Path Lines of Code preprocessing/src/main/scala/com/facebook/spark/rl/Constants.scala 55 preprocessing/src/main/scala/com/facebook/spark/rl/Helper.scala 96 preprocessing/src/main/scala/com/facebook/spark/rl/MultiStepTimeline.scala 215 preprocessing/src/main/scala/com/facebook/spark/rl/Timeline.scala 302 preprocessing/src/main/scala/com/facebook/spark/rl/Udfs.scala 23 pyproject.toml 8 reagent/__init__.py 1 reagent/core/__init__.py 1 reagent/core/aggregators.py 144 reagent/core/base_dataclass.py 5 reagent/core/configuration.py 104 reagent/core/dataclasses.py 56 reagent/core/debug_on_error.py 12 reagent/core/fb_checker.py 8 reagent/core/multiprocess_utils.py 34 reagent/core/observers.py 78 reagent/core/oss_tensorboard_logger.py 112 reagent/core/parameters.py 152 reagent/core/parameters_seq2slate.py 33 reagent/core/registry_meta.py 72 reagent/core/report_utils.py 23 reagent/core/result_registries.py 10 reagent/core/result_types.py 8 reagent/core/running_stats.py 36 reagent/core/tagged_union.py 31 reagent/core/tensorboardX.py 76 reagent/core/torch_utils.py 51 reagent/core/tracker.py 85 reagent/core/types.py 852 reagent/core/utils.py 18 reagent/data/__init__.py 8 reagent/data/data_fetcher.py 25 reagent/data/manual_data_module.py 247 reagent/data/oss_data_fetcher.py 299 reagent/data/reagent_data_module.py 22 reagent/data/spark_utils.py 47 reagent/evaluation/__init__.py 1 reagent/evaluation/cpe.py 153 reagent/evaluation/doubly_robust_estimator.py 280 reagent/evaluation/evaluation_data_page.py 534 reagent/evaluation/evaluator.py 133 reagent/evaluation/feature_importance/__init__.py 1 reagent/evaluation/feature_importance/feature_importance_base.py 10 reagent/evaluation/feature_importance/feature_importance_perturbation.py 54 reagent/evaluation/ope_adapter.py 252 reagent/evaluation/sequential_doubly_robust_estimator.py 114 reagent/evaluation/weighted_sequential_doubly_robust_estimator.py 324 reagent/evaluation/world_model_evaluator.py 186 reagent/gym/__init__.py 3 reagent/gym/agents/__init__.py 1 reagent/gym/agents/agent.py 91 reagent/gym/agents/post_step.py 18 reagent/gym/datasets/__init__.py 1 reagent/gym/datasets/episodic_dataset.py 30 reagent/gym/datasets/replay_buffer_dataset.py 171 reagent/gym/envs/__init__.py 46 reagent/gym/envs/changing_arms.py 179 reagent/gym/envs/dynamics/__init__.py 1 reagent/gym/envs/dynamics/linear_dynamics.py 53 reagent/gym/envs/env_wrapper.py 109 reagent/gym/envs/functionality/__init__.py 1 reagent/gym/envs/functionality/possible_actions_mask_tester.py 33 reagent/gym/envs/gym.py 42 reagent/gym/envs/oracle_pvm.py 110 reagent/gym/envs/pomdp/__init__.py 1 reagent/gym/envs/pomdp/pocman.py 395 reagent/gym/envs/pomdp/state_embed_env.py 94 reagent/gym/envs/pomdp/string_game.py 89 reagent/gym/envs/pomdp/string_game_v1.py 81 reagent/gym/envs/recsim.py 109 reagent/gym/envs/toy_vm.py 106 reagent/gym/envs/utils.py 7 reagent/gym/envs/wrappers/__init__.py 1 reagent/gym/envs/wrappers/recsim.py 44 reagent/gym/envs/wrappers/simple_minigrid.py 25 reagent/gym/normalizers.py 47 reagent/gym/policies/__init__.py 2 reagent/gym/policies/policy.py 17 reagent/gym/policies/predictor_policies.py 109 reagent/gym/policies/random_policies.py 108 reagent/gym/policies/samplers/__init__.py 1 reagent/gym/policies/samplers/continuous_sampler.py 36 reagent/gym/policies/samplers/discrete_sampler.py 117 reagent/gym/policies/samplers/top_k_sampler.py 13 reagent/gym/policies/scorers/__init__.py 1 reagent/gym/policies/scorers/continuous_scorer.py 12 reagent/gym/policies/scorers/discrete_scorer.py 88 reagent/gym/policies/scorers/slate_q_scorer.py 39 reagent/gym/preprocessors/__init__.py 10 reagent/gym/preprocessors/default_preprocessors.py 92 reagent/gym/preprocessors/replay_buffer_inserters.py 157 reagent/gym/preprocessors/trainer_preprocessor.py 386 reagent/gym/runners/__init__.py 1 reagent/gym/runners/gymrunner.py 108 reagent/gym/types.py 94 reagent/gym/utils.py 331 reagent/lite/__init__.py 1 reagent/lite/optimizer.py 766 reagent/mab/__init__.py 1 reagent/mab/mab_algorithm.py 150 reagent/mab/simulation.py 160 reagent/mab/thompson_sampling.py 93 reagent/mab/ucb.py 82 reagent/model_managers/__init__.py 1 reagent/model_managers/actor_critic/__init__.py 3 reagent/model_managers/actor_critic/sac.py 102 reagent/model_managers/actor_critic/td3.py 92 reagent/model_managers/actor_critic_base.py 201 reagent/model_managers/discrete/__init__.py 5 reagent/model_managers/discrete/discrete_c51dqn.py 72 reagent/model_managers/discrete/discrete_crr.py 253 reagent/model_managers/discrete/discrete_dqn.py 169 reagent/model_managers/discrete/discrete_qrdqn.py 101 reagent/model_managers/discrete_dqn_base.py 171 reagent/model_managers/model_based/__init__.py 5 reagent/model_managers/model_based/cross_entropy_method.py 124 reagent/model_managers/model_based/seq2reward_model.py 47 reagent/model_managers/model_based/synthetic_reward.py 209 reagent/model_managers/model_based/world_model.py 43 reagent/model_managers/model_manager.py 122 reagent/model_managers/parametric/__init__.py 2 reagent/model_managers/parametric/parametric_dqn.py 65 reagent/model_managers/parametric_dqn_base.py 139 reagent/model_managers/policy_gradient/__init__.py 3 reagent/model_managers/policy_gradient/ppo.py 108 reagent/model_managers/policy_gradient/reinforce.py 110 reagent/model_managers/ranking/__init__.py 2 reagent/model_managers/ranking/slate_q.py 64 reagent/model_managers/slate_q_base.py 76 reagent/model_managers/union.py 35 reagent/model_managers/world_model_base.py 59 reagent/model_utils/__init__.py 1 reagent/model_utils/seq2slate_utils.py 102 reagent/models/__init__.py 33 reagent/models/actor.py 208 reagent/models/base.py 15 reagent/models/bcq.py 22 reagent/models/categorical_dqn.py 25 reagent/models/cem_planner.py 217 reagent/models/containers.py 12 reagent/models/convolutional_network.py 77 reagent/models/critic.py 48 reagent/models/dqn.py 44 reagent/models/dueling_q_network.py 193 reagent/models/embedding_bag_concat.py 75 reagent/models/fully_connected_network.py 118 reagent/models/linear_regression.py 46 reagent/models/mdn_rnn.py 135 reagent/models/mlp_scorer.py 27 reagent/models/model_feature_config_provider.py 13 reagent/models/no_soft_update_embedding.py 5 reagent/models/seq2reward_model.py 53 reagent/models/seq2slate.py 671 reagent/models/seq2slate_reward.py 313 reagent/models/synthetic_reward.py 355 reagent/models/world_model.py 46 reagent/net_builder/__init__.py 1 reagent/net_builder/categorical_dqn/__init__.py 1 reagent/net_builder/categorical_dqn/categorical.py 39 reagent/net_builder/categorical_dqn_net_builder.py 47 reagent/net_builder/continuous_actor/__init__.py 3 reagent/net_builder/continuous_actor/dirichlet_fully_connected.py 43 reagent/net_builder/continuous_actor/fully_connected.py 48 reagent/net_builder/continuous_actor/gaussian_fully_connected.py 67 reagent/net_builder/continuous_actor_net_builder.py 87 reagent/net_builder/discrete_actor/__init__.py 1 reagent/net_builder/discrete_actor/fully_connected.py 39 reagent/net_builder/discrete_actor_net_builder.py 39 reagent/net_builder/discrete_dqn/__init__.py 3 reagent/net_builder/discrete_dqn/dueling.py 27 reagent/net_builder/discrete_dqn/fully_connected.py 35 reagent/net_builder/discrete_dqn/fully_connected_with_embedding.py 42 reagent/net_builder/discrete_dqn_net_builder.py 73 reagent/net_builder/parametric_dqn/__init__.py 1 reagent/net_builder/parametric_dqn/fully_connected.py 41 reagent/net_builder/parametric_dqn_net_builder.py 40 reagent/net_builder/quantile_dqn/__init__.py 2 reagent/net_builder/quantile_dqn/dueling_quantile.py 30 reagent/net_builder/quantile_dqn/quantile.py 33 reagent/net_builder/quantile_dqn_net_builder.py 51 reagent/net_builder/slate_ranking/__init__.py 11 reagent/net_builder/slate_ranking/slate_ranking_scorer.py 76 reagent/net_builder/slate_ranking/slate_ranking_transformer.py 32 reagent/net_builder/slate_ranking_net_builder.py 8 reagent/net_builder/slate_reward/__init__.py 11 reagent/net_builder/slate_reward/slate_reward_gru.py 27 reagent/net_builder/slate_reward/slate_reward_transformer.py 31 reagent/net_builder/slate_reward_net_builder.py 11 reagent/net_builder/synthetic_reward/__init__.py 3 reagent/net_builder/synthetic_reward/ngram_synthetic_reward.py 88 reagent/net_builder/synthetic_reward/sequence_synthetic_reward.py 42 reagent/net_builder/synthetic_reward/single_step_synthetic_reward.py 44 reagent/net_builder/synthetic_reward/transformer_synthetic_reward.py 52 reagent/net_builder/synthetic_reward_net_builder.py 48 reagent/net_builder/unions.py 75 reagent/net_builder/value/__init__.py 2 reagent/net_builder/value/fully_connected.py 32 reagent/net_builder/value/seq2reward_rnn.py 24 reagent/net_builder/value_net_builder.py 9 reagent/ope/__init__.py 1 reagent/ope/datasets/__init__.py 1 reagent/ope/datasets/logged_dataset.py 30 reagent/ope/estimators/__init__.py 1 reagent/ope/estimators/contextual_bandits_estimators.py 571 reagent/ope/estimators/estimator.py 222 reagent/ope/estimators/sequential_estimators.py 624 reagent/ope/estimators/slate_estimators.py 1160 reagent/ope/estimators/types.py 433 reagent/ope/trainers/__init__.py 1 reagent/ope/trainers/linear_trainers.py 306 reagent/ope/trainers/rl_tabular_trainers.py 337 reagent/ope/utils.py 64 reagent/optimizer/__init__.py 3 reagent/optimizer/optimizer.py 31 reagent/optimizer/scheduler.py 26 reagent/optimizer/scheduler_union.py 42 reagent/optimizer/soft_update.py 43 reagent/optimizer/uninferrable_optimizers.py 71 reagent/optimizer/uninferrable_schedulers.py 86 reagent/optimizer/union.py 40 reagent/optimizer/utils.py 10 reagent/prediction/__init__.py 1 reagent/prediction/cfeval/predictor_wrapper.py 32 reagent/prediction/predictor_wrapper.py 671 reagent/prediction/ranking/__init__.py 1 reagent/prediction/ranking/predictor_wrapper.py 77 reagent/prediction/synthetic_reward/__init__.py 1 reagent/prediction/synthetic_reward/synthetic_reward_predictor_wrapper.py 52 reagent/preprocessing/__init__.py 1 reagent/preprocessing/batch_preprocessor.py 135 reagent/preprocessing/identify_types.py 53 reagent/preprocessing/normalization.py 250 reagent/preprocessing/postprocessor.py 57 reagent/preprocessing/preprocessor.py 486 reagent/preprocessing/sparse_preprocessor.py 151 reagent/preprocessing/sparse_to_dense.py 60 reagent/preprocessing/transforms.py 344 reagent/preprocessing/types.py 37 reagent/publishers/__init__.py 1 reagent/publishers/file_system_publisher.py 69 reagent/publishers/model_publisher.py 44 reagent/publishers/no_publishing.py 22 reagent/publishers/union.py 11 reagent/replay_memory/__init__.py 3 reagent/replay_memory/circular_replay_buffer.py 522 reagent/replay_memory/prioritized_replay_buffer.py 87 reagent/replay_memory/sum_tree.py 61 reagent/replay_memory/utils.py 53 reagent/reporting/__init__.py 6 reagent/reporting/actor_critic_reporter.py 53 reagent/reporting/compound_reporter.py 25 reagent/reporting/discrete_crr_reporter.py 96 reagent/reporting/discrete_dqn_reporter.py 96 reagent/reporting/parametric_dqn_reporter.py 49 reagent/reporting/reporter_base.py 54 reagent/reporting/reward_network_reporter.py 43 reagent/reporting/seq2reward_reporter.py 139 reagent/reporting/slate_q_reporter.py 42 reagent/reporting/td3_reporter.py 31 reagent/reporting/world_model_reporter.py 57 reagent/samplers/__init__.py 2 reagent/samplers/frechet.py 101 reagent/scripts/__init__.py 1 reagent/scripts/hparam_tuning.py 140 reagent/training/__init__.py 72 reagent/training/behavioral_cloning_trainer.py 67 reagent/training/c51_trainer.py 136 reagent/training/cb/__init__.py 1 reagent/training/cb/linucb_trainer.py 59 reagent/training/cem_trainer.py 30 reagent/training/cfeval/__init__.py 4 reagent/training/cfeval/bandit_reward_network_trainer.py 103 reagent/training/discrete_crr_trainer.py 269 reagent/training/dqn_trainer.py 234 reagent/training/dqn_trainer_base.py 254 reagent/training/gradient_free/__init__.py 1 reagent/training/gradient_free/ars_util.py 59 reagent/training/gradient_free/es_worker.py 42 reagent/training/gradient_free/evolution_pool.py 85 reagent/training/imitator_training.py 13 reagent/training/multi_stage_trainer.py 151 reagent/training/parameters.py 143 reagent/training/parametric_dqn_trainer.py 141 reagent/training/ppo_trainer.py 167 reagent/training/qrdqn_trainer.py 174 reagent/training/ranking/__init__.py 1 reagent/training/ranking/helper.py 12 reagent/training/ranking/seq2slate_attn_trainer.py 117 reagent/training/ranking/seq2slate_sim_trainer.py 145 reagent/training/ranking/seq2slate_tf_trainer.py 116 reagent/training/ranking/seq2slate_trainer.py 218 reagent/training/reagent_lightning_module.py 135 reagent/training/reinforce_trainer.py 106 reagent/training/reward_network_trainer.py 147 reagent/training/rl_trainer_pytorch.py 49 reagent/training/sac_trainer.py 281 reagent/training/slate_q_trainer.py 192 reagent/training/td3_trainer.py 136 reagent/training/utils.py 41 reagent/training/world_model/__init__.py 1 reagent/training/world_model/compress_model_trainer.py 93 reagent/training/world_model/mdnrnn_trainer.py 120 reagent/training/world_model/seq2reward_trainer.py 179 reagent/validators/__init__.py 1 reagent/validators/model_validator.py 31 reagent/validators/no_validation.py 15 reagent/validators/union.py 10 reagent/workflow/__init__.py 1 reagent/workflow/cli.py 55 reagent/workflow/env.py 16 reagent/workflow/gym_batch_rl.py 133 reagent/workflow/identify_types_flow.py 104 reagent/workflow/sample_configs/discrete_dqn_cartpole_offline.yaml 55 reagent/workflow/sample_configs/sac_pendulum_offline.yaml 65 reagent/workflow/training.py 261 reagent/workflow/training_reports.py 29 reagent/workflow/types.py 89 reagent/workflow/utils.py 115 serving/reagent/serving/cli/Main.cpp 28 serving/reagent/serving/cli/Server.cpp 57 serving/reagent/serving/cli/Server.h 20 serving/reagent/serving/config/applications/__init__.py 7 serving/reagent/serving/config/applications/example/__init__.py 1 serving/reagent/serving/config/applications/example/example.py 39 serving/reagent/serving/config/builder.py 76 serving/reagent/serving/config/config.py 83 serving/reagent/serving/config/main.py 41 serving/reagent/serving/config/namespace.py 16 serving/reagent/serving/config/operators.py 24 serving/reagent/serving/config/serialize.py 91 serving/reagent/serving/core/ActionValueScorer.cpp 1 serving/reagent/serving/core/ActionValueScorer.h 10 serving/reagent/serving/core/ConfigProvider.cpp 1 serving/reagent/serving/core/ConfigProvider.h 16 serving/reagent/serving/core/Containers.cpp 78 serving/reagent/serving/core/Containers.h 229 serving/reagent/serving/core/DecisionPlan.cpp 22 serving/reagent/serving/core/DecisionPlan.h 27 serving/reagent/serving/core/DecisionService.cpp 130 serving/reagent/serving/core/DecisionService.h 54 serving/reagent/serving/core/DecisionServiceException.cpp 1 serving/reagent/serving/core/DecisionServiceException.h 11 serving/reagent/serving/core/DiskConfigProvider.cpp 44 serving/reagent/serving/core/DiskConfigProvider.h 15 serving/reagent/serving/core/Headers.cpp 50 serving/reagent/serving/core/Headers.h 39 serving/reagent/serving/core/InMemoryLogJoiner.cpp 44 serving/reagent/serving/core/InMemoryLogJoiner.h 38 serving/reagent/serving/core/LocalRealTimeCounter.cpp 52 serving/reagent/serving/core/LocalRealTimeCounter.h 18 serving/reagent/serving/core/LogJoiner.cpp 31 serving/reagent/serving/core/LogJoiner.h 23 serving/reagent/serving/core/Operator.cpp 20 serving/reagent/serving/core/Operator.h 58 serving/reagent/serving/core/OperatorFactory.cpp 39 serving/reagent/serving/core/OperatorFactory.h 45 serving/reagent/serving/core/OperatorRunner.cpp 64 serving/reagent/serving/core/OperatorRunner.h 15 serving/reagent/serving/core/PytorchActionValueScorer.cpp 80 serving/reagent/serving/core/PytorchActionValueScorer.h 14 serving/reagent/serving/core/RealTimeCounter.cpp 1 serving/reagent/serving/core/RealTimeCounter.h 13 serving/reagent/serving/core/SharedParameterHandler.cpp 23 serving/reagent/serving/core/SharedParameterHandler.h 39 serving/reagent/serving/operators/ActionValueScoring.cpp 18 serving/reagent/serving/operators/ActionValueScoring.h 21 serving/reagent/serving/operators/EpsilonGreedyRanker.cpp 43 serving/reagent/serving/operators/EpsilonGreedyRanker.h 25 serving/reagent/serving/operators/Expression.cpp 49 serving/reagent/serving/operators/Expression.h 22 serving/reagent/serving/operators/Frechet.cpp 37 serving/reagent/serving/operators/Frechet.h 21 serving/reagent/serving/operators/InputFromRequest.cpp 10 serving/reagent/serving/operators/InputFromRequest.h 19 serving/reagent/serving/operators/PropensityFit.cpp 92 serving/reagent/serving/operators/PropensityFit.h 33 serving/reagent/serving/operators/Softmax.cpp 30 serving/reagent/serving/operators/Softmax.h 20 serving/reagent/serving/operators/SoftmaxRanker.cpp 52 serving/reagent/serving/operators/SoftmaxRanker.h 17 serving/reagent/serving/operators/Ucb.cpp 94 serving/reagent/serving/operators/Ucb.h 26 serving/scripts/__init__.py 1 serving/scripts/rasp_to_model.py 40 serving/setup.py 16 setup.cfg 54 setup.py 2