├── .gitignore ├── .travis.yml ├── LICENSE ├── docs ├── Makefile ├── _static │ ├── css │ │ └── modify.css │ ├── openai-favicon2_32x32.ico │ ├── openai-favicon2_32x32.png │ └── openai_icon.ico ├── algorithms │ ├── ddpg.rst │ ├── ppo.rst │ ├── sac.rst │ ├── td3.rst │ ├── trpo.rst │ └── vpg.rst ├── conf.py ├── docs_requirements.txt ├── etc │ ├── acknowledgements.rst │ └── author.rst ├── images │ ├── alphago.jpg │ ├── bench │ │ ├── bench_ant.svg │ │ ├── bench_halfcheetah.svg │ │ ├── bench_hopper.svg │ │ ├── bench_swim.svg │ │ └── bench_walker.svg │ ├── ex2-1_trpo_hopper.png │ ├── ex2-2_ddpg_bug.svg │ ├── ex2-2_ddpg_bug_pytorch.png │ ├── knocked-over-stand-up.mp4 │ ├── knocked_down_standup.png │ ├── logo.png │ ├── ms_pacman.png │ ├── openai-favicon.png │ ├── openai-favicon2.png │ ├── openai-favicon2_32x32.png │ ├── plots │ │ ├── ddpg │ │ │ ├── ddpg_ant_performance.svg │ │ │ ├── ddpg_halfcheetah_performance.svg │ │ │ ├── ddpg_hopper_performance.svg │ │ │ ├── ddpg_swimmer_performance.svg │ │ │ └── ddpg_walker2d_performance.svg │ │ ├── ppo │ │ │ ├── ppo_ant_performance.svg │ │ │ ├── ppo_halfcheetah_performance.svg │ │ │ ├── ppo_hopper_performance.svg │ │ │ ├── ppo_swimmer_performance.svg │ │ │ └── ppo_walker2d_performance.svg │ │ ├── pyt │ │ │ ├── pytorch_ant_performance.svg │ │ │ ├── pytorch_halfcheetah_performance.svg │ │ │ ├── pytorch_hopper_performance.svg │ │ │ ├── pytorch_swimmer_performance.svg │ │ │ └── pytorch_walker2d_performance.svg │ │ ├── sac │ │ │ ├── sac_ant_performance.svg │ │ │ ├── sac_halfcheetah_performance.svg │ │ │ ├── sac_hopper_performance.svg │ │ │ ├── sac_swimmer_performance.svg │ │ │ └── sac_walker2d_performance.svg │ │ ├── td3 │ │ │ ├── td3_ant_performance.svg │ │ │ ├── td3_halfcheetah_performance.svg │ │ │ ├── td3_hopper_performance.svg │ │ │ ├── td3_swimmer_performance.svg │ │ │ └── td3_walker2d_performance.svg │ │ ├── tf1 │ │ │ ├── tensorflow_ant_performance.svg │ │ │ ├── tensorflow_halfcheetah_performance.svg │ │ │ ├── tensorflow_hopper_performance.svg │ │ │ ├── tensorflow_swimmer_performance.svg │ │ │ └── tensorflow_walker2d_performance.svg │ │ └── vpg │ │ │ ├── vpg_ant_performance.svg │ │ │ ├── vpg_halfcheetah_performance.svg │ │ │ ├── vpg_hopper_performance.svg │ │ │ ├── vpg_swimmer_performance.svg │ │ │ └── vpg_walker2d_performance.svg │ ├── recolored_logo.png │ ├── rl_algorithms.png │ ├── rl_algorithms.svg │ ├── rl_algorithms.xml │ ├── rl_algorithms_9_12.png │ ├── rl_algorithms_9_15.svg │ ├── rl_algorithms_9_15.xml │ ├── rl_diagram_transparent_bg.png │ ├── spinning-up-in-rl.png │ ├── spinning-up-logo.png │ ├── spinning-up-logo.svg │ └── spinning-up-logo2.png ├── index.rst ├── make.bat ├── spinningup │ ├── bench.rst │ ├── bench_ddpg.rst │ ├── bench_ppo.rst │ ├── bench_sac.rst │ ├── bench_td3.rst │ ├── bench_vpg.rst │ ├── exercise2_1_soln.rst │ ├── exercise2_2_soln.rst │ ├── exercises.rst │ ├── extra_pg_proof1.rst │ ├── extra_pg_proof2.rst │ ├── extra_tf_pg_implementation.rst │ ├── keypapers.rst │ ├── rl_intro.rst │ ├── rl_intro2.rst │ ├── rl_intro3.rst │ ├── rl_intro4.rst │ └── spinningup.rst ├── user │ ├── algorithms.rst │ ├── installation.rst │ ├── introduction.rst │ ├── plotting.rst │ ├── running.rst │ └── saving_and_loading.rst └── utils │ ├── logger.rst │ ├── mpi.rst │ ├── plotter.rst │ └── run_utils.rst ├── readme.md ├── readthedocs.yml ├── setup.py ├── spinup ├── __init__.py ├── algos │ ├── __init__.py │ └── tf1 │ │ └── td3_peng │ │ ├── __init__.py │ │ ├── core.py │ │ ├── core_retrace.py │ │ ├── td3_peng.py │ │ ├── td3_retrace.py │ │ └── wrappers.py ├── run.py ├── user_config.py ├── utils │ ├── __init__.py │ ├── logx.py │ ├── mpi_tools.py │ ├── plot.py │ ├── run_entrypoint.py │ ├── run_utils.py │ ├── serialization_utils.py │ └── test_policy.py └── version.py ├── test └── test_ppo.py └── travis_setup.sh /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/.gitignore -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/.travis.yml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/LICENSE -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/_static/css/modify.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/_static/css/modify.css -------------------------------------------------------------------------------- /docs/_static/openai-favicon2_32x32.ico: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/_static/openai-favicon2_32x32.ico -------------------------------------------------------------------------------- /docs/_static/openai-favicon2_32x32.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/_static/openai-favicon2_32x32.png -------------------------------------------------------------------------------- /docs/_static/openai_icon.ico: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/_static/openai_icon.ico -------------------------------------------------------------------------------- /docs/algorithms/ddpg.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/algorithms/ddpg.rst -------------------------------------------------------------------------------- /docs/algorithms/ppo.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/algorithms/ppo.rst -------------------------------------------------------------------------------- /docs/algorithms/sac.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/algorithms/sac.rst -------------------------------------------------------------------------------- /docs/algorithms/td3.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/algorithms/td3.rst -------------------------------------------------------------------------------- /docs/algorithms/trpo.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/algorithms/trpo.rst -------------------------------------------------------------------------------- /docs/algorithms/vpg.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/algorithms/vpg.rst -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/conf.py -------------------------------------------------------------------------------- /docs/docs_requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/docs_requirements.txt -------------------------------------------------------------------------------- /docs/etc/acknowledgements.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/etc/acknowledgements.rst -------------------------------------------------------------------------------- /docs/etc/author.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/etc/author.rst -------------------------------------------------------------------------------- /docs/images/alphago.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/alphago.jpg -------------------------------------------------------------------------------- /docs/images/bench/bench_ant.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/bench/bench_ant.svg -------------------------------------------------------------------------------- /docs/images/bench/bench_halfcheetah.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/bench/bench_halfcheetah.svg -------------------------------------------------------------------------------- /docs/images/bench/bench_hopper.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/bench/bench_hopper.svg -------------------------------------------------------------------------------- /docs/images/bench/bench_swim.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/bench/bench_swim.svg -------------------------------------------------------------------------------- /docs/images/bench/bench_walker.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/bench/bench_walker.svg -------------------------------------------------------------------------------- /docs/images/ex2-1_trpo_hopper.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/ex2-1_trpo_hopper.png -------------------------------------------------------------------------------- /docs/images/ex2-2_ddpg_bug.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/ex2-2_ddpg_bug.svg -------------------------------------------------------------------------------- /docs/images/ex2-2_ddpg_bug_pytorch.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/ex2-2_ddpg_bug_pytorch.png -------------------------------------------------------------------------------- /docs/images/knocked-over-stand-up.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/knocked-over-stand-up.mp4 -------------------------------------------------------------------------------- /docs/images/knocked_down_standup.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/knocked_down_standup.png -------------------------------------------------------------------------------- /docs/images/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/logo.png -------------------------------------------------------------------------------- /docs/images/ms_pacman.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/ms_pacman.png -------------------------------------------------------------------------------- /docs/images/openai-favicon.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/openai-favicon.png -------------------------------------------------------------------------------- /docs/images/openai-favicon2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/openai-favicon2.png -------------------------------------------------------------------------------- /docs/images/openai-favicon2_32x32.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/openai-favicon2_32x32.png -------------------------------------------------------------------------------- /docs/images/plots/ddpg/ddpg_ant_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ddpg/ddpg_ant_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/ddpg/ddpg_halfcheetah_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ddpg/ddpg_halfcheetah_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/ddpg/ddpg_hopper_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ddpg/ddpg_hopper_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/ddpg/ddpg_swimmer_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ddpg/ddpg_swimmer_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/ddpg/ddpg_walker2d_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ddpg/ddpg_walker2d_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/ppo/ppo_ant_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ppo/ppo_ant_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/ppo/ppo_halfcheetah_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ppo/ppo_halfcheetah_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/ppo/ppo_hopper_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ppo/ppo_hopper_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/ppo/ppo_swimmer_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ppo/ppo_swimmer_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/ppo/ppo_walker2d_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/ppo/ppo_walker2d_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/pyt/pytorch_ant_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/pyt/pytorch_ant_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/pyt/pytorch_halfcheetah_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/pyt/pytorch_halfcheetah_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/pyt/pytorch_hopper_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/pyt/pytorch_hopper_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/pyt/pytorch_swimmer_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/pyt/pytorch_swimmer_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/pyt/pytorch_walker2d_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/pyt/pytorch_walker2d_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/sac/sac_ant_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/sac/sac_ant_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/sac/sac_halfcheetah_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/sac/sac_halfcheetah_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/sac/sac_hopper_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/sac/sac_hopper_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/sac/sac_swimmer_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/sac/sac_swimmer_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/sac/sac_walker2d_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/sac/sac_walker2d_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/td3/td3_ant_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/td3/td3_ant_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/td3/td3_halfcheetah_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/td3/td3_halfcheetah_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/td3/td3_hopper_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/td3/td3_hopper_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/td3/td3_swimmer_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/td3/td3_swimmer_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/td3/td3_walker2d_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/td3/td3_walker2d_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/tf1/tensorflow_ant_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/tf1/tensorflow_ant_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/tf1/tensorflow_halfcheetah_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/tf1/tensorflow_halfcheetah_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/tf1/tensorflow_hopper_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/tf1/tensorflow_hopper_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/tf1/tensorflow_swimmer_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/tf1/tensorflow_swimmer_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/tf1/tensorflow_walker2d_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/tf1/tensorflow_walker2d_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/vpg/vpg_ant_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/vpg/vpg_ant_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/vpg/vpg_halfcheetah_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/vpg/vpg_halfcheetah_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/vpg/vpg_hopper_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/vpg/vpg_hopper_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/vpg/vpg_swimmer_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/vpg/vpg_swimmer_performance.svg -------------------------------------------------------------------------------- /docs/images/plots/vpg/vpg_walker2d_performance.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/plots/vpg/vpg_walker2d_performance.svg -------------------------------------------------------------------------------- /docs/images/recolored_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/recolored_logo.png -------------------------------------------------------------------------------- /docs/images/rl_algorithms.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/rl_algorithms.png -------------------------------------------------------------------------------- /docs/images/rl_algorithms.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/rl_algorithms.svg -------------------------------------------------------------------------------- /docs/images/rl_algorithms.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/rl_algorithms.xml -------------------------------------------------------------------------------- /docs/images/rl_algorithms_9_12.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/rl_algorithms_9_12.png -------------------------------------------------------------------------------- /docs/images/rl_algorithms_9_15.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/rl_algorithms_9_15.svg -------------------------------------------------------------------------------- /docs/images/rl_algorithms_9_15.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/rl_algorithms_9_15.xml -------------------------------------------------------------------------------- /docs/images/rl_diagram_transparent_bg.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/rl_diagram_transparent_bg.png -------------------------------------------------------------------------------- /docs/images/spinning-up-in-rl.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/spinning-up-in-rl.png -------------------------------------------------------------------------------- /docs/images/spinning-up-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/spinning-up-logo.png -------------------------------------------------------------------------------- /docs/images/spinning-up-logo.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/spinning-up-logo.svg -------------------------------------------------------------------------------- /docs/images/spinning-up-logo2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/images/spinning-up-logo2.png -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/index.rst -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/make.bat -------------------------------------------------------------------------------- /docs/spinningup/bench.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/bench.rst -------------------------------------------------------------------------------- /docs/spinningup/bench_ddpg.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/bench_ddpg.rst -------------------------------------------------------------------------------- /docs/spinningup/bench_ppo.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/bench_ppo.rst -------------------------------------------------------------------------------- /docs/spinningup/bench_sac.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/bench_sac.rst -------------------------------------------------------------------------------- /docs/spinningup/bench_td3.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/bench_td3.rst -------------------------------------------------------------------------------- /docs/spinningup/bench_vpg.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/bench_vpg.rst -------------------------------------------------------------------------------- /docs/spinningup/exercise2_1_soln.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/exercise2_1_soln.rst -------------------------------------------------------------------------------- /docs/spinningup/exercise2_2_soln.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/exercise2_2_soln.rst -------------------------------------------------------------------------------- /docs/spinningup/exercises.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/exercises.rst -------------------------------------------------------------------------------- /docs/spinningup/extra_pg_proof1.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/extra_pg_proof1.rst -------------------------------------------------------------------------------- /docs/spinningup/extra_pg_proof2.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/extra_pg_proof2.rst -------------------------------------------------------------------------------- /docs/spinningup/extra_tf_pg_implementation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/extra_tf_pg_implementation.rst -------------------------------------------------------------------------------- /docs/spinningup/keypapers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/keypapers.rst -------------------------------------------------------------------------------- /docs/spinningup/rl_intro.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/rl_intro.rst -------------------------------------------------------------------------------- /docs/spinningup/rl_intro2.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/rl_intro2.rst -------------------------------------------------------------------------------- /docs/spinningup/rl_intro3.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/rl_intro3.rst -------------------------------------------------------------------------------- /docs/spinningup/rl_intro4.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/rl_intro4.rst -------------------------------------------------------------------------------- /docs/spinningup/spinningup.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/spinningup/spinningup.rst -------------------------------------------------------------------------------- /docs/user/algorithms.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/user/algorithms.rst -------------------------------------------------------------------------------- /docs/user/installation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/user/installation.rst -------------------------------------------------------------------------------- /docs/user/introduction.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/user/introduction.rst -------------------------------------------------------------------------------- /docs/user/plotting.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/user/plotting.rst -------------------------------------------------------------------------------- /docs/user/running.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/user/running.rst -------------------------------------------------------------------------------- /docs/user/saving_and_loading.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/user/saving_and_loading.rst -------------------------------------------------------------------------------- /docs/utils/logger.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/utils/logger.rst -------------------------------------------------------------------------------- /docs/utils/mpi.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/utils/mpi.rst -------------------------------------------------------------------------------- /docs/utils/plotter.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/utils/plotter.rst -------------------------------------------------------------------------------- /docs/utils/run_utils.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/docs/utils/run_utils.rst -------------------------------------------------------------------------------- /readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/readme.md -------------------------------------------------------------------------------- /readthedocs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/readthedocs.yml -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/setup.py -------------------------------------------------------------------------------- /spinup/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/__init__.py -------------------------------------------------------------------------------- /spinup/algos/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /spinup/algos/tf1/td3_peng/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /spinup/algos/tf1/td3_peng/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/algos/tf1/td3_peng/core.py -------------------------------------------------------------------------------- /spinup/algos/tf1/td3_peng/core_retrace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/algos/tf1/td3_peng/core_retrace.py -------------------------------------------------------------------------------- /spinup/algos/tf1/td3_peng/td3_peng.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/algos/tf1/td3_peng/td3_peng.py -------------------------------------------------------------------------------- /spinup/algos/tf1/td3_peng/td3_retrace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/algos/tf1/td3_peng/td3_retrace.py -------------------------------------------------------------------------------- /spinup/algos/tf1/td3_peng/wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/algos/tf1/td3_peng/wrappers.py -------------------------------------------------------------------------------- /spinup/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/run.py -------------------------------------------------------------------------------- /spinup/user_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/user_config.py -------------------------------------------------------------------------------- /spinup/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /spinup/utils/logx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/utils/logx.py -------------------------------------------------------------------------------- /spinup/utils/mpi_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/utils/mpi_tools.py -------------------------------------------------------------------------------- /spinup/utils/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/utils/plot.py -------------------------------------------------------------------------------- /spinup/utils/run_entrypoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/utils/run_entrypoint.py -------------------------------------------------------------------------------- /spinup/utils/run_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/utils/run_utils.py -------------------------------------------------------------------------------- /spinup/utils/serialization_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/utils/serialization_utils.py -------------------------------------------------------------------------------- /spinup/utils/test_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/utils/test_policy.py -------------------------------------------------------------------------------- /spinup/version.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/spinup/version.py -------------------------------------------------------------------------------- /test/test_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/test/test_ppo.py -------------------------------------------------------------------------------- /travis_setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/robintyh1/icml2021-pengqlambda/HEAD/travis_setup.sh --------------------------------------------------------------------------------