.gitignore
.gitmodules
.isort.cfg
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
README.md
pyproject.toml
rasp_requirements.txt
requirements.txt
setup.cfg
setup.py
tox.ini
.circleci/config.yml
docs/build.sh
docs/conf.py
docs/continuous_integration.rst
docs/distributed.rst
docs/index.rst
docs/installation.rst
docs/license.rst
docs/rasp_tutorial.rst
docs/usage.rst
docs/_static/empty
docs/api/ml.rl.evaluation.rst
docs/api/ml.rl.models.rst
docs/api/ml.rl.prediction.rst
docs/api/ml.rl.preprocessing.rst
docs/api/ml.rl.readers.rst
docs/api/ml.rl.rst
docs/api/ml.rl.simulators.rst
docs/api/ml.rl.training.gradient_free.rst
docs/api/ml.rl.training.ranking.rst
docs/api/ml.rl.training.rst
docs/api/ml.rl.training.world_model.rst
docs/api/ml.rl.workflow.rst
docs/api/ml.rst
docs/api/modules.rst
logo/horizon_banner.png
logo/horizon_logo.png
logo/horizon_logo_256.png
logo/horizon_logo_inverted.png
logo/reagent_banner.png
logo/reagent_logo.png
preprocessing/pom.xml
preprocessing/src/main/scala/com/facebook/spark/rl/Constants.scala
preprocessing/src/main/scala/com/facebook/spark/rl/Helper.scala
preprocessing/src/main/scala/com/facebook/spark/rl/MultiStepTimeline.scala
preprocessing/src/main/scala/com/facebook/spark/rl/Timeline.scala
preprocessing/src/main/scala/com/facebook/spark/rl/Udfs.scala
preprocessing/src/test/scala/com/facebook/spark/common/testutil/PipelineTester.scala
preprocessing/src/test/scala/com/facebook/spark/common/testutil/TestLogger.scala
preprocessing/src/test/scala/com/facebook/spark/common/testutil/TestLogging.scala
preprocessing/src/test/scala/com/facebook/spark/rl/TimelineTest.scala
reagent/__init__.py
reagent/debug_on_error.py
reagent/json_serialize.py
reagent/parameters.py
reagent/parameters_seq2slate.py
reagent/tensorboardX.py
reagent/torch_utils.py
reagent/types.py
reagent.egg-info/PKG-INFO
reagent.egg-info/SOURCES.txt
reagent.egg-info/dependency_links.txt
reagent.egg-info/requires.txt
reagent.egg-info/top_level.txt
reagent/core/aggregators.py
reagent/core/configuration.py
reagent/core/dataclasses.py
reagent/core/observers.py
reagent/core/registry_meta.py
reagent/core/report_utils.py
reagent/core/tagged_union.py
reagent/core/tracker.py
reagent/evaluation/__init__.py
reagent/evaluation/cpe.py
reagent/evaluation/doubly_robust_estimator.py
reagent/evaluation/evaluation_data_page.py
reagent/evaluation/evaluator.py
reagent/evaluation/ranking_listwise_evaluator.py
reagent/evaluation/ranking_policy_gradient_evaluator.py
reagent/evaluation/reward_net_evaluator.py
reagent/evaluation/sequential_doubly_robust_estimator.py
reagent/evaluation/weighted_sequential_doubly_robust_estimator.py
reagent/evaluation/world_model_evaluator.py
reagent/gym/__init__.py
reagent/gym/types.py
reagent/gym/utils.py
reagent/gym/agents/__init__.py
reagent/gym/agents/agent.py
reagent/gym/agents/post_step.py
reagent/gym/envs/__init__.py
reagent/gym/envs/env_factory.py
reagent/gym/envs/recsim.py
reagent/gym/envs/simple_minigrid.py
reagent/gym/envs/utils.py
reagent/gym/policies/__init__.py
reagent/gym/policies/policy.py
reagent/gym/policies/predictor_policies.py
reagent/gym/policies/random_policies.py
reagent/gym/policies/samplers/__init__.py
reagent/gym/policies/samplers/continuous_sampler.py
reagent/gym/policies/samplers/discrete_sampler.py
reagent/gym/policies/samplers/top_k_sampler.py
reagent/gym/policies/scorers/__init__.py
reagent/gym/policies/scorers/continuous_scorer.py
reagent/gym/policies/scorers/discrete_scorer.py
reagent/gym/policies/scorers/slate_q_scorer.py
reagent/gym/preprocessors/__init__.py
reagent/gym/preprocessors/default_preprocessors.py
reagent/gym/preprocessors/default_serving_preprocessors.py
reagent/gym/preprocessors/replay_buffer_inserters.py
reagent/gym/preprocessors/trainer_preprocessor.py
reagent/gym/runners/__init__.py
reagent/gym/runners/gymrunner.py
reagent/gym/tests/__init__.py
reagent/gym/tests/test_gym.py
reagent/gym/tests/test_gym_offline.py
reagent/gym/tests/test_linear_dynamics.py
reagent/gym/tests/test_pomdp.py
reagent/gym/tests/test_world_model.py
reagent/gym/tests/configs/cartpole/discrete_dqn_cartpole_online.yaml
reagent/gym/tests/configs/open_gridworld/discrete_dqn_open_gridworld.yaml
reagent/gym/tests/preprocessors/__init__.py
reagent/gym/tests/preprocessors/test_default_preprocessors.py
reagent/gym/tests/preprocessors/test_replay_buffer_inserters.py
reagent/models/__init__.py
reagent/models/actor.py
reagent/models/base.py
reagent/models/bcq.py
reagent/models/categorical_dqn.py
reagent/models/cem_planner.py
reagent/models/containers.py
reagent/models/convolutional_network.py
reagent/models/critic.py
reagent/models/dqn.py
reagent/models/dueling_q_network.py
reagent/models/embedding_bag_concat.py
reagent/models/fully_connected_network.py
reagent/models/mdn_rnn.py
reagent/models/no_soft_update_embedding.py
reagent/models/seq2slate.py
reagent/models/seq2slate_reward.py
reagent/models/world_model.py
reagent/net_builder/categorical_dqn_net_builder.py
reagent/net_builder/continuous_actor_net_builder.py
reagent/net_builder/discrete_dqn_net_builder.py
reagent/net_builder/parametric_dqn_net_builder.py
reagent/net_builder/quantile_dqn_net_builder.py
reagent/net_builder/unions.py
reagent/net_builder/value_net_builder.py
reagent/net_builder/categorical_dqn/__init__.py
reagent/net_builder/categorical_dqn/categorical.py
reagent/net_builder/continuous_actor/__init__.py
reagent/net_builder/continuous_actor/dirichlet_fully_connected.py
reagent/net_builder/continuous_actor/gaussian_fully_connected.py
reagent/net_builder/discrete_dqn/__init__.py
reagent/net_builder/discrete_dqn/dueling.py
reagent/net_builder/discrete_dqn/fully_connected.py
reagent/net_builder/discrete_dqn/fully_connected_with_embedding.py
reagent/net_builder/parametric_dqn/__init__.py
reagent/net_builder/parametric_dqn/fully_connected.py
reagent/net_builder/quantile_dqn/__init__.py
reagent/net_builder/quantile_dqn/dueling_quantile.py
reagent/net_builder/quantile_dqn/quantile.py
reagent/net_builder/value/__init__.py
reagent/net_builder/value/fully_connected.py
reagent/ope/__init__.py
reagent/ope/utils.py
reagent/ope/datasets/__init__.py
reagent/ope/datasets/logged_dataset.py
reagent/ope/estimators/__init__.py
reagent/ope/estimators/contextual_bandits_estimators.py
reagent/ope/estimators/estimator.py
reagent/ope/estimators/sequential_estimators.py
reagent/ope/estimators/slate_estimators.py
reagent/ope/estimators/types.py
reagent/ope/test/__init__.py
reagent/ope/test/envs.py
reagent/ope/test/gridworld.py
reagent/ope/test/mslr_slate.py
reagent/ope/test/multiclass_bandits.py
reagent/ope/test/yandex_web_search.py
reagent/ope/test/configs/ecoli_config.json
reagent/ope/test/configs/letter_recog_config.json
reagent/ope/test/configs/mslr_web30k_config.json
reagent/ope/test/configs/pendigits_config.json
reagent/ope/test/configs/yandex_web_search_config.json
reagent/ope/test/data/ecoli.data
reagent/ope/test/data/ecoli.names
reagent/ope/test/data/letter-recognition.data
reagent/ope/test/data/letter-recognition.names
reagent/ope/test/data/pendigits.data
reagent/ope/test/data/pendigits.names
reagent/ope/test/unit_tests/__init__.py
reagent/ope/test/unit_tests/test_slate_estimators.py
reagent/ope/test/unit_tests/test_types.py
reagent/ope/test/unit_tests/test_utils.py
reagent/ope/trainers/__init__.py
reagent/ope/trainers/linear_trainers.py
reagent/ope/trainers/rl_tabular_trainers.py
reagent/prediction/__init__.py
reagent/prediction/dqn_torch_predictor.py
reagent/prediction/predictor_wrapper.py
reagent/preprocessing/__init__.py
reagent/preprocessing/batch_preprocessor.py
reagent/preprocessing/identify_types.py
reagent/preprocessing/normalization.py
reagent/preprocessing/postprocessor.py
reagent/preprocessing/preprocessor.py
reagent/preprocessing/sparse_to_dense.py
reagent/preprocessing/transforms.py
reagent/replay_memory/__init__.py
reagent/replay_memory/circular_replay_buffer.py
reagent/replay_memory/prioritized_replay_buffer.py
reagent/replay_memory/sum_tree.py
reagent/replay_memory/utils.py
reagent/test/__init__.py
reagent/test/base/__init__.py
reagent/test/base/horizon_test_base.py
reagent/test/base/test_json_serialize.py
reagent/test/base/test_tensorboardX.py
reagent/test/base/test_utils.py
reagent/test/base/utils.py
reagent/test/configs/cem_cartpole_v0.json
reagent/test/configs/cem_linear_dynamics_v0.json
reagent/test/configs/discrete_dqn_pocman_v0.json
reagent/test/configs/discrete_dqn_string_game_v0.json
reagent/test/configs/mdnrnn_cartpole_v0.json
reagent/test/configs/mdnrnn_lunarlander_v2.json
reagent/test/configs/mdnrnn_pocman_v0.json
reagent/test/configs/mdnrnn_string_game_v0.json
reagent/test/core/__init__.py
reagent/test/core/aggregators_test.py
reagent/test/core/test_config_parsing.py
reagent/test/core/tracker_test.py
reagent/test/environment/__init__.py
reagent/test/environment/environment.py
reagent/test/environment/test_environment.py
reagent/test/evaluation/__init__.py
reagent/test/evaluation/test_evaluation_data_page.py
reagent/test/gridworld/__init__.py
reagent/test/gridworld/gridworld.py
reagent/test/gridworld/gridworld_base.py
reagent/test/gridworld/gridworld_continuous.py
reagent/test/gridworld/gridworld_evaluator.py
reagent/test/gridworld/gridworld_test_base.py
reagent/test/gridworld/test_gridworld_cpe.py
reagent/test/gridworld/test_gridworld_pytorch.py
reagent/test/gym/__init__.py
reagent/test/gym/c51_cartpole_v0.json
reagent/test/gym/discrete_dqn_cartpole_small_v0.json
reagent/test/gym/discrete_dqn_cartpole_v0.json
reagent/test/gym/discrete_dqn_lunarlander_v2.json
reagent/test/gym/discrete_dqn_maxq_asteroids_v0.json
reagent/test/gym/discrete_qlearn_maxq_cartpole_v0.json
reagent/test/gym/discrete_qlearn_softmax_cartpole_v0.json
reagent/test/gym/discrete_rainbow_dqn_cartpole_v0.json
reagent/test/gym/discrete_sarsa_softmax_cartpole_v0.json
reagent/test/gym/gym_evaluator.py
reagent/test/gym/maxq_asteroids_v0.json
reagent/test/gym/maxq_lunarlander_v2.json
reagent/test/gym/open_ai_gym_environment.py
reagent/test/gym/parametric_dqn_cartpole_v0.json
reagent/test/gym/parametric_qlearn_softmax_cartpole_v0.json
reagent/test/gym/parametric_rainbow_dqn_cartpole_v0.json
reagent/test/gym/parametric_sarsa_softmax_cartpole_v0.json
reagent/test/gym/qrdqn_cartpole_v0.json
reagent/test/gym/sac_pendulum_v0.json
reagent/test/gym/td3_pendulum_v0.json
reagent/test/models/__init__.py
reagent/test/models/test_actor.py
reagent/test/models/test_base.py
reagent/test/models/test_bcq.py
reagent/test/models/test_critic.py
reagent/test/models/test_dqn.py
reagent/test/models/test_dueling_q_network.py
reagent/test/models/test_no_soft_update_embedding.py
reagent/test/models/test_utils.py
reagent/test/net_builder/__init__.py
reagent/test/net_builder/test_continuous_actor_net_builder.py
reagent/test/net_builder/test_discrete_dqn_net_builder.py
reagent/test/net_builder/test_parametric_dqn_net_builder.py
reagent/test/net_builder/test_value_net_builder.py
reagent/test/prediction/__init__.py
reagent/test/prediction/test_predictor_wrapper.py
reagent/test/preprocessing/__init__.py
reagent/test/preprocessing/preprocessing_util.py
reagent/test/preprocessing/test_postprocessing.py
reagent/test/preprocessing/test_preprocessing.py
reagent/test/preprocessing/test_sparse_to_dense.py
reagent/test/preprocessing/test_type_identification.py
reagent/test/replay_memory/__init__.py
reagent/test/replay_memory/circular_replay_buffer_test.py
reagent/test/replay_memory/create_from_env_test.py
reagent/test/replay_memory/prioritized_replay_buffer_test.py
reagent/test/replay_memory/sum_tree_test.py
reagent/test/simulators/__init__.py
reagent/test/workflow/__init__.py
reagent/test/workflow/reagent_sql_test_base.py
reagent/test/workflow/test_oss_workflows.py
reagent/test/workflow/test_preprocessing.py
reagent/test/workflow/test_query_data.py
reagent/test/workflow/test_query_data_parametric.py
reagent/test/workflow/test_data/continuous_action/action_norm.json
reagent/test/workflow/test_data/continuous_action/pendulum_eval.json.bz2
reagent/test/workflow/test_data/continuous_action/pendulum_training.json.bz2
reagent/test/workflow/test_data/continuous_action/state_features_norm.json
reagent/test/workflow/test_data/discrete_action/cartpole_norm.json
reagent/test/workflow/test_data/discrete_action/dqn_workflow.zip
reagent/test/workflow/test_data/parametric_action/action_norm.json
reagent/test/workflow/test_data/parametric_action/cartpole_eval.json.bz2
reagent/test/workflow/test_data/parametric_action/cartpole_training.json.bz2
reagent/test/workflow/test_data/parametric_action/cartpole_training_data.json
reagent/test/workflow/test_data/parametric_action/state_features_norm.json
reagent/test/world_model/__init__.py
reagent/test/world_model/simulated_world_model.py
reagent/test/world_model/test_mdnrnn.py
reagent/training/__init__.py
reagent/training/c51_trainer.py
reagent/training/cem_trainer.py
reagent/training/dqn_trainer.py
reagent/training/dqn_trainer_base.py
reagent/training/imitator_training.py
reagent/training/loss_reporter.py
reagent/training/on_policy_predictor.py
reagent/training/parametric_dqn_trainer.py
reagent/training/qrdqn_trainer.py
reagent/training/reward_network_trainer.py
reagent/training/rl_dataset.py
reagent/training/rl_trainer_pytorch.py
reagent/training/sac_trainer.py
reagent/training/slate_q_trainer.py
reagent/training/td3_trainer.py
reagent/training/trainer.py
reagent/training/training_data_page.py
reagent/training/utils.py
reagent/training/gradient_free/__init__.py
reagent/training/gradient_free/es_worker.py
reagent/training/gradient_free/evolution_pool.py
reagent/training/ranking/__init__.py
reagent/training/ranking/seq2slate_attn_trainer.py
reagent/training/ranking/seq2slate_dr_trainer.py
reagent/training/ranking/seq2slate_sim_trainer.py
reagent/training/ranking/seq2slate_tf_trainer.py
reagent/training/ranking/seq2slate_trainer.py
reagent/training/world_model/__init__.py
reagent/training/world_model/mdnrnn_trainer.py
reagent/workflow/__init__.py
reagent/workflow/cli.py
reagent/workflow/data_fetcher.py
reagent/workflow/env.py
reagent/workflow/gym_batch_rl.py
reagent/workflow/helpers.py
reagent/workflow/identify_types_flow.py
reagent/workflow/predictor_policies.py
reagent/workflow/result_registries.py
reagent/workflow/result_types.py
reagent/workflow/spark_utils.py
reagent/workflow/tagged_union.py
reagent/workflow/training.py
reagent/workflow/training_reports.py
reagent/workflow/types.py
reagent/workflow/utils.py
reagent/workflow/model_managers/discrete_dqn_base.py
reagent/workflow/model_managers/model_manager.py
reagent/workflow/model_managers/union.py
reagent/workflow/model_managers/discrete/__init__.py
reagent/workflow/model_managers/discrete/discrete_c51dqn.py
reagent/workflow/model_managers/discrete/discrete_dqn.py
reagent/workflow/model_managers/discrete/discrete_qrdqn.py
reagent/workflow/publishers/model_publisher.py
reagent/workflow/publishers/no_publishing.py
reagent/workflow/publishers/union.py
reagent/workflow/reporters/discrete_dqn_reporter.py
reagent/workflow/sample_configs/gridworld_dqn.yaml
reagent/workflow/sample_configs/parametric_dqn_example.json
reagent/workflow/sample_configs/continuous_action/timeline.json
reagent/workflow/sample_configs/discrete_action/dqn_example.json
reagent/workflow/sample_configs/discrete_action/timeline.json
reagent/workflow/sample_configs/parametric_action/parametric_dqn_example.json
reagent/workflow/sample_configs/parametric_action/timeline.json
reagent/workflow/validators/model_validator.py
reagent/workflow/validators/no_validation.py
reagent/workflow/validators/union.py
reagent/workflow_utils/page_handler.py
serving/CMakeLists.txt
serving/README.md
serving/requirements.txt
serving/setup.py
serving/examples/ecommerce/customer_simulator.py
serving/examples/ecommerce/plans/contextual_bandit.json
serving/examples/ecommerce/plans/heuristic.json
serving/examples/ecommerce/plans/multi_armed_bandit.json
serving/examples/ecommerce/training/cb_train.json
serving/examples/ecommerce/training/contextual_bandit.json
serving/examples/ecommerce/training/timeline.json
serving/reagent/serving/cli/Main.cpp
serving/reagent/serving/cli/Server.cpp
serving/reagent/serving/cli/Server.h
serving/reagent/serving/config/builder.py
serving/reagent/serving/config/config.py
serving/reagent/serving/config/main.py
serving/reagent/serving/config/namespace.py
serving/reagent/serving/config/operators.py
serving/reagent/serving/config/serialize.py
serving/reagent/serving/config/applications/__init__.py
serving/reagent/serving/config/applications/example/__init__.py
serving/reagent/serving/config/applications/example/example.py
serving/reagent/serving/core/ActionValueScorer.cpp
serving/reagent/serving/core/ActionValueScorer.h
serving/reagent/serving/core/ConfigProvider.cpp
serving/reagent/serving/core/ConfigProvider.h
serving/reagent/serving/core/Containers.cpp
serving/reagent/serving/core/Containers.h
serving/reagent/serving/core/DecisionPlan.cpp
serving/reagent/serving/core/DecisionPlan.h
serving/reagent/serving/core/DecisionService.cpp
serving/reagent/serving/core/DecisionService.h
serving/reagent/serving/core/DecisionServiceException.cpp
serving/reagent/serving/core/DecisionServiceException.h
serving/reagent/serving/core/DiskConfigProvider.cpp
serving/reagent/serving/core/DiskConfigProvider.h
serving/reagent/serving/core/Headers.cpp
serving/reagent/serving/core/Headers.h
serving/reagent/serving/core/InMemoryLogJoiner.cpp
serving/reagent/serving/core/InMemoryLogJoiner.h
serving/reagent/serving/core/LocalRealTimeCounter.cpp
serving/reagent/serving/core/LocalRealTimeCounter.h
serving/reagent/serving/core/LogJoiner.cpp
serving/reagent/serving/core/LogJoiner.h
serving/reagent/serving/core/Operator.cpp
serving/reagent/serving/core/Operator.h
serving/reagent/serving/core/OperatorFactory.cpp
serving/reagent/serving/core/OperatorFactory.h
serving/reagent/serving/core/OperatorRunner.cpp
serving/reagent/serving/core/OperatorRunner.h
serving/reagent/serving/core/PytorchActionValueScorer.cpp
serving/reagent/serving/core/PytorchActionValueScorer.h
serving/reagent/serving/core/RealTimeCounter.cpp
serving/reagent/serving/core/RealTimeCounter.h
serving/reagent/serving/core/SharedParameterHandler.cpp
serving/reagent/serving/core/SharedParameterHandler.h
serving/reagent/serving/operators/ActionValueScoring.cpp
serving/reagent/serving/operators/ActionValueScoring.h
serving/reagent/serving/operators/EpsilonGreedyRanker.cpp
serving/reagent/serving/operators/EpsilonGreedyRanker.h
serving/reagent/serving/operators/Expression.cpp
serving/reagent/serving/operators/Expression.h
serving/reagent/serving/operators/Frechet.cpp
serving/reagent/serving/operators/Frechet.h
serving/reagent/serving/operators/InputFromRequest.cpp
serving/reagent/serving/operators/InputFromRequest.h
serving/reagent/serving/operators/PropensityFit.cpp
serving/reagent/serving/operators/PropensityFit.h
serving/reagent/serving/operators/Softmax.cpp
serving/reagent/serving/operators/Softmax.h
serving/reagent/serving/operators/SoftmaxRanker.cpp
serving/reagent/serving/operators/SoftmaxRanker.h
serving/reagent/serving/operators/Ucb.cpp
serving/reagent/serving/operators/Ucb.h
serving/reagent/serving/test/DecisionService_test.cpp
serving/reagent/serving/test/EpsilonGreedyRanker_test.cpp
serving/reagent/serving/test/Expression_test.cpp
serving/reagent/serving/test/Frechet_test.cpp
serving/reagent/serving/test/InMemoryLogJoiner_test.cpp
serving/reagent/serving/test/InputFromRequest_test.cpp
serving/reagent/serving/test/PlanProvider_test.cpp
serving/reagent/serving/test/PropensityFit_test.cpp
serving/reagent/serving/test/PytorchScoring_test.cpp
serving/reagent/serving/test/SoftmaxRanker_test.cpp
serving/reagent/serving/test/Softmax_test.cpp
serving/reagent/serving/test/TestHeaders.cpp
serving/reagent/serving/test/TestHeaders.h
serving/reagent/serving/test/Ucb_test.cpp
serving/scripts/rasp_to_model.py