├── LICENSE ├── README.md ├── experiments ├── benchmark_circle_tasks.py ├── benchmark_gather_tasks.py ├── benchmark_reach_tasks.py ├── benchmark_run_tasks.py └── safety_settings.py ├── rl_safety_algorithms ├── __init__.py ├── algs │ ├── __init__.py │ ├── core.py │ ├── cpo │ │ ├── __init__.py │ │ ├── cpo.py │ │ └── defaults.py │ ├── iwpg │ │ ├── __init__.py │ │ ├── defaults.py │ │ └── iwpg.py │ ├── lag-trpo │ │ ├── __init__.py │ │ ├── defaults.py │ │ └── lag-trpo.py │ ├── npg │ │ ├── __init__.py │ │ ├── defaults.py │ │ └── npg.py │ ├── pdo │ │ ├── __init__.py │ │ ├── defaults.py │ │ └── pdo.py │ ├── trpo │ │ ├── __init__.py │ │ ├── defaults.py │ │ └── trpo.py │ ├── utils.py │ └── vtrace.py ├── benchmark.py ├── common │ ├── __init__.py │ ├── experiment_analysis.py │ ├── loggers.py │ ├── model.py │ ├── mpi_tools.py │ ├── multi_processing_utils.py │ ├── online_mean_std.py │ ├── trainer.py │ └── utils.py ├── play.py ├── plot.py └── train.py ├── setup.py └── tests ├── test_algs_mpi.py ├── test_algs_single_thread.py ├── test_gae.py ├── test_mean_std.py ├── test_mean_std_mpi.py └── test_trust_region_utils.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/README.md -------------------------------------------------------------------------------- /experiments/benchmark_circle_tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/experiments/benchmark_circle_tasks.py -------------------------------------------------------------------------------- /experiments/benchmark_gather_tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/experiments/benchmark_gather_tasks.py -------------------------------------------------------------------------------- /experiments/benchmark_reach_tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/experiments/benchmark_reach_tasks.py -------------------------------------------------------------------------------- /experiments/benchmark_run_tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/experiments/benchmark_run_tasks.py -------------------------------------------------------------------------------- /experiments/safety_settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/experiments/safety_settings.py -------------------------------------------------------------------------------- /rl_safety_algorithms/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/core.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/cpo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/cpo/cpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/cpo/cpo.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/cpo/defaults.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/cpo/defaults.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/iwpg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/iwpg/defaults.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/iwpg/defaults.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/iwpg/iwpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/iwpg/iwpg.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/lag-trpo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/lag-trpo/defaults.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/lag-trpo/defaults.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/lag-trpo/lag-trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/lag-trpo/lag-trpo.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/npg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/npg/defaults.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/npg/defaults.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/npg/npg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/npg/npg.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/pdo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/pdo/defaults.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/pdo/defaults.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/pdo/pdo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/pdo/pdo.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/trpo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/trpo/defaults.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/trpo/defaults.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/trpo/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/trpo/trpo.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/utils.py -------------------------------------------------------------------------------- /rl_safety_algorithms/algs/vtrace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/algs/vtrace.py -------------------------------------------------------------------------------- /rl_safety_algorithms/benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/benchmark.py -------------------------------------------------------------------------------- /rl_safety_algorithms/common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl_safety_algorithms/common/experiment_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/common/experiment_analysis.py -------------------------------------------------------------------------------- /rl_safety_algorithms/common/loggers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/common/loggers.py -------------------------------------------------------------------------------- /rl_safety_algorithms/common/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/common/model.py -------------------------------------------------------------------------------- /rl_safety_algorithms/common/mpi_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/common/mpi_tools.py -------------------------------------------------------------------------------- /rl_safety_algorithms/common/multi_processing_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/common/multi_processing_utils.py -------------------------------------------------------------------------------- /rl_safety_algorithms/common/online_mean_std.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/common/online_mean_std.py -------------------------------------------------------------------------------- /rl_safety_algorithms/common/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/common/trainer.py -------------------------------------------------------------------------------- /rl_safety_algorithms/common/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/common/utils.py -------------------------------------------------------------------------------- /rl_safety_algorithms/play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/play.py -------------------------------------------------------------------------------- /rl_safety_algorithms/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/plot.py -------------------------------------------------------------------------------- /rl_safety_algorithms/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/rl_safety_algorithms/train.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/setup.py -------------------------------------------------------------------------------- /tests/test_algs_mpi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/tests/test_algs_mpi.py -------------------------------------------------------------------------------- /tests/test_algs_single_thread.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/tests/test_algs_single_thread.py -------------------------------------------------------------------------------- /tests/test_gae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/tests/test_gae.py -------------------------------------------------------------------------------- /tests/test_mean_std.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/tests/test_mean_std.py -------------------------------------------------------------------------------- /tests/test_mean_std_mpi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/tests/test_mean_std_mpi.py -------------------------------------------------------------------------------- /tests/test_trust_region_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SvenGronauer/RL-Safety-Algorithms/HEAD/tests/test_trust_region_utils.py --------------------------------------------------------------------------------