├── .flake8 ├── .github └── workflows │ └── python-package.yml ├── .gitignore ├── CODE_OF_CONDUCT.md ├── LICENSE ├── README.md ├── SECURITY.md ├── SUPPORT.md ├── examples ├── cartpole │ ├── box_encoder.py │ ├── concatenate_multiple_datasets.py │ ├── ppo_agent_rollout.py │ ├── ppo_revealed_rollout.py │ └── psrs_from_expert_heuristic.py └── continuous_grid │ ├── random_agent_rollout.py │ ├── run.sh │ └── train_homer_encoder.py ├── offsim4rl ├── __init__.py ├── agents │ ├── __init__.py │ ├── agent.py │ ├── discrete_random.py │ ├── ppo.py │ └── tabular.py ├── core.py ├── data.py ├── encoders │ ├── __init__.py │ ├── heuristic.py │ ├── homer.py │ └── models.py ├── envs │ ├── __init__.py │ └── gridworld.py ├── evaluators │ ├── __init__.py │ ├── per_state_rejection.py │ ├── psrs.py │ ├── queue_evaluator.py │ └── trivial_baselines.py └── utils │ ├── __init__.py │ ├── dataset_utils.py │ ├── prob_utils.py │ ├── tb_utils.py │ └── vis_utils.py ├── requirements.txt ├── setup.py └── tests ├── __init__.py ├── test_agents.py ├── test_core.py ├── test_data.py ├── test_dataset_utils.py ├── test_e2e.py ├── test_gym.py ├── test_per_state_rejection.py ├── test_psrs.py ├── test_spinup.py └── test_trivial_baselines.py /.flake8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/.flake8 -------------------------------------------------------------------------------- /.github/workflows/python-package.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/.github/workflows/python-package.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/.gitignore -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/README.md -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/SECURITY.md -------------------------------------------------------------------------------- /SUPPORT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/SUPPORT.md -------------------------------------------------------------------------------- /examples/cartpole/box_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/examples/cartpole/box_encoder.py -------------------------------------------------------------------------------- /examples/cartpole/concatenate_multiple_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/examples/cartpole/concatenate_multiple_datasets.py -------------------------------------------------------------------------------- /examples/cartpole/ppo_agent_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/examples/cartpole/ppo_agent_rollout.py -------------------------------------------------------------------------------- /examples/cartpole/ppo_revealed_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/examples/cartpole/ppo_revealed_rollout.py -------------------------------------------------------------------------------- /examples/cartpole/psrs_from_expert_heuristic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/examples/cartpole/psrs_from_expert_heuristic.py -------------------------------------------------------------------------------- /examples/continuous_grid/random_agent_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/examples/continuous_grid/random_agent_rollout.py -------------------------------------------------------------------------------- /examples/continuous_grid/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/examples/continuous_grid/run.sh -------------------------------------------------------------------------------- /examples/continuous_grid/train_homer_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/examples/continuous_grid/train_homer_encoder.py -------------------------------------------------------------------------------- /offsim4rl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/__init__.py -------------------------------------------------------------------------------- /offsim4rl/agents/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /offsim4rl/agents/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/agents/agent.py -------------------------------------------------------------------------------- /offsim4rl/agents/discrete_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/agents/discrete_random.py -------------------------------------------------------------------------------- /offsim4rl/agents/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/agents/ppo.py -------------------------------------------------------------------------------- /offsim4rl/agents/tabular.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/agents/tabular.py -------------------------------------------------------------------------------- /offsim4rl/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/core.py -------------------------------------------------------------------------------- /offsim4rl/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/data.py -------------------------------------------------------------------------------- /offsim4rl/encoders/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /offsim4rl/encoders/heuristic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/encoders/heuristic.py -------------------------------------------------------------------------------- /offsim4rl/encoders/homer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/encoders/homer.py -------------------------------------------------------------------------------- /offsim4rl/encoders/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/encoders/models.py -------------------------------------------------------------------------------- /offsim4rl/envs/__init__.py: -------------------------------------------------------------------------------- 1 | from offsim4rl.envs.gridworld import MyGridNaviCoords 2 | -------------------------------------------------------------------------------- /offsim4rl/envs/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/envs/gridworld.py -------------------------------------------------------------------------------- /offsim4rl/evaluators/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /offsim4rl/evaluators/per_state_rejection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/evaluators/per_state_rejection.py -------------------------------------------------------------------------------- /offsim4rl/evaluators/psrs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/evaluators/psrs.py -------------------------------------------------------------------------------- /offsim4rl/evaluators/queue_evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/evaluators/queue_evaluator.py -------------------------------------------------------------------------------- /offsim4rl/evaluators/trivial_baselines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/evaluators/trivial_baselines.py -------------------------------------------------------------------------------- /offsim4rl/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /offsim4rl/utils/dataset_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/utils/dataset_utils.py -------------------------------------------------------------------------------- /offsim4rl/utils/prob_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/utils/prob_utils.py -------------------------------------------------------------------------------- /offsim4rl/utils/tb_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/utils/tb_utils.py -------------------------------------------------------------------------------- /offsim4rl/utils/vis_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/offsim4rl/utils/vis_utils.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/setup.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/test_agents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_agents.py -------------------------------------------------------------------------------- /tests/test_core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_core.py -------------------------------------------------------------------------------- /tests/test_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_data.py -------------------------------------------------------------------------------- /tests/test_dataset_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_dataset_utils.py -------------------------------------------------------------------------------- /tests/test_e2e.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_e2e.py -------------------------------------------------------------------------------- /tests/test_gym.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_gym.py -------------------------------------------------------------------------------- /tests/test_per_state_rejection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_per_state_rejection.py -------------------------------------------------------------------------------- /tests/test_psrs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_psrs.py -------------------------------------------------------------------------------- /tests/test_spinup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_spinup.py -------------------------------------------------------------------------------- /tests/test_trivial_baselines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/microsoft/rl-offline-simulation/HEAD/tests/test_trivial_baselines.py --------------------------------------------------------------------------------