├── .circleci └── config.yml ├── .codecov.yml ├── .coveragerc ├── .dockerignore ├── .gitattributes ├── .github ├── ISSUE_TEMPLATE │ ├── bug_report.md │ └── feature_request.md ├── pull_request_template.md └── workflows │ └── publish-to-pypi.yml ├── .gitignore ├── .pre-commit-config.yaml ├── .readthedocs.yml ├── CITATION.bib ├── Dockerfile ├── LICENSE ├── README.md ├── benchmarking ├── README.md ├── compute_probability_of_improvement.py ├── run_all_benchmarks.sh ├── run_all_benchmarks_on_slurm.sh ├── run_benchmark_on_slurm.sh ├── sacred_output_to_csv.py ├── sacred_output_to_markdown_summary.py └── util.py ├── ci ├── Xdummy-entrypoint.py ├── build_and_activate_venv.ps1 ├── build_and_activate_venv.sh ├── check_typeignore.py ├── clean_notebooks.py └── xorg.conf ├── docs ├── .gitignore ├── Makefile ├── _static │ └── css │ │ └── custom.css ├── _templates │ └── autosummary │ │ ├── base.rst │ │ ├── class.rst │ │ └── module.rst ├── algorithms │ ├── airl.rst │ ├── bc.rst │ ├── dagger.rst │ ├── density.rst │ ├── gail.rst │ ├── mce_irl.rst │ ├── preference_comparisons.rst │ └── sqil.rst ├── conf.py ├── development │ ├── contributing │ │ ├── code-of-conduct.rst │ │ ├── index.rst │ │ └── ways-to-contribute.rst │ ├── developer.rst │ ├── license.rst │ └── release-notes.rst ├── getting-started │ ├── cli.rst │ ├── first_steps.rst │ ├── installation.rst │ └── what_is_imitation.rst ├── index.rst ├── main-concepts │ ├── benchmarks.md │ ├── experts.rst │ ├── reward_networks.rst │ ├── trajectories.rst │ └── variable_horizon.rst ├── make.bat └── tutorials │ ├── 10_train_custom_env.ipynb │ ├── 1_train_bc.ipynb │ ├── 2_train_dagger.ipynb │ ├── 3_train_gail.ipynb │ ├── 4_train_airl.ipynb │ ├── 5_train_preference_comparisons.ipynb │ ├── 5a_train_preference_comparisons_with_cnn.ipynb │ ├── 6_train_mce.ipynb │ ├── 7_train_density.ipynb │ ├── 8_train_sqil.ipynb │ ├── 8a_train_sqil_sac.ipynb │ └── 9_compare_baselines.ipynb ├── examples ├── quickstart.py ├── quickstart.sh └── train_dagger_atari_interactive_policy.py ├── experiments ├── .gitignore ├── README.md ├── bc_benchmark.sh ├── benchmark_and_table.sh ├── commands.py ├── common.sh ├── convert_traj.py ├── dagger_benchmark.sh ├── imit_benchmark.sh ├── imit_benchmark_config.csv ├── imit_table_cheetahs.csv ├── imit_table_mvp_seals_config.csv ├── rollouts_from_policies.sh ├── rollouts_from_policies_config.csv └── transfer_learn_benchmark.sh ├── mypy.ini ├── pyproject.toml ├── runners ├── build_push_image.sh └── launch_docker-dev.sh ├── setup.cfg ├── setup.py ├── src └── imitation │ ├── __init__.py │ ├── algorithms │ ├── __init__.py │ ├── adversarial │ │ ├── __init__.py │ │ ├── airl.py │ │ ├── common.py │ │ └── gail.py │ ├── base.py │ ├── bc.py │ ├── dagger.py │ ├── density.py │ ├── mce_irl.py │ ├── preference_comparisons.py │ └── sqil.py │ ├── data │ ├── __init__.py │ ├── buffer.py │ ├── huggingface_utils.py │ ├── rollout.py │ ├── serialize.py │ ├── types.py │ └── wrappers.py │ ├── policies │ ├── __init__.py │ ├── base.py │ ├── exploration_wrapper.py │ ├── interactive.py │ ├── replay_buffer_wrapper.py │ └── serialize.py │ ├── py.typed │ ├── regularization │ ├── __init__.py │ ├── regularizers.py │ └── updaters.py │ ├── rewards │ ├── __init__.py │ ├── reward_function.py │ ├── reward_nets.py │ ├── reward_wrapper.py │ └── serialize.py │ ├── scripts │ ├── __init__.py │ ├── analyze.py │ ├── config │ │ ├── __init__.py │ │ ├── analyze.py │ │ ├── eval_policy.py │ │ ├── parallel.py │ │ ├── train_adversarial.py │ │ ├── train_imitation.py │ │ ├── train_preference_comparisons.py │ │ ├── train_rl.py │ │ ├── tuned_hps │ │ │ ├── airl_seals_ant_best_hp_eval.json │ │ │ ├── airl_seals_half_cheetah_best_hp_eval.json │ │ │ ├── airl_seals_hopper_best_hp_eval.json │ │ │ ├── airl_seals_swimmer_best_hp_eval.json │ │ │ ├── airl_seals_walker_best_hp_eval.json │ │ │ ├── bc_seals_ant_best_hp_eval.json │ │ │ ├── bc_seals_half_cheetah_best_hp_eval.json │ │ │ ├── bc_seals_hopper_best_hp_eval.json │ │ │ ├── bc_seals_swimmer_best_hp_eval.json │ │ │ ├── bc_seals_walker_best_hp_eval.json │ │ │ ├── dagger_seals_ant_best_hp_eval.json │ │ │ ├── dagger_seals_half_cheetah_best_hp_eval.json │ │ │ ├── dagger_seals_hopper_best_hp_eval.json │ │ │ ├── dagger_seals_swimmer_best_hp_eval.json │ │ │ ├── dagger_seals_walker_best_hp_eval.json │ │ │ ├── fast_dagger_seals_cartpole.json │ │ │ ├── gail_seals_ant_best_hp_eval.json │ │ │ ├── gail_seals_half_cheetah_best_hp_eval.json │ │ │ ├── gail_seals_hopper_best_hp_eval.json │ │ │ ├── gail_seals_swimmer_best_hp_eval.json │ │ │ └── gail_seals_walker_best_hp_eval.json │ │ └── tuning.py │ ├── convert_trajs.py │ ├── eval_policy.py │ ├── ingredients │ │ ├── __init__.py │ │ ├── bc.py │ │ ├── demonstrations.py │ │ ├── environment.py │ │ ├── expert.py │ │ ├── logging.py │ │ ├── policy.py │ │ ├── policy_evaluation.py │ │ ├── reward.py │ │ ├── rl.py │ │ ├── sqil.py │ │ └── wb.py │ ├── parallel.py │ ├── train_adversarial.py │ ├── train_imitation.py │ ├── train_preference_comparisons.py │ ├── train_rl.py │ └── tuning.py │ ├── testing │ ├── __init__.py │ ├── expert_trajectories.py │ ├── hypothesis_strategies.py │ ├── reward_improvement.py │ └── reward_nets.py │ └── util │ ├── __init__.py │ ├── logger.py │ ├── networks.py │ ├── registry.py │ ├── sacred.py │ ├── sacred_file_parsing.py │ ├── util.py │ └── video_wrapper.py └── tests ├── algorithms ├── __init__.py ├── conftest.py ├── test_adversarial.py ├── test_base.py ├── test_bc.py ├── test_dagger.py ├── test_density_baselines.py ├── test_mce_irl.py ├── test_preference_comparisons.py └── test_sqil.py ├── conftest.py ├── data ├── test_buffer.py ├── test_huggingface_utils.py ├── test_rollout.py ├── test_types.py └── test_wrappers.py ├── generate_test_data.sh ├── policies ├── test_exploration_wrapper.py ├── test_interactive.py ├── test_policies.py └── test_replay_buffer_wrapper.py ├── rewards ├── test_reward_fn.py ├── test_reward_nets.py └── test_reward_wrapper.py ├── scripts ├── ingredients │ └── test_rewards.py └── test_scripts.py ├── test_benchmarking.py ├── test_examples.py ├── test_experiments.py ├── test_regularization.py ├── testdata ├── expert_models │ ├── cartpole_0 │ │ ├── policies │ │ │ └── final │ │ │ │ └── model.zip │ │ └── rollouts │ │ │ └── final.npz │ └── pendulum_0 │ │ └── rollouts │ │ └── final.npz ├── imit_benchmark_config.csv ├── npz_format_rollout.npz ├── pickle_format_rollout.pkl └── rollouts_from_policies_config.csv └── util ├── test_logger.py ├── test_networks.py ├── test_registry.py ├── test_sacred_file_parsing.py ├── test_util.py └── test_wb_logger.py /.circleci/config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.circleci/config.yml -------------------------------------------------------------------------------- /.codecov.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.codecov.yml -------------------------------------------------------------------------------- /.coveragerc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.coveragerc -------------------------------------------------------------------------------- /.dockerignore: -------------------------------------------------------------------------------- 1 | .gitignore -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.gitattributes -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug_report.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.github/ISSUE_TEMPLATE/bug_report.md -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.github/ISSUE_TEMPLATE/feature_request.md -------------------------------------------------------------------------------- /.github/pull_request_template.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.github/pull_request_template.md -------------------------------------------------------------------------------- /.github/workflows/publish-to-pypi.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.github/workflows/publish-to-pypi.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /.readthedocs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/.readthedocs.yml -------------------------------------------------------------------------------- /CITATION.bib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/CITATION.bib -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/Dockerfile -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/README.md -------------------------------------------------------------------------------- /benchmarking/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/benchmarking/README.md -------------------------------------------------------------------------------- /benchmarking/compute_probability_of_improvement.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/benchmarking/compute_probability_of_improvement.py -------------------------------------------------------------------------------- /benchmarking/run_all_benchmarks.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/benchmarking/run_all_benchmarks.sh -------------------------------------------------------------------------------- /benchmarking/run_all_benchmarks_on_slurm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/benchmarking/run_all_benchmarks_on_slurm.sh -------------------------------------------------------------------------------- /benchmarking/run_benchmark_on_slurm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/benchmarking/run_benchmark_on_slurm.sh -------------------------------------------------------------------------------- /benchmarking/sacred_output_to_csv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/benchmarking/sacred_output_to_csv.py -------------------------------------------------------------------------------- /benchmarking/sacred_output_to_markdown_summary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/benchmarking/sacred_output_to_markdown_summary.py -------------------------------------------------------------------------------- /benchmarking/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/benchmarking/util.py -------------------------------------------------------------------------------- /ci/Xdummy-entrypoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/ci/Xdummy-entrypoint.py -------------------------------------------------------------------------------- /ci/build_and_activate_venv.ps1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/ci/build_and_activate_venv.ps1 -------------------------------------------------------------------------------- /ci/build_and_activate_venv.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/ci/build_and_activate_venv.sh -------------------------------------------------------------------------------- /ci/check_typeignore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/ci/check_typeignore.py -------------------------------------------------------------------------------- /ci/clean_notebooks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/ci/clean_notebooks.py -------------------------------------------------------------------------------- /ci/xorg.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/ci/xorg.conf -------------------------------------------------------------------------------- /docs/.gitignore: -------------------------------------------------------------------------------- 1 | _api 2 | -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/_static/css/custom.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/_static/css/custom.css -------------------------------------------------------------------------------- /docs/_templates/autosummary/base.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/_templates/autosummary/base.rst -------------------------------------------------------------------------------- /docs/_templates/autosummary/class.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/_templates/autosummary/class.rst -------------------------------------------------------------------------------- /docs/_templates/autosummary/module.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/_templates/autosummary/module.rst -------------------------------------------------------------------------------- /docs/algorithms/airl.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/algorithms/airl.rst -------------------------------------------------------------------------------- /docs/algorithms/bc.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/algorithms/bc.rst -------------------------------------------------------------------------------- /docs/algorithms/dagger.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/algorithms/dagger.rst -------------------------------------------------------------------------------- /docs/algorithms/density.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/algorithms/density.rst -------------------------------------------------------------------------------- /docs/algorithms/gail.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/algorithms/gail.rst -------------------------------------------------------------------------------- /docs/algorithms/mce_irl.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/algorithms/mce_irl.rst -------------------------------------------------------------------------------- /docs/algorithms/preference_comparisons.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/algorithms/preference_comparisons.rst -------------------------------------------------------------------------------- /docs/algorithms/sqil.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/algorithms/sqil.rst -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/conf.py -------------------------------------------------------------------------------- /docs/development/contributing/code-of-conduct.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/development/contributing/code-of-conduct.rst -------------------------------------------------------------------------------- /docs/development/contributing/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/development/contributing/index.rst -------------------------------------------------------------------------------- /docs/development/contributing/ways-to-contribute.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/development/contributing/ways-to-contribute.rst -------------------------------------------------------------------------------- /docs/development/developer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/development/developer.rst -------------------------------------------------------------------------------- /docs/development/license.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/development/license.rst -------------------------------------------------------------------------------- /docs/development/release-notes.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/development/release-notes.rst -------------------------------------------------------------------------------- /docs/getting-started/cli.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/getting-started/cli.rst -------------------------------------------------------------------------------- /docs/getting-started/first_steps.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/getting-started/first_steps.rst -------------------------------------------------------------------------------- /docs/getting-started/installation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/getting-started/installation.rst -------------------------------------------------------------------------------- /docs/getting-started/what_is_imitation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/getting-started/what_is_imitation.rst -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/index.rst -------------------------------------------------------------------------------- /docs/main-concepts/benchmarks.md: -------------------------------------------------------------------------------- 1 | ../../benchmarking/README.md -------------------------------------------------------------------------------- /docs/main-concepts/experts.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/main-concepts/experts.rst -------------------------------------------------------------------------------- /docs/main-concepts/reward_networks.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/main-concepts/reward_networks.rst -------------------------------------------------------------------------------- /docs/main-concepts/trajectories.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/main-concepts/trajectories.rst -------------------------------------------------------------------------------- /docs/main-concepts/variable_horizon.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/main-concepts/variable_horizon.rst -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/make.bat -------------------------------------------------------------------------------- /docs/tutorials/10_train_custom_env.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/10_train_custom_env.ipynb -------------------------------------------------------------------------------- /docs/tutorials/1_train_bc.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/1_train_bc.ipynb -------------------------------------------------------------------------------- /docs/tutorials/2_train_dagger.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/2_train_dagger.ipynb -------------------------------------------------------------------------------- /docs/tutorials/3_train_gail.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/3_train_gail.ipynb -------------------------------------------------------------------------------- /docs/tutorials/4_train_airl.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/4_train_airl.ipynb -------------------------------------------------------------------------------- /docs/tutorials/5_train_preference_comparisons.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/5_train_preference_comparisons.ipynb -------------------------------------------------------------------------------- /docs/tutorials/5a_train_preference_comparisons_with_cnn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/5a_train_preference_comparisons_with_cnn.ipynb -------------------------------------------------------------------------------- /docs/tutorials/6_train_mce.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/6_train_mce.ipynb -------------------------------------------------------------------------------- /docs/tutorials/7_train_density.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/7_train_density.ipynb -------------------------------------------------------------------------------- /docs/tutorials/8_train_sqil.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/8_train_sqil.ipynb -------------------------------------------------------------------------------- /docs/tutorials/8a_train_sqil_sac.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/8a_train_sqil_sac.ipynb -------------------------------------------------------------------------------- /docs/tutorials/9_compare_baselines.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/docs/tutorials/9_compare_baselines.ipynb -------------------------------------------------------------------------------- /examples/quickstart.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/examples/quickstart.py -------------------------------------------------------------------------------- /examples/quickstart.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/examples/quickstart.sh -------------------------------------------------------------------------------- /examples/train_dagger_atari_interactive_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/examples/train_dagger_atari_interactive_policy.py -------------------------------------------------------------------------------- /experiments/.gitignore: -------------------------------------------------------------------------------- 1 | figures/ 2 | -------------------------------------------------------------------------------- /experiments/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/README.md -------------------------------------------------------------------------------- /experiments/bc_benchmark.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/bc_benchmark.sh -------------------------------------------------------------------------------- /experiments/benchmark_and_table.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/benchmark_and_table.sh -------------------------------------------------------------------------------- /experiments/commands.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/commands.py -------------------------------------------------------------------------------- /experiments/common.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/common.sh -------------------------------------------------------------------------------- /experiments/convert_traj.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/convert_traj.py -------------------------------------------------------------------------------- /experiments/dagger_benchmark.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/dagger_benchmark.sh -------------------------------------------------------------------------------- /experiments/imit_benchmark.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/imit_benchmark.sh -------------------------------------------------------------------------------- /experiments/imit_benchmark_config.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/imit_benchmark_config.csv -------------------------------------------------------------------------------- /experiments/imit_table_cheetahs.csv: -------------------------------------------------------------------------------- 1 | env_config_name,n_expert_demos 2 | seals_half_cheetah,40 3 | -------------------------------------------------------------------------------- /experiments/imit_table_mvp_seals_config.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/imit_table_mvp_seals_config.csv -------------------------------------------------------------------------------- /experiments/rollouts_from_policies.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/rollouts_from_policies.sh -------------------------------------------------------------------------------- /experiments/rollouts_from_policies_config.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/rollouts_from_policies_config.csv -------------------------------------------------------------------------------- /experiments/transfer_learn_benchmark.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/experiments/transfer_learn_benchmark.sh -------------------------------------------------------------------------------- /mypy.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/mypy.ini -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/pyproject.toml -------------------------------------------------------------------------------- /runners/build_push_image.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/runners/build_push_image.sh -------------------------------------------------------------------------------- /runners/launch_docker-dev.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/runners/launch_docker-dev.sh -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/setup.py -------------------------------------------------------------------------------- /src/imitation/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/__init__.py -------------------------------------------------------------------------------- /src/imitation/algorithms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/__init__.py -------------------------------------------------------------------------------- /src/imitation/algorithms/adversarial/__init__.py: -------------------------------------------------------------------------------- 1 | """Adversarial imitation learning algorithms, AIRL and GAIL.""" 2 | -------------------------------------------------------------------------------- /src/imitation/algorithms/adversarial/airl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/adversarial/airl.py -------------------------------------------------------------------------------- /src/imitation/algorithms/adversarial/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/adversarial/common.py -------------------------------------------------------------------------------- /src/imitation/algorithms/adversarial/gail.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/adversarial/gail.py -------------------------------------------------------------------------------- /src/imitation/algorithms/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/base.py -------------------------------------------------------------------------------- /src/imitation/algorithms/bc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/bc.py -------------------------------------------------------------------------------- /src/imitation/algorithms/dagger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/dagger.py -------------------------------------------------------------------------------- /src/imitation/algorithms/density.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/density.py -------------------------------------------------------------------------------- /src/imitation/algorithms/mce_irl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/mce_irl.py -------------------------------------------------------------------------------- /src/imitation/algorithms/preference_comparisons.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/preference_comparisons.py -------------------------------------------------------------------------------- /src/imitation/algorithms/sqil.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/algorithms/sqil.py -------------------------------------------------------------------------------- /src/imitation/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/data/__init__.py -------------------------------------------------------------------------------- /src/imitation/data/buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/data/buffer.py -------------------------------------------------------------------------------- /src/imitation/data/huggingface_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/data/huggingface_utils.py -------------------------------------------------------------------------------- /src/imitation/data/rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/data/rollout.py -------------------------------------------------------------------------------- /src/imitation/data/serialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/data/serialize.py -------------------------------------------------------------------------------- /src/imitation/data/types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/data/types.py -------------------------------------------------------------------------------- /src/imitation/data/wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/data/wrappers.py -------------------------------------------------------------------------------- /src/imitation/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/policies/__init__.py -------------------------------------------------------------------------------- /src/imitation/policies/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/policies/base.py -------------------------------------------------------------------------------- /src/imitation/policies/exploration_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/policies/exploration_wrapper.py -------------------------------------------------------------------------------- /src/imitation/policies/interactive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/policies/interactive.py -------------------------------------------------------------------------------- /src/imitation/policies/replay_buffer_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/policies/replay_buffer_wrapper.py -------------------------------------------------------------------------------- /src/imitation/policies/serialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/policies/serialize.py -------------------------------------------------------------------------------- /src/imitation/py.typed: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/imitation/regularization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/regularization/__init__.py -------------------------------------------------------------------------------- /src/imitation/regularization/regularizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/regularization/regularizers.py -------------------------------------------------------------------------------- /src/imitation/regularization/updaters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/regularization/updaters.py -------------------------------------------------------------------------------- /src/imitation/rewards/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/rewards/__init__.py -------------------------------------------------------------------------------- /src/imitation/rewards/reward_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/rewards/reward_function.py -------------------------------------------------------------------------------- /src/imitation/rewards/reward_nets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/rewards/reward_nets.py -------------------------------------------------------------------------------- /src/imitation/rewards/reward_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/rewards/reward_wrapper.py -------------------------------------------------------------------------------- /src/imitation/rewards/serialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/rewards/serialize.py -------------------------------------------------------------------------------- /src/imitation/scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/__init__.py -------------------------------------------------------------------------------- /src/imitation/scripts/analyze.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/analyze.py -------------------------------------------------------------------------------- /src/imitation/scripts/config/__init__.py: -------------------------------------------------------------------------------- 1 | """Configuration settings for scripts.""" 2 | -------------------------------------------------------------------------------- /src/imitation/scripts/config/analyze.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/analyze.py -------------------------------------------------------------------------------- /src/imitation/scripts/config/eval_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/eval_policy.py -------------------------------------------------------------------------------- /src/imitation/scripts/config/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/parallel.py -------------------------------------------------------------------------------- /src/imitation/scripts/config/train_adversarial.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/train_adversarial.py -------------------------------------------------------------------------------- /src/imitation/scripts/config/train_imitation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/train_imitation.py -------------------------------------------------------------------------------- /src/imitation/scripts/config/train_preference_comparisons.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/train_preference_comparisons.py -------------------------------------------------------------------------------- /src/imitation/scripts/config/train_rl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/train_rl.py -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/airl_seals_ant_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/airl_seals_ant_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/airl_seals_half_cheetah_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/airl_seals_half_cheetah_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/airl_seals_hopper_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/airl_seals_hopper_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/airl_seals_swimmer_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/airl_seals_swimmer_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/airl_seals_walker_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/airl_seals_walker_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/bc_seals_ant_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/bc_seals_ant_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/bc_seals_half_cheetah_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/bc_seals_half_cheetah_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/bc_seals_hopper_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/bc_seals_hopper_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/bc_seals_swimmer_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/bc_seals_swimmer_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/bc_seals_walker_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/bc_seals_walker_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/dagger_seals_ant_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/dagger_seals_ant_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/dagger_seals_half_cheetah_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/dagger_seals_half_cheetah_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/dagger_seals_hopper_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/dagger_seals_hopper_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/dagger_seals_swimmer_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/dagger_seals_swimmer_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/dagger_seals_walker_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/dagger_seals_walker_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/fast_dagger_seals_cartpole.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/fast_dagger_seals_cartpole.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/gail_seals_ant_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/gail_seals_ant_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/gail_seals_half_cheetah_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/gail_seals_half_cheetah_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/gail_seals_hopper_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/gail_seals_hopper_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/gail_seals_swimmer_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/gail_seals_swimmer_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuned_hps/gail_seals_walker_best_hp_eval.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuned_hps/gail_seals_walker_best_hp_eval.json -------------------------------------------------------------------------------- /src/imitation/scripts/config/tuning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/config/tuning.py -------------------------------------------------------------------------------- /src/imitation/scripts/convert_trajs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/convert_trajs.py -------------------------------------------------------------------------------- /src/imitation/scripts/eval_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/eval_policy.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/__init__.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/bc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/bc.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/demonstrations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/demonstrations.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/environment.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/expert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/expert.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/logging.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/policy.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/policy_evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/policy_evaluation.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/reward.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/rl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/rl.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/sqil.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/sqil.py -------------------------------------------------------------------------------- /src/imitation/scripts/ingredients/wb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/ingredients/wb.py -------------------------------------------------------------------------------- /src/imitation/scripts/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/parallel.py -------------------------------------------------------------------------------- /src/imitation/scripts/train_adversarial.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/train_adversarial.py -------------------------------------------------------------------------------- /src/imitation/scripts/train_imitation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/train_imitation.py -------------------------------------------------------------------------------- /src/imitation/scripts/train_preference_comparisons.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/train_preference_comparisons.py -------------------------------------------------------------------------------- /src/imitation/scripts/train_rl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/train_rl.py -------------------------------------------------------------------------------- /src/imitation/scripts/tuning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/scripts/tuning.py -------------------------------------------------------------------------------- /src/imitation/testing/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/testing/__init__.py -------------------------------------------------------------------------------- /src/imitation/testing/expert_trajectories.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/testing/expert_trajectories.py -------------------------------------------------------------------------------- /src/imitation/testing/hypothesis_strategies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/testing/hypothesis_strategies.py -------------------------------------------------------------------------------- /src/imitation/testing/reward_improvement.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/testing/reward_improvement.py -------------------------------------------------------------------------------- /src/imitation/testing/reward_nets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/testing/reward_nets.py -------------------------------------------------------------------------------- /src/imitation/util/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/util/__init__.py -------------------------------------------------------------------------------- /src/imitation/util/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/util/logger.py -------------------------------------------------------------------------------- /src/imitation/util/networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/util/networks.py -------------------------------------------------------------------------------- /src/imitation/util/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/util/registry.py -------------------------------------------------------------------------------- /src/imitation/util/sacred.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/util/sacred.py -------------------------------------------------------------------------------- /src/imitation/util/sacred_file_parsing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/util/sacred_file_parsing.py -------------------------------------------------------------------------------- /src/imitation/util/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/util/util.py -------------------------------------------------------------------------------- /src/imitation/util/video_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/src/imitation/util/video_wrapper.py -------------------------------------------------------------------------------- /tests/algorithms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/__init__.py -------------------------------------------------------------------------------- /tests/algorithms/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/conftest.py -------------------------------------------------------------------------------- /tests/algorithms/test_adversarial.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/test_adversarial.py -------------------------------------------------------------------------------- /tests/algorithms/test_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/test_base.py -------------------------------------------------------------------------------- /tests/algorithms/test_bc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/test_bc.py -------------------------------------------------------------------------------- /tests/algorithms/test_dagger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/test_dagger.py -------------------------------------------------------------------------------- /tests/algorithms/test_density_baselines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/test_density_baselines.py -------------------------------------------------------------------------------- /tests/algorithms/test_mce_irl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/test_mce_irl.py -------------------------------------------------------------------------------- /tests/algorithms/test_preference_comparisons.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/test_preference_comparisons.py -------------------------------------------------------------------------------- /tests/algorithms/test_sqil.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/algorithms/test_sqil.py -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/conftest.py -------------------------------------------------------------------------------- /tests/data/test_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/data/test_buffer.py -------------------------------------------------------------------------------- /tests/data/test_huggingface_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/data/test_huggingface_utils.py -------------------------------------------------------------------------------- /tests/data/test_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/data/test_rollout.py -------------------------------------------------------------------------------- /tests/data/test_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/data/test_types.py -------------------------------------------------------------------------------- /tests/data/test_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/data/test_wrappers.py -------------------------------------------------------------------------------- /tests/generate_test_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/generate_test_data.sh -------------------------------------------------------------------------------- /tests/policies/test_exploration_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/policies/test_exploration_wrapper.py -------------------------------------------------------------------------------- /tests/policies/test_interactive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/policies/test_interactive.py -------------------------------------------------------------------------------- /tests/policies/test_policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/policies/test_policies.py -------------------------------------------------------------------------------- /tests/policies/test_replay_buffer_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/policies/test_replay_buffer_wrapper.py -------------------------------------------------------------------------------- /tests/rewards/test_reward_fn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/rewards/test_reward_fn.py -------------------------------------------------------------------------------- /tests/rewards/test_reward_nets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/rewards/test_reward_nets.py -------------------------------------------------------------------------------- /tests/rewards/test_reward_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/rewards/test_reward_wrapper.py -------------------------------------------------------------------------------- /tests/scripts/ingredients/test_rewards.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/scripts/ingredients/test_rewards.py -------------------------------------------------------------------------------- /tests/scripts/test_scripts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/scripts/test_scripts.py -------------------------------------------------------------------------------- /tests/test_benchmarking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/test_benchmarking.py -------------------------------------------------------------------------------- /tests/test_examples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/test_examples.py -------------------------------------------------------------------------------- /tests/test_experiments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/test_experiments.py -------------------------------------------------------------------------------- /tests/test_regularization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/test_regularization.py -------------------------------------------------------------------------------- /tests/testdata/expert_models/cartpole_0/policies/final/model.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/testdata/expert_models/cartpole_0/policies/final/model.zip -------------------------------------------------------------------------------- /tests/testdata/expert_models/cartpole_0/rollouts/final.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/testdata/expert_models/cartpole_0/rollouts/final.npz -------------------------------------------------------------------------------- /tests/testdata/expert_models/pendulum_0/rollouts/final.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/testdata/expert_models/pendulum_0/rollouts/final.npz -------------------------------------------------------------------------------- /tests/testdata/imit_benchmark_config.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/testdata/imit_benchmark_config.csv -------------------------------------------------------------------------------- /tests/testdata/npz_format_rollout.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/testdata/npz_format_rollout.npz -------------------------------------------------------------------------------- /tests/testdata/pickle_format_rollout.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/testdata/pickle_format_rollout.pkl -------------------------------------------------------------------------------- /tests/testdata/rollouts_from_policies_config.csv: -------------------------------------------------------------------------------- 1 | env_config_name,n_demonstrations 2 | seals_cartpole,1 3 | -------------------------------------------------------------------------------- /tests/util/test_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/util/test_logger.py -------------------------------------------------------------------------------- /tests/util/test_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/util/test_networks.py -------------------------------------------------------------------------------- /tests/util/test_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/util/test_registry.py -------------------------------------------------------------------------------- /tests/util/test_sacred_file_parsing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/util/test_sacred_file_parsing.py -------------------------------------------------------------------------------- /tests/util/test_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/util/test_util.py -------------------------------------------------------------------------------- /tests/util/test_wb_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/HumanCompatibleAI/imitation/HEAD/tests/util/test_wb_logger.py --------------------------------------------------------------------------------