Path	Lines of Code
MANIFEST.in	1
setup.py	242
tf_agents/__init__.py	46
tf_agents/agents/__init__.py	23
tf_agents/agents/behavioral_cloning/__init__.py	1
tf_agents/agents/behavioral_cloning/behavioral_cloning_agent.py	174
tf_agents/agents/categorical_dqn/__init__.py	1
tf_agents/agents/categorical_dqn/categorical_dqn_agent.py	324
tf_agents/agents/cql/__init__.py	1
tf_agents/agents/cql/cql_sac_agent.py	454
tf_agents/agents/data_converter.py	303
tf_agents/agents/ddpg/__init__.py	5
tf_agents/agents/ddpg/actor_network.py	61
tf_agents/agents/ddpg/actor_rnn_network.py	98
tf_agents/agents/ddpg/critic_network.py	79
tf_agents/agents/ddpg/critic_rnn_network.py	147
tf_agents/agents/ddpg/ddpg_agent.py	252
tf_agents/agents/dqn/__init__.py	1
tf_agents/agents/dqn/dqn_agent.py	306
tf_agents/agents/ppo/__init__.py	6
tf_agents/agents/ppo/ppo_actor_network.py	62
tf_agents/agents/ppo/ppo_agent.py	903
tf_agents/agents/ppo/ppo_clip_agent.py	82
tf_agents/agents/ppo/ppo_kl_penalty_agent.py	88
tf_agents/agents/ppo/ppo_policy.py	155
tf_agents/agents/ppo/ppo_utils.py	109
tf_agents/agents/qtopt/qtopt_agent.py	382
tf_agents/agents/random/__init__.py	2
tf_agents/agents/random/fixed_policy_agent.py	44
tf_agents/agents/random/random_agent.py	30
tf_agents/agents/reinforce/__init__.py	1
tf_agents/agents/reinforce/reinforce_agent.py	276
tf_agents/agents/sac/__init__.py	1
tf_agents/agents/sac/sac_agent.py	452
tf_agents/agents/sac/tanh_normal_projection_network.py	79
tf_agents/agents/td3/__init__.py	1
tf_agents/agents/td3/td3_agent.py	330
tf_agents/agents/tf_agent.py	222
tf_agents/bandits/__init__.py	8
tf_agents/bandits/agents/__init__.py	15
tf_agents/bandits/agents/bernoulli_thompson_sampling_agent.py	97
tf_agents/bandits/agents/dropout_thompson_sampling_agent.py	87
tf_agents/bandits/agents/exp3_agent.py	76
tf_agents/bandits/agents/exp3_mixture_agent.py	107
tf_agents/bandits/agents/greedy_multi_objective_neural_agent.py	201
tf_agents/bandits/agents/greedy_reward_prediction_agent.py	225
tf_agents/bandits/agents/lin_ucb_agent.py	50
tf_agents/bandits/agents/linear_bandit_agent.py	369
tf_agents/bandits/agents/linear_thompson_sampling_agent.py	50
tf_agents/bandits/agents/mixture_agent.py	111
tf_agents/bandits/agents/neural_boltzmann_agent.py	64
tf_agents/bandits/agents/neural_epsilon_greedy_agent.py	59
tf_agents/bandits/agents/neural_linucb_agent.py	360
tf_agents/bandits/agents/static_mixture_agent.py	9
tf_agents/bandits/agents/utils.py	73
tf_agents/bandits/drivers/__init__.py	1
tf_agents/bandits/drivers/driver_utils.py	17
tf_agents/bandits/environments/__init__.py	17
tf_agents/bandits/environments/bandit_py_environment.py	43
tf_agents/bandits/environments/bandit_tf_environment.py	69
tf_agents/bandits/environments/bernoulli_action_mask_tf_environment.py	74
tf_agents/bandits/environments/bernoulli_py_environment.py	40
tf_agents/bandits/environments/classification_environment.py	100
tf_agents/bandits/environments/dataset_utilities.py	70
tf_agents/bandits/environments/drifting_linear_environment.py	138
tf_agents/bandits/environments/environment_utilities.py	158
tf_agents/bandits/environments/movielens_per_arm_py_environment.py	103
tf_agents/bandits/environments/movielens_py_environment.py	72
tf_agents/bandits/environments/non_stationary_stochastic_environment.py	72
tf_agents/bandits/environments/piecewise_bernoulli_py_environment.py	57
tf_agents/bandits/environments/piecewise_stochastic_environment.py	133
tf_agents/bandits/environments/random_bandit_environment.py	58
tf_agents/bandits/environments/stationary_stochastic_per_arm_py_environment.py	80
tf_agents/bandits/environments/stationary_stochastic_py_environment.py	70
tf_agents/bandits/environments/stationary_stochastic_structured_py_environment.py	81
tf_agents/bandits/environments/wheel_py_environment.py	104
tf_agents/bandits/metrics/__init__.py	1
tf_agents/bandits/metrics/tf_metrics.py	98
tf_agents/bandits/multi_objective/__init__.py	1
tf_agents/bandits/multi_objective/multi_objective_scalarizer.py	187
tf_agents/bandits/networks/__init__.py	2
tf_agents/bandits/networks/global_and_arm_feature_network.py	162
tf_agents/bandits/networks/heteroscedastic_q_network.py	77
tf_agents/bandits/policies/__init__.py	9
tf_agents/bandits/policies/bernoulli_thompson_sampling_policy.py	103
tf_agents/bandits/policies/boltzmann_reward_prediction_policy.py	207
tf_agents/bandits/policies/categorical_policy.py	49
tf_agents/bandits/policies/constraints.py	280
tf_agents/bandits/policies/greedy_multi_objective_neural_policy.py	209
tf_agents/bandits/policies/greedy_reward_prediction_policy.py	149
tf_agents/bandits/policies/lin_ucb_policy.py	40
tf_agents/bandits/policies/linalg.py	80
tf_agents/bandits/policies/linear_bandit_policy.py	276
tf_agents/bandits/policies/linear_thompson_sampling_policy.py	39
tf_agents/bandits/policies/loss_utils.py	28
tf_agents/bandits/policies/mixture_policy.py	77
tf_agents/bandits/policies/neural_linucb_policy.py	241
tf_agents/bandits/replay_buffers/bandit_replay_buffer.py	2
tf_agents/benchmark/__init__.py	1
tf_agents/benchmark/cql_sac_benchmark.py	46
tf_agents/benchmark/distribution_strategy_utils.py	47
tf_agents/benchmark/dqn_benchmark.py	28
tf_agents/benchmark/perfzero_benchmark.py	41
tf_agents/benchmark/ppo_benchmark.py	45
tf_agents/benchmark/sac_benchmark.py	39
tf_agents/benchmark/utils.py	167
tf_agents/distributions/__init__.py	4
tf_agents/distributions/gumbel_softmax.py	36
tf_agents/distributions/masked.py	49
tf_agents/distributions/reparameterized_sampling.py	19
tf_agents/distributions/shifted_categorical.py	48
tf_agents/distributions/tanh_bijector_stable.py	27
tf_agents/distributions/utils.py	246
tf_agents/drivers/__init__.py	4
tf_agents/drivers/driver.py	26
tf_agents/drivers/dynamic_episode_driver.py	97
tf_agents/drivers/dynamic_step_driver.py	88
tf_agents/drivers/py_driver.py	53
tf_agents/drivers/tf_driver.py	55
tf_agents/environments/__init__.py	42
tf_agents/environments/atari_preprocessing.py	78
tf_agents/environments/atari_wrappers.py	60
tf_agents/environments/batched_py_environment.py	113
tf_agents/environments/dm_control_wrapper.py	65
tf_agents/environments/gym_wrapper.py	156
tf_agents/environments/parallel_py_environment.py	253
tf_agents/environments/py_environment.py	77
tf_agents/environments/random_py_environment.py	103
tf_agents/environments/random_tf_environment.py	61
tf_agents/environments/suite_atari.py	54
tf_agents/environments/suite_bsuite.py	35
tf_agents/environments/suite_dm_control.py	90
tf_agents/environments/suite_gym.py	63
tf_agents/environments/suite_mujoco.py	33
tf_agents/environments/suite_pybullet.py	5
tf_agents/environments/tf_environment.py	39
tf_agents/environments/tf_py_environment.py	185
tf_agents/environments/tf_wrappers.py	62
tf_agents/environments/trajectory_replay.py	114
tf_agents/environments/utils.py	54
tf_agents/environments/wrappers.py	586
tf_agents/eval/__init__.py	1
tf_agents/eval/metric_utils.py	85
tf_agents/experimental/__init__.py	2
tf_agents/experimental/distributed/__init__.py	1
tf_agents/experimental/distributed/reverb_variable_container.py	53
tf_agents/keras_layers/__init__.py	5
tf_agents/keras_layers/bias_layer.py	39
tf_agents/keras_layers/dynamic_unroll_layer.py	248
tf_agents/keras_layers/inner_reshape.py	40
tf_agents/keras_layers/permanent_variable_rate_dropout.py	24
tf_agents/keras_layers/rnn_wrapper.py	107
tf_agents/keras_layers/squashed_outer_wrapper.py	95
tf_agents/metrics/__init__.py	6
tf_agents/metrics/batched_py_metric.py	61
tf_agents/metrics/py_metric.py	101
tf_agents/metrics/py_metrics.py	166
tf_agents/metrics/tf_metric.py	111
tf_agents/metrics/tf_metrics.py	283
tf_agents/metrics/tf_py_metric.py	57
tf_agents/networks/__init__.py	21
tf_agents/networks/actor_distribution_network.py	103
tf_agents/networks/actor_distribution_rnn_network.py	85
tf_agents/networks/categorical_projection_network.py	73
tf_agents/networks/categorical_q_network.py	48
tf_agents/networks/encoding_network.py	157
tf_agents/networks/expand_dims_layer.py	31
tf_agents/networks/lstm_encoding_network.py	122
tf_agents/networks/mask_splitter_network.py	58
tf_agents/networks/nest_map.py	87
tf_agents/networks/network.py	311
tf_agents/networks/normal_projection_network.py	127
tf_agents/networks/q_network.py	64
tf_agents/networks/q_rnn_network.py	51
tf_agents/networks/sequential.py	158
tf_agents/networks/utils.py	114
tf_agents/networks/value_network.py	49
tf_agents/networks/value_rnn_network.py	54
tf_agents/policies/__init__.py	25
tf_agents/policies/actor_policy.py	101
tf_agents/policies/async_policy_saver.py	73
tf_agents/policies/batched_py_policy.py	114
tf_agents/policies/boltzmann_policy.py	41
tf_agents/policies/categorical_q_policy.py	89
tf_agents/policies/epsilon_greedy_policy.py	118
tf_agents/policies/fixed_policy.py	61
tf_agents/policies/gaussian_policy.py	49
tf_agents/policies/greedy_policy.py	42
tf_agents/policies/ou_noise_policy.py	56
tf_agents/policies/policy_info_updater_wrapper.py	49
tf_agents/policies/policy_loader.py	29
tf_agents/policies/policy_saver.py	387
tf_agents/policies/py_epsilon_greedy_policy.py	70
tf_agents/policies/py_policy.py	88
tf_agents/policies/py_tf_eager_policy.py	115
tf_agents/policies/py_tf_policy.py	148
tf_agents/policies/q_policy.py	93
tf_agents/policies/qtopt_cem_policy.py	300
tf_agents/policies/random_py_policy.py	73
tf_agents/policies/random_tf_policy.py	143
tf_agents/policies/samplers/cem_actions_sampler.py	30
tf_agents/policies/samplers/cem_actions_sampler_continuous.py	114
tf_agents/policies/samplers/cem_actions_sampler_continuous_and_one_hot.py	293
tf_agents/policies/samplers/cem_actions_sampler_hybrid.py	43
tf_agents/policies/scripted_py_policy.py	55
tf_agents/policies/temporal_action_smoothing.py	41
tf_agents/policies/tf_policy.py	252
tf_agents/policies/tf_py_policy.py	86
tf_agents/policies/utils.py	161
tf_agents/replay_buffers/__init__.py	11
tf_agents/replay_buffers/episodic_replay_buffer.py	726
tf_agents/replay_buffers/episodic_table.py	122
tf_agents/replay_buffers/py_hashed_replay_buffer.py	76
tf_agents/replay_buffers/py_uniform_replay_buffer.py	127
tf_agents/replay_buffers/replay_buffer.py	104
tf_agents/replay_buffers/reverb_replay_buffer.py	252
tf_agents/replay_buffers/reverb_utils.py	201
tf_agents/replay_buffers/table.py	51
tf_agents/replay_buffers/tf_uniform_replay_buffer.py	276
tf_agents/system/__init__.py	1
tf_agents/system/default/__init__.py	1
tf_agents/system/default/multiprocessing_core.py	40
tf_agents/system/system_multiprocessing.py	128
tf_agents/train/__init__.py	5
tf_agents/train/actor.py	127
tf_agents/train/interval_trigger.py	23
tf_agents/train/learner.py	238
tf_agents/train/ppo_learner.py	138
tf_agents/train/ppo_learner_test_utils.py	74
tf_agents/train/step_per_second_tracker.py	14
tf_agents/train/triggers.py	131
tf_agents/train/utils/__init__.py	1
tf_agents/train/utils/replay_buffer_utils.py	68
tf_agents/train/utils/spec_utils.py	17
tf_agents/train/utils/strategy_utils.py	22
tf_agents/train/utils/train_utils.py	96
tf_agents/trajectories/__init__.py	23
tf_agents/trajectories/policy_step.py	48
tf_agents/trajectories/time_step.py	235
tf_agents/trajectories/trajectory.py	349
tf_agents/typing/__init__.py	1
tf_agents/typing/types.py	75
tf_agents/utils/__init__.py	12
tf_agents/utils/common.py	627
tf_agents/utils/composite.py	99
tf_agents/utils/eager_utils.py	283
tf_agents/utils/example_encoding.py	143
tf_agents/utils/example_encoding_dataset.py	117
tf_agents/utils/lazy_loader.py	26
tf_agents/utils/nest_utils.py	584
tf_agents/utils/numpy_storage.py	91
tf_agents/utils/object_identity.py	121
tf_agents/utils/session_utils.py	21
tf_agents/utils/tensor_normalizer.py	225
tf_agents/utils/timer.py	20
tf_agents/utils/value_ops.py	63
tf_agents/utils/xla.py	43
tf_agents/version.py	12
tools/build_docs.py	52
tools/graph_builder.py	146
tools/release_builder.py	130