lazy_loader.LazyLoadertf_agents.utils.nest_utilstf_agents.utils.nest_utils.assert_matching_dtypes_and_inner_shapestf_agents.utils.nest_utils.assert_same_structuretf_agents.utils.nest_utils.assert_tensors_matching_dtypes_and_shapestf_agents.utils.nest_utils.assert_value_spectf_agents.utils.nest_utils.batch_nested_arraytf_agents.utils.nest_utils.batch_nested_tensorstf_agents.utils.nest_utils.fast_map_structuretf_agents.utils.nest_utils.fast_map_structure_flattentf_agents.utils.nest_utils.flatten_and_check_shape_nested_specstf_agents.utils.nest_utils.flatten_multi_batched_nested_tensorstf_agents.utils.nest_utils.flatten_with_joined_pathstf_agents.utils.nest_utils.get_outer_array_shapetf_agents.utils.nest_utils.get_outer_ranktf_agents.utils.nest_utils.get_outer_shapetf_agents.utils.nest_utils.has_tensorstf_agents.utils.nest_utils.is_batched_nested_tensorstf_agents.utils.nest_utils.prune_extra_keystf_agents.utils.nest_utils.remove_singleton_batch_spec_dimtf_agents.utils.nest_utils.spec_shapetf_agents.utils.nest_utils.split_nested_tensorstf_agents.utils.nest_utils.stack_nested_arraystf_agents.utils.nest_utils.stack_nested_tensorstf_agents.utils.nest_utils.tile_batchtf_agents.utils.nest_utils.unbatch_nested_arraytf_agents.utils.nest_utils.unbatch_nested_tensorstf_agents.utils.nest_utils.unbatch_nested_tensors_to_arraystf_agents.utils.nest_utils.unstack_nested_arraystf_agents.utils.nest_utils.unstack_nested_arrays_into_flat_itemstf_agents.utils.nest_utils.unstack_nested_tensorstf_agents.utils.nest_utils.wheretf_agents.utils.numpy_storagetf_agents.utils.numpy_storage.NumpyStatetf_agents.utils.numpy_storage.NumpyStoragetf_agents.utils.object_identitytf_agents.utils.object_identity.ObjectIdentityDictionarytf_agents.utils.object_identity.ObjectIdentitySettf_agents.utils.object_identity.ObjectIdentityWeakKeyDictionarytf_agents.utils.object_identity.ObjectIdentityWeakSettf_agents.utils.object_identity.Referencetf_agents.utils.session_utilstf_agents.utils.session_utils.SessionUsertf_agents.utils.tensor_normalizertf_agents.utils.tensor_normalizer.EMATensorNormalizertf_agents.utils.tensor_normalizer.StreamingTensorNormalizertf_agents.utils.tensor_normalizer.TensorNormalizertf_agents.utils.tensor_normalizer.kahan_summationtf_agents.utils.tensor_normalizer.parallel_variance_calculationtf_agents.utils.test_utilstf_agents.utils.test_utils.FLAGStf_agents.utils.test_utils.TestCasetf_agents.utils.test_utils.TestCase.failureExceptiontf_agents.utils.test_utils.containstf_agents.utils.test_utils.maintf_agents.utils.test_utils.test_src_dir_pathtf_agents.utils.timertf_agents.utils.timer.Timertf_agents.utils.value_opstf_agents.utils.value_ops.discounted_returntf_agents.utils.value_ops.generalized_advantage_estimationtf_agents.version