{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/openai-gym","name":"OpenAI Gym","slug":"openai-gym","description_markdown":"An open-source toolkit from OpenAI that implements several Reinforcement Learning benchmarks including: classic control, Atari, Robotics and MuJoCo tasks.\r\n\r\n(Description by [Evolutionary learning of interpretable decision trees](https://paperswithcode.com/paper/evolutionary-learning-of-interpretable))\r\n\r\n(Image Credit: [OpenAI Gym](https://gym.openai.com/))","categories":[{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":382,"papers_with_code":179,"benchmarks":17,"benchmark_tables_in_archive":17,"benchmark_tables_shown":17,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/openai-gym-on-ant-v4","slug":"openai-gym-on-ant-v4","dataset":"Ant-v4","dataset_url":null,"rows_in_archive":5,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"MEow","paper_title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","paper_url":"/paper/maximum-entropy-reinforcement-learning-via","paper_date":"2024-05-22","arxiv_id":"2405.13629","code_links":[{"title":"ChienFeng-hub/meow","url":"https://github.com/ChienFeng-hub/meow"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-halfcheetah-v4","slug":"openai-gym-on-halfcheetah-v4","dataset":"HalfCheetah-v4","dataset_url":null,"rows_in_archive":5,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"SAC","paper_title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","paper_url":"/paper/soft-actor-critic-off-policy-maximum-entropy","paper_date":"2018-01-04","arxiv_id":"1801.01290","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/sac.py"},{"title":"pytorch/rl","url":"https://github.com/pytorch/rl/tree/main/examples/sac"},{"title":"facebookresearch/rl","url":"https://github.com/facebookresearch/rl/blob/main/examples/sac/sac.py"},{"title":"quantumiracle/Popular-RL-Algorithms","url":"https://github.com/quantumiracle/Popular-RL-Algorithms"},{"title":"haarnoja/sac","url":"https://github.com/haarnoja/sac"},{"title":"MrSyee/pg-is-all-you-need","url":"https://github.com/MrSyee/pg-is-all-you-need"},{"title":"Rafael1s/Deep-Reinforcement-Learning-Udacity","url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity"},{"title":"pranz24/pytorch-soft-actor-critic","url":"https://github.com/pranz24/pytorch-soft-actor-critic"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"ikostrikov/jax-rl","url":"https://github.com/ikostrikov/jax-rl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"trackmania-rl/tmrl","url":"https://github.com/trackmania-rl/tmrl"},{"title":"Kaixhin/imitation-learning","url":"https://github.com/Kaixhin/imitation-learning"},{"title":"araffin/sbx","url":"https://github.com/araffin/sbx"},{"title":"andrejorsula/drl_grasping","url":"https://github.com/andrejorsula/drl_grasping"},{"title":"BY571/Soft-Actor-Critic-and-Extensions","url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions"},{"title":"ShawK91/Evolutionary-Reinforcement-Learning","url":"https://github.com/ShawK91/Evolutionary-Reinforcement-Learning"},{"title":"ShawK91/erl_paper_nips18","url":"https://github.com/ShawK91/erl_paper_nips18"},{"title":"ku2482/gail-airl-ppo.pytorch","url":"https://github.com/ku2482/gail-airl-ppo.pytorch"},{"title":"learn-to-race/l2r","url":"https://github.com/learn-to-race/l2r"},{"title":"dasgringuen/assetto_corsa_gym","url":"https://github.com/dasgringuen/assetto_corsa_gym"},{"title":"polixir/NeoRL","url":"https://github.com/polixir/NeoRL"},{"title":"toshikwa/soft-actor-critic.pytorch","url":"https://github.com/toshikwa/soft-actor-critic.pytorch"},{"title":"ku2482/soft-actor-critic.pytorch","url":"https://github.com/ku2482/soft-actor-critic.pytorch"},{"title":"ku2482/rljax","url":"https://github.com/ku2482/rljax"},{"title":"jakegrigsby/deep_control","url":"https://github.com/jakegrigsby/deep_control/blob/master/deep_control/sac.py"},{"title":"ac-93/soft-actor-critic","url":"https://github.com/ac-93/soft-actor-critic"},{"title":"RLAgent/state-marginal-matching","url":"https://github.com/RLAgent/state-marginal-matching"},{"title":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum"},{"title":"FOCAL-ICLR/FOCAL-ICLR","url":"https://github.com/FOCAL-ICLR/FOCAL-ICLR"},{"title":"lanqingli1993/focal-iclr","url":"https://github.com/lanqingli1993/focal-iclr"},{"title":"toshikwa/discor.pytorch","url":"https://github.com/toshikwa/discor.pytorch"},{"title":"ku2482/discor.pytorch","url":"https://github.com/ku2482/discor.pytorch"},{"title":"tilkb/thermoai","url":"https://github.com/tilkb/thermoai"},{"title":"kdally/fault-tolerant-flight-control-drl","url":"https://github.com/kdally/fault-tolerant-flight-control-drl"},{"title":"kairproject/kair_algorithms_draft","url":"https://github.com/kairproject/kair_algorithms_draft"},{"title":"fdcl-gwu/gym-rotor","url":"https://github.com/fdcl-gwu/gym-rotor"},{"title":"roythuly/obac","url":"https://github.com/roythuly/obac"},{"title":"kushagra06/SAC","url":"https://github.com/kushagra06/SAC"},{"title":"yining043/SAC-discrete","url":"https://github.com/yining043/SAC-discrete"},{"title":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning"},{"title":"AutumnWu/Streamlined-Off-Policy-Learning","url":"https://github.com/AutumnWu/Streamlined-Off-Policy-Learning"},{"title":"core-robotics-lab/icct","url":"https://github.com/core-robotics-lab/icct"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/sac"},{"title":"ku2482/rltorch","url":"https://github.com/ku2482/rltorch"},{"title":"baturaysaglam/la3p","url":"https://github.com/baturaysaglam/la3p"},{"title":"seungju-k1m/sac-td3-td7","url":"https://github.com/seungju-k1m/sac-td3-td7"},{"title":"X3N4/car_racer","url":"https://github.com/X3N4/car_racer"},{"title":"timoklein/car_racer","url":"https://github.com/timoklein/car_racer"},{"title":"moreanp/csro","url":"https://github.com/moreanp/csro"},{"title":"ajaysub110/rl-pytorch","url":"https://github.com/ajaysub110/rl-pytorch"},{"title":"watchernyu/spinningup-drl-prototyping","url":"https://github.com/watchernyu/spinningup-drl-prototyping"},{"title":"tliu1997/rnac","url":"https://github.com/tliu1997/rnac"},{"title":"thomashirtz/pytorch-soft-actor-critic","url":"https://github.com/thomashirtz/pytorch-soft-actor-critic"},{"title":"thomashirtz/soft-actor-critic","url":"https://github.com/thomashirtz/soft-actor-critic"},{"title":"ccolas/rl_stats","url":"https://github.com/ccolas/rl_stats"},{"title":"nagisazj/idaq_public","url":"https://github.com/nagisazj/idaq_public"},{"title":"Ipsedo/EvoMotion","url":"https://github.com/Ipsedo/EvoMotion"},{"title":"lucadellalib/sac-beta","url":"https://github.com/lucadellalib/sac-beta"},{"title":"h-aboutalebi/SparceReward","url":"https://github.com/h-aboutalebi/SparceReward"},{"title":"garyzyr001/rethinking-airl","url":"https://github.com/garyzyr001/rethinking-airl"},{"title":"flowersteam/rl_stats","url":"https://github.com/flowersteam/rl_stats"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"yimingpeng/sac-master","url":"https://github.com/yimingpeng/sac-master"},{"title":"MarsEleven/car_racer_RL","url":"https://github.com/MarsEleven/car_racer_RL"},{"title":"yhisaki/average-reward-drl","url":"https://github.com/yhisaki/average-reward-drl"},{"title":"AmmarFayad/Behavioral-Actor-Critic","url":"https://github.com/AmmarFayad/Behavioral-Actor-Critic"},{"title":"autumnwu/aggressive-q-learning-with-ensembles","url":"https://github.com/autumnwu/aggressive-q-learning-with-ensembles"},{"title":"tarod13/SAC","url":"https://github.com/tarod13/SAC"},{"title":"Steinheilig/Imbiss","url":"https://github.com/Steinheilig/Imbiss"},{"title":"tmjeong1103/RL_with_RAY","url":"https://github.com/tmjeong1103/RL_with_RAY"},{"title":"QuentinVacher-rl/SoftActorCritic-in-Cpp-using-LibTorch","url":"https://github.com/QuentinVacher-rl/SoftActorCritic-in-Cpp-using-LibTorch"},{"title":"SaminYeasar/off_policy_ac","url":"https://github.com/SaminYeasar/off_policy_ac"},{"title":"lollcat/Soft-Actor-Critic","url":"https://github.com/lollcat/Soft-Actor-Critic"},{"title":"donamin/llc","url":"https://github.com/donamin/llc"},{"title":"susan-amin/SparseBaseline1","url":"https://github.com/susan-amin/SparseBaseline1"},{"title":"hyunin-lee/ForecasterSAC","url":"https://github.com/hyunin-lee/ForecasterSAC"},{"title":"cindycia/Atari-SAC-Discrete","url":"https://github.com/cindycia/Atari-SAC-Discrete"},{"title":"mxblr/DeepRLHockey","url":"https://github.com/mxblr/DeepRLHockey"},{"title":"rk1998/robot-sac","url":"https://github.com/rk1998/robot-sac"},{"title":"sunfex/weighted-sac","url":"https://github.com/sunfex/weighted-sac"}],"syntology":{"n":148,"n_ran":91,"n_constructed":61,"n_ran_checked":73,"n_instrument":18,"n_unverified":57,"n_honours":3,"n_violates":1,"n_no_contract":69,"n_pointer_only":66,"phrase":"91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified","sample_list":"/paper/soft-actor-critic-off-policy-maximum-entropy#ran","syntology_url":"https://syntology.ai/paper/1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"}},"official":{"repos":["haarnoja/sac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/openai-gym-on-hopper-v4","slug":"openai-gym-on-hopper-v4","dataset":"Hopper-v4","dataset_url":null,"rows_in_archive":5,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"MEow","paper_title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","paper_url":"/paper/maximum-entropy-reinforcement-learning-via","paper_date":"2024-05-22","arxiv_id":"2405.13629","code_links":[{"title":"ChienFeng-hub/meow","url":"https://github.com/ChienFeng-hub/meow"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-humanoid-v4","slug":"openai-gym-on-humanoid-v4","dataset":"Humanoid-v4","dataset_url":null,"rows_in_archive":5,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"MEow","paper_title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","paper_url":"/paper/maximum-entropy-reinforcement-learning-via","paper_date":"2024-05-22","arxiv_id":"2405.13629","code_links":[{"title":"ChienFeng-hub/meow","url":"https://github.com/ChienFeng-hub/meow"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-walker2d-v4","slug":"openai-gym-on-walker2d-v4","dataset":"Walker2d-v4","dataset_url":null,"rows_in_archive":5,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"SAC","paper_title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","paper_url":"/paper/soft-actor-critic-off-policy-maximum-entropy","paper_date":"2018-01-04","arxiv_id":"1801.01290","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/sac.py"},{"title":"pytorch/rl","url":"https://github.com/pytorch/rl/tree/main/examples/sac"},{"title":"facebookresearch/rl","url":"https://github.com/facebookresearch/rl/blob/main/examples/sac/sac.py"},{"title":"quantumiracle/Popular-RL-Algorithms","url":"https://github.com/quantumiracle/Popular-RL-Algorithms"},{"title":"haarnoja/sac","url":"https://github.com/haarnoja/sac"},{"title":"MrSyee/pg-is-all-you-need","url":"https://github.com/MrSyee/pg-is-all-you-need"},{"title":"Rafael1s/Deep-Reinforcement-Learning-Udacity","url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity"},{"title":"pranz24/pytorch-soft-actor-critic","url":"https://github.com/pranz24/pytorch-soft-actor-critic"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"ikostrikov/jax-rl","url":"https://github.com/ikostrikov/jax-rl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"trackmania-rl/tmrl","url":"https://github.com/trackmania-rl/tmrl"},{"title":"Kaixhin/imitation-learning","url":"https://github.com/Kaixhin/imitation-learning"},{"title":"araffin/sbx","url":"https://github.com/araffin/sbx"},{"title":"andrejorsula/drl_grasping","url":"https://github.com/andrejorsula/drl_grasping"},{"title":"BY571/Soft-Actor-Critic-and-Extensions","url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions"},{"title":"ShawK91/Evolutionary-Reinforcement-Learning","url":"https://github.com/ShawK91/Evolutionary-Reinforcement-Learning"},{"title":"ShawK91/erl_paper_nips18","url":"https://github.com/ShawK91/erl_paper_nips18"},{"title":"ku2482/gail-airl-ppo.pytorch","url":"https://github.com/ku2482/gail-airl-ppo.pytorch"},{"title":"learn-to-race/l2r","url":"https://github.com/learn-to-race/l2r"},{"title":"dasgringuen/assetto_corsa_gym","url":"https://github.com/dasgringuen/assetto_corsa_gym"},{"title":"polixir/NeoRL","url":"https://github.com/polixir/NeoRL"},{"title":"toshikwa/soft-actor-critic.pytorch","url":"https://github.com/toshikwa/soft-actor-critic.pytorch"},{"title":"ku2482/soft-actor-critic.pytorch","url":"https://github.com/ku2482/soft-actor-critic.pytorch"},{"title":"ku2482/rljax","url":"https://github.com/ku2482/rljax"},{"title":"jakegrigsby/deep_control","url":"https://github.com/jakegrigsby/deep_control/blob/master/deep_control/sac.py"},{"title":"ac-93/soft-actor-critic","url":"https://github.com/ac-93/soft-actor-critic"},{"title":"RLAgent/state-marginal-matching","url":"https://github.com/RLAgent/state-marginal-matching"},{"title":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum"},{"title":"FOCAL-ICLR/FOCAL-ICLR","url":"https://github.com/FOCAL-ICLR/FOCAL-ICLR"},{"title":"lanqingli1993/focal-iclr","url":"https://github.com/lanqingli1993/focal-iclr"},{"title":"toshikwa/discor.pytorch","url":"https://github.com/toshikwa/discor.pytorch"},{"title":"ku2482/discor.pytorch","url":"https://github.com/ku2482/discor.pytorch"},{"title":"tilkb/thermoai","url":"https://github.com/tilkb/thermoai"},{"title":"kdally/fault-tolerant-flight-control-drl","url":"https://github.com/kdally/fault-tolerant-flight-control-drl"},{"title":"kairproject/kair_algorithms_draft","url":"https://github.com/kairproject/kair_algorithms_draft"},{"title":"fdcl-gwu/gym-rotor","url":"https://github.com/fdcl-gwu/gym-rotor"},{"title":"roythuly/obac","url":"https://github.com/roythuly/obac"},{"title":"kushagra06/SAC","url":"https://github.com/kushagra06/SAC"},{"title":"yining043/SAC-discrete","url":"https://github.com/yining043/SAC-discrete"},{"title":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning"},{"title":"AutumnWu/Streamlined-Off-Policy-Learning","url":"https://github.com/AutumnWu/Streamlined-Off-Policy-Learning"},{"title":"core-robotics-lab/icct","url":"https://github.com/core-robotics-lab/icct"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/sac"},{"title":"ku2482/rltorch","url":"https://github.com/ku2482/rltorch"},{"title":"baturaysaglam/la3p","url":"https://github.com/baturaysaglam/la3p"},{"title":"seungju-k1m/sac-td3-td7","url":"https://github.com/seungju-k1m/sac-td3-td7"},{"title":"X3N4/car_racer","url":"https://github.com/X3N4/car_racer"},{"title":"timoklein/car_racer","url":"https://github.com/timoklein/car_racer"},{"title":"moreanp/csro","url":"https://github.com/moreanp/csro"},{"title":"ajaysub110/rl-pytorch","url":"https://github.com/ajaysub110/rl-pytorch"},{"title":"watchernyu/spinningup-drl-prototyping","url":"https://github.com/watchernyu/spinningup-drl-prototyping"},{"title":"tliu1997/rnac","url":"https://github.com/tliu1997/rnac"},{"title":"thomashirtz/pytorch-soft-actor-critic","url":"https://github.com/thomashirtz/pytorch-soft-actor-critic"},{"title":"thomashirtz/soft-actor-critic","url":"https://github.com/thomashirtz/soft-actor-critic"},{"title":"ccolas/rl_stats","url":"https://github.com/ccolas/rl_stats"},{"title":"nagisazj/idaq_public","url":"https://github.com/nagisazj/idaq_public"},{"title":"Ipsedo/EvoMotion","url":"https://github.com/Ipsedo/EvoMotion"},{"title":"lucadellalib/sac-beta","url":"https://github.com/lucadellalib/sac-beta"},{"title":"h-aboutalebi/SparceReward","url":"https://github.com/h-aboutalebi/SparceReward"},{"title":"garyzyr001/rethinking-airl","url":"https://github.com/garyzyr001/rethinking-airl"},{"title":"flowersteam/rl_stats","url":"https://github.com/flowersteam/rl_stats"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"yimingpeng/sac-master","url":"https://github.com/yimingpeng/sac-master"},{"title":"MarsEleven/car_racer_RL","url":"https://github.com/MarsEleven/car_racer_RL"},{"title":"yhisaki/average-reward-drl","url":"https://github.com/yhisaki/average-reward-drl"},{"title":"AmmarFayad/Behavioral-Actor-Critic","url":"https://github.com/AmmarFayad/Behavioral-Actor-Critic"},{"title":"autumnwu/aggressive-q-learning-with-ensembles","url":"https://github.com/autumnwu/aggressive-q-learning-with-ensembles"},{"title":"tarod13/SAC","url":"https://github.com/tarod13/SAC"},{"title":"Steinheilig/Imbiss","url":"https://github.com/Steinheilig/Imbiss"},{"title":"tmjeong1103/RL_with_RAY","url":"https://github.com/tmjeong1103/RL_with_RAY"},{"title":"QuentinVacher-rl/SoftActorCritic-in-Cpp-using-LibTorch","url":"https://github.com/QuentinVacher-rl/SoftActorCritic-in-Cpp-using-LibTorch"},{"title":"SaminYeasar/off_policy_ac","url":"https://github.com/SaminYeasar/off_policy_ac"},{"title":"lollcat/Soft-Actor-Critic","url":"https://github.com/lollcat/Soft-Actor-Critic"},{"title":"donamin/llc","url":"https://github.com/donamin/llc"},{"title":"susan-amin/SparseBaseline1","url":"https://github.com/susan-amin/SparseBaseline1"},{"title":"hyunin-lee/ForecasterSAC","url":"https://github.com/hyunin-lee/ForecasterSAC"},{"title":"cindycia/Atari-SAC-Discrete","url":"https://github.com/cindycia/Atari-SAC-Discrete"},{"title":"mxblr/DeepRLHockey","url":"https://github.com/mxblr/DeepRLHockey"},{"title":"rk1998/robot-sac","url":"https://github.com/rk1998/robot-sac"},{"title":"sunfex/weighted-sac","url":"https://github.com/sunfex/weighted-sac"}],"syntology":{"n":148,"n_ran":91,"n_constructed":61,"n_ran_checked":73,"n_instrument":18,"n_unverified":57,"n_honours":3,"n_violates":1,"n_no_contract":69,"n_pointer_only":66,"phrase":"91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified","sample_list":"/paper/soft-actor-critic-off-policy-maximum-entropy#ran","syntology_url":"https://syntology.ai/paper/1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"}},"official":{"repos":["haarnoja/sac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/openai-gym-on-ant-v2","slug":"openai-gym-on-ant-v2","dataset":"Ant-v2","dataset_url":null,"rows_in_archive":2,"metrics":["Mean Reward","Average Decisions","Action Repetition"],"first_row_in_archive_order":{"model":"TLA","paper_title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","paper_url":"/paper/temporally-layered-architecture-for-efficient","paper_date":"2023-05-30","arxiv_id":"2305.18701","code_links":[{"title":"dee0512/Temporally-Layered-Architecture","url":"https://github.com/dee0512/Temporally-Layered-Architecture"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-cartpole-v1","slug":"openai-gym-on-cartpole-v1","dataset":"CartPole-v1","dataset_url":null,"rows_in_archive":2,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"Orthogonal decision tree","paper_title":"Evolutionary learning of interpretable decision trees","paper_url":"/paper/evolutionary-learning-of-interpretable","paper_date":"2020-12-14","arxiv_id":"2012.07723","code_links":[{"title":"leocus/ge_q_dts","url":"https://gitlab.com/leocus/ge_q_dts"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-halfcheetah-v2","slug":"openai-gym-on-halfcheetah-v2","dataset":"HalfCheetah-v2","dataset_url":null,"rows_in_archive":2,"metrics":["Mean Reward","Average Decisions","Action Repetition"],"first_row_in_archive_order":{"model":"TLA","paper_title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","paper_url":"/paper/temporally-layered-architecture-for-efficient","paper_date":"2023-05-30","arxiv_id":"2305.18701","code_links":[{"title":"dee0512/Temporally-Layered-Architecture","url":"https://github.com/dee0512/Temporally-Layered-Architecture"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-hopper-v2","slug":"openai-gym-on-hopper-v2","dataset":"Hopper-v2","dataset_url":null,"rows_in_archive":2,"metrics":["Mean Reward","Average Decisions","Action Repetition"],"first_row_in_archive_order":{"model":"TLA","paper_title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","paper_url":"/paper/temporally-layered-architecture-for-efficient","paper_date":"2023-05-30","arxiv_id":"2305.18701","code_links":[{"title":"dee0512/Temporally-Layered-Architecture","url":"https://github.com/dee0512/Temporally-Layered-Architecture"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-lunarlander-v2","slug":"openai-gym-on-lunarlander-v2","dataset":"LunarLander-v2","dataset_url":null,"rows_in_archive":2,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"Oblique decision tree","paper_title":"Evolutionary learning of interpretable decision trees","paper_url":"/paper/evolutionary-learning-of-interpretable","paper_date":"2020-12-14","arxiv_id":"2012.07723","code_links":[{"title":"leocus/ge_q_dts","url":"https://gitlab.com/leocus/ge_q_dts"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-mountain-car","slug":"openai-gym-on-mountain-car","dataset":"Mountain Car","dataset_url":null,"rows_in_archive":2,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"Orthogonal decision tree","paper_title":"Evolutionary learning of interpretable decision trees","paper_url":"/paper/evolutionary-learning-of-interpretable","paper_date":"2020-12-14","arxiv_id":"2012.07723","code_links":[{"title":"leocus/ge_q_dts","url":"https://gitlab.com/leocus/ge_q_dts"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-pendulum-v1","slug":"openai-gym-on-pendulum-v1","dataset":"Pendulum-v1","dataset_url":"/dataset/openai-gym","rows_in_archive":2,"metrics":["Mean Reward","Average Decisions","Action Repetition"],"first_row_in_archive_order":{"model":"TLA with Hierarchical Reward Functions","paper_title":"Creating Hierarchical Dispositions of Needs in an Agent","paper_url":"/paper/creating-hierarchical-dispositions-of-needs","paper_date":"2024-11-23","arxiv_id":"2412.00044","code_links":[{"title":"TofaraMoyo/Heirachical-Reward-Functions","url":"https://github.com/TofaraMoyo/Heirachical-Reward-Functions"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-walker2d-v2","slug":"openai-gym-on-walker2d-v2","dataset":"Walker2d-v2","dataset_url":null,"rows_in_archive":2,"metrics":["Mean Reward","Average Decisions","Action Repetition"],"first_row_in_archive_order":{"model":"AWR","paper_title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","paper_url":"/paper/advantage-weighted-regression-simple-and","paper_date":"2019-10-01","arxiv_id":"1910.00177","code_links":[{"title":"google/trax","url":"https://github.com/google/trax"},{"title":"xbpeng/awr","url":"https://github.com/xbpeng/awr"},{"title":"nvlabs/gbrl_sb3","url":"https://github.com/nvlabs/gbrl_sb3"},{"title":"NitinVishalKulkarni/OfflineReinforcementLearning","url":"https://github.com/NitinVishalKulkarni/OfflineReinforcementLearning"},{"title":"fomorians-oss/awr","url":"https://github.com/fomorians-oss/awr"},{"title":"peisuke/awr","url":"https://github.com/peisuke/awr"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-humanoid-v2","slug":"openai-gym-on-humanoid-v2","dataset":"Humanoid-v2","dataset_url":null,"rows_in_archive":1,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"AWR","paper_title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","paper_url":"/paper/advantage-weighted-regression-simple-and","paper_date":"2019-10-01","arxiv_id":"1910.00177","code_links":[{"title":"google/trax","url":"https://github.com/google/trax"},{"title":"xbpeng/awr","url":"https://github.com/xbpeng/awr"},{"title":"nvlabs/gbrl_sb3","url":"https://github.com/nvlabs/gbrl_sb3"},{"title":"NitinVishalKulkarni/OfflineReinforcementLearning","url":"https://github.com/NitinVishalKulkarni/OfflineReinforcementLearning"},{"title":"fomorians-oss/awr","url":"https://github.com/fomorians-oss/awr"},{"title":"peisuke/awr","url":"https://github.com/peisuke/awr"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-inverteddoublependulum-v2","slug":"openai-gym-on-inverteddoublependulum-v2","dataset":"InvertedDoublePendulum-v2","dataset_url":null,"rows_in_archive":1,"metrics":["Mean Reward","Average Decisions","Action Repetition"],"first_row_in_archive_order":{"model":"TLA","paper_title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","paper_url":"/paper/temporally-layered-architecture-for-efficient","paper_date":"2023-05-30","arxiv_id":"2305.18701","code_links":[{"title":"dee0512/Temporally-Layered-Architecture","url":"https://github.com/dee0512/Temporally-Layered-Architecture"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-invertedpendulum-v2","slug":"openai-gym-on-invertedpendulum-v2","dataset":"InvertedPendulum-v2","dataset_url":null,"rows_in_archive":1,"metrics":["Mean Reward","Average Decisions","Action Repetition"],"first_row_in_archive_order":{"model":"TLA","paper_title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","paper_url":"/paper/temporally-layered-architecture-for-efficient","paper_date":"2023-05-30","arxiv_id":"2305.18701","code_links":[{"title":"dee0512/Temporally-Layered-Architecture","url":"https://github.com/dee0512/Temporally-Layered-Architecture"}],"syntology":null}},{"leaderboard":"/sota/openai-gym-on-mountaincarcontinuous-v0","slug":"openai-gym-on-mountaincarcontinuous-v0","dataset":"MountainCarContinuous-v0","dataset_url":null,"rows_in_archive":1,"metrics":["Mean Reward","Average Decisions","Action Repetition"],"first_row_in_archive_order":{"model":"TLA","paper_title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","paper_url":"/paper/temporally-layered-architecture-for-efficient","paper_date":"2023-05-30","arxiv_id":"2305.18701","code_links":[{"title":"dee0512/Temporally-Layered-Architecture","url":"https://github.com/dee0512/Temporally-Layered-Architecture"}],"syntology":null}}],"datasets":[{"url":"/dataset/openai-gym","name":"OpenAI Gym","full_name":"OpenAI Gym","num_papers_in_archive":1305},{"url":"/dataset/industrial-benchmark","name":"Industrial Benchmark","full_name":"","num_papers_in_archive":13},{"url":"/dataset/mo-gymnasium","name":"MO-Gymnasium","full_name":"","num_papers_in_archive":8}],"subtasks":[{"url":"/task/acrobot","name":"Acrobot"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":382,"of_with_code":179,"tagged_in_all":382,"counts":{"archive_papers_tagged":382,"with_a_code_link":179,"where_syntology_ran_a_sample":43,"not_listed_spam_title":0,"listed":382,"listed_where_code_ran":43,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":36,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":36,"listed_every_run_a_failure_of_syntologys_instrument":7,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/proximal-policy-optimization-algorithms","slug":"proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","arxiv_id":"1707.06347","repositories_listed":188,"syntology":{"n":176,"n_ran":99,"n_constructed":53,"n_ran_checked":71,"n_instrument":28,"n_unverified":77,"n_honours":7,"n_violates":2,"n_no_contract":62,"n_pointer_only":94,"phrase":"99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified","sample_list":"/paper/proximal-policy-optimization-algorithms#ran","syntology_url":"https://syntology.ai/paper/1707.06347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06347"}},"official":null}},{"url":"/paper/continuous-control-with-deep-reinforcement","slug":"continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","arxiv_id":"1509.02971","repositories_listed":161,"syntology":{"n":306,"n_ran":163,"n_constructed":126,"n_ran_checked":152,"n_instrument":11,"n_unverified":143,"n_honours":3,"n_violates":0,"n_no_contract":149,"n_pointer_only":163,"phrase":"163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified","sample_list":"/paper/continuous-control-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1509.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.02971"}},"official":null}},{"url":"/paper/soft-actor-critic-off-policy-maximum-entropy","slug":"soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","arxiv_id":"1801.01290","repositories_listed":86,"syntology":{"n":148,"n_ran":91,"n_constructed":61,"n_ran_checked":73,"n_instrument":18,"n_unverified":57,"n_honours":3,"n_violates":1,"n_no_contract":69,"n_pointer_only":66,"phrase":"91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified","sample_list":"/paper/soft-actor-critic-off-policy-maximum-entropy#ran","syntology_url":"https://syntology.ai/paper/1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"}},"official":{"repos":["haarnoja/sac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/addressing-function-approximation-error-in","slug":"addressing-function-approximation-error-in","title":"Addressing Function Approximation Error in Actor-Critic Methods","date":"2018-02-26","arxiv_id":"1802.09477","repositories_listed":67,"syntology":{"n":36,"n_ran":26,"n_constructed":0,"n_ran_checked":20,"n_instrument":6,"n_unverified":10,"n_honours":1,"n_violates":2,"n_no_contract":17,"n_pointer_only":21,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 2 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/addressing-function-approximation-error-in#ran","syntology_url":"https://syntology.ai/paper/1802.09477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09477"}},"official":{"repos":["sfujim/TD3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/multi-goal-reinforcement-learning-challenging","slug":"multi-goal-reinforcement-learning-challenging","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","date":"2018-02-26","arxiv_id":"1802.09464","repositories_listed":28,"syntology":null},{"url":"/paper/decision-transformer-reinforcement-learning","slug":"decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","arxiv_id":"2106.01345","repositories_listed":20,"syntology":{"n":26,"n_ran":17,"n_constructed":10,"n_ran_checked":12,"n_instrument":5,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":8,"phrase":"17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/decision-transformer-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.01345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01345"}},"official":{"repos":["kzl/decision-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/advantage-weighted-regression-simple-and","slug":"advantage-weighted-regression-simple-and","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","date":"2019-10-01","arxiv_id":"1910.00177","repositories_listed":6,"syntology":null},{"url":"/paper/deep-recurrent-q-learning-for-partially","slug":"deep-recurrent-q-learning-for-partially","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","date":"2015-07-23","arxiv_id":"1507.06527","repositories_listed":5,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/deep-recurrent-q-learning-for-partially#ran","syntology_url":"https://syntology.ai/paper/1507.06527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1507.06527"}},"official":null}},{"url":"/paper/comparing-the-efficacy-of-fine-tuning-and","slug":"comparing-the-efficacy-of-fine-tuning-and","title":"Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation","date":"2023-06-23","arxiv_id":"2306.13554","repositories_listed":4,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-playing-25d","slug":"deep-reinforcement-learning-for-playing-25d","title":"Deep Reinforcement Learning for Playing 2.5D Fighting Games","date":"2018-05-05","arxiv_id":"1805.02070","repositories_listed":4,"syntology":null},{"url":"/paper/learning-to-fly-a-gym-environment-with","slug":"learning-to-fly-a-gym-environment-with","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","date":"2021-03-03","arxiv_id":"2103.02142","repositories_listed":3,"syntology":null},{"url":"/paper/implicit-distributional-reinforcement","slug":"implicit-distributional-reinforcement","title":"Implicit Distributional Reinforcement Learning","date":"2020-07-13","arxiv_id":"2007.06159","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/implicit-distributional-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2007.06159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06159"}},"official":{"repos":["zhougroup/IDAC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/torchbeast-a-pytorch-platform-for-distributed","slug":"torchbeast-a-pytorch-platform-for-distributed","title":"TorchBeast: A PyTorch Platform for Distributed RL","date":"2019-10-08","arxiv_id":"1910.03552","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/torchbeast-a-pytorch-platform-for-distributed#ran","syntology_url":"https://syntology.ai/paper/1910.03552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.03552"}},"official":{"repos":["heiner/scalable_agent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/maximum-entropy-regularized-multi-goal","slug":"maximum-entropy-regularized-multi-goal","title":"Maximum Entropy-Regularized Multi-Goal Reinforcement Learning","date":"2019-05-21","arxiv_id":"1905.08786","repositories_listed":3,"syntology":null},{"url":"/paper/hierarchical-decision-mamba","slug":"hierarchical-decision-mamba","title":"Decision Mamba Architectures","date":"2024-05-13","arxiv_id":"2405.07943","repositories_listed":2,"syntology":null},{"url":"/paper/for-sale-state-action-representation-learning-1","slug":"for-sale-state-action-representation-learning-1","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","date":"2023-06-04","arxiv_id":"2306.02451","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/for-sale-state-action-representation-learning-1#ran","syntology_url":"https://syntology.ai/paper/2306.02451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02451"}},"official":{"repos":["sfujim/td7"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/mo-gym-a-library-of-multi-objective","slug":"mo-gym-a-library-of-multi-objective","title":"MO-Gym: A Library of Multi-Objective Reinforcement Learning Environments","date":"2022-11-30","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/pyrddlgym-from-rddl-to-gym-environments","slug":"pyrddlgym-from-rddl-to-gym-environments","title":"pyRDDLGym: From RDDL to Gym Environments","date":"2022-11-11","arxiv_id":"2211.05939","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pyrddlgym-from-rddl-to-gym-environments#ran","syntology_url":"https://syntology.ai/paper/2211.05939","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05939"}},"official":{"repos":["ataitler/pyrddlgym","pyrddlgym-project/pyrddlgym"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cool-mc-a-comprehensive-tool-for","slug":"cool-mc-a-comprehensive-tool-for","title":"COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checking","date":"2022-09-15","arxiv_id":"2209.07133","repositories_listed":2,"syntology":null},{"url":"/paper/bsac-bayesian-strategy-network-based-soft","slug":"bsac-bayesian-strategy-network-based-soft","title":"Bayesian Soft Actor-Critic: A Directed Acyclic Strategy Graph Based Deep Reinforcement Learning","date":"2022-08-11","arxiv_id":"2208.06033","repositories_listed":2,"syntology":null},{"url":"/paper/quantum-deep-reinforcement-learning-for-robot","slug":"quantum-deep-reinforcement-learning-for-robot","title":"Quantum Deep Reinforcement Learning for Robot Navigation Tasks","date":"2022-02-24","arxiv_id":"2202.12180","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/quantum-deep-reinforcement-learning-for-robot#ran","syntology_url":"https://syntology.ai/paper/2202.12180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.12180"}},"official":{"repos":["dfki-ric-quantum/qdrl-turtlebot-env","dfki-ric-quantum/qdrl-turtlebot-eval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/marsexplorer-exploration-of-unknown-terrains","slug":"marsexplorer-exploration-of-unknown-terrains","title":"MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments","date":"2021-07-21","arxiv_id":"2107.09996","repositories_listed":2,"syntology":null},{"url":"/paper/an-open-source-multi-goal-reinforcement","slug":"an-open-source-multi-goal-reinforcement","title":"An Open-Source Multi-Goal Reinforcement Learning Environment for Robotic Manipulation with Pybullet","date":"2021-05-12","arxiv_id":"2105.05985","repositories_listed":2,"syntology":null},{"url":"/paper/cropgym-a-reinforcement-learning-environment","slug":"cropgym-a-reinforcement-learning-environment","title":"CropGym: a Reinforcement Learning Environment for Crop Management","date":"2021-04-09","arxiv_id":"2104.04326","repositories_listed":2,"syntology":null},{"url":"/paper/improving-model-based-reinforcement-learning","slug":"improving-model-based-reinforcement-learning","title":"Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision","date":"2021-02-10","arxiv_id":"2102.05599","repositories_listed":2,"syntology":null},{"url":"/paper/neurogenetic-programming-framework-for","slug":"neurogenetic-programming-framework-for","title":"Neurogenetic Programming Framework for Explainable Reinforcement Learning","date":"2021-02-08","arxiv_id":"2102.04231","repositories_listed":2,"syntology":null},{"url":"/paper/reinforcement-learning-for-control-of-valves","slug":"reinforcement-learning-for-control-of-valves","title":"Reinforcement Learning for Control of Valves","date":"2020-12-29","arxiv_id":"2012.14668","repositories_listed":2,"syntology":null},{"url":"/paper/softgym-benchmarking-deep-reinforcement","slug":"softgym-benchmarking-deep-reinforcement","title":"SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation","date":"2020-11-14","arxiv_id":"2011.07215","repositories_listed":2,"syntology":null},{"url":"/paper/ecole-a-gym-like-library-for-machine-learning","slug":"ecole-a-gym-like-library-for-machine-learning","title":"Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers","date":"2020-11-11","arxiv_id":"2011.06069","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ecole-a-gym-like-library-for-machine-learning#ran","syntology_url":"https://syntology.ai/paper/2011.06069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.06069"}},"official":{"repos":["ds4dm/ecole"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/epidemioptim-a-toolbox-for-the-optimization-1","slug":"epidemioptim-a-toolbox-for-the-optimization-1","title":"EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models","date":"2020-10-09","arxiv_id":"2010.04452","repositories_listed":2,"syntology":null},{"url":"/paper/reinforcement-learning-with-quantum","slug":"reinforcement-learning-with-quantum","title":"Reinforcement Learning with Quantum Variational Circuits","date":"2020-08-15","arxiv_id":"2008.07524","repositories_listed":2,"syntology":null},{"url":"/paper/reinforcement-learning-with-augmented-data","slug":"reinforcement-learning-with-augmented-data","title":"Reinforcement Learning with Augmented Data","date":"2020-04-30","arxiv_id":"2004.14990","repositories_listed":2,"syntology":{"n":24,"n_ran":21,"n_constructed":8,"n_ran_checked":9,"n_instrument":12,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":21,"phrase":"21 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reinforcement-learning-with-augmented-data#ran","syntology_url":"https://syntology.ai/paper/2004.14990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14990"}},"official":null}},{"url":"/paper/pddlgym-gym-environments-from-pddl-problems","slug":"pddlgym-gym-environments-from-pddl-problems","title":"PDDLGym: Gym Environments from PDDL Problems","date":"2020-02-15","arxiv_id":"2002.06432","repositories_listed":2,"syntology":{"n":11,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/pddlgym-gym-environments-from-pddl-problems#ran","syntology_url":"https://syntology.ai/paper/2002.06432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06432"}},"official":{"repos":["tomsilver/pddlgym"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-reinforcement-learning-environment","slug":"towards-a-reinforcement-learning-environment","title":"Towards a Reinforcement Learning Environment Toolbox for Intelligent Electric Motor Control","date":"2019-10-21","arxiv_id":"1910.09434","repositories_listed":2,"syntology":null},{"url":"/paper/arena-a-toolkit-for-multi-agent-reinforcement","slug":"arena-a-toolkit-for-multi-agent-reinforcement","title":"Arena: a toolkit for Multi-Agent Reinforcement Learning","date":"2019-07-20","arxiv_id":"1907.09467","repositories_listed":2,"syntology":null},{"url":"/paper/playing-adaptively-against-stealthy-opponents","slug":"playing-adaptively-against-stealthy-opponents","title":"QFlip: An Adaptive Reinforcement Learning Strategy for the FlipIt Security Game","date":"2019-06-27","arxiv_id":"1906.11938","repositories_listed":2,"syntology":null},{"url":"/paper/moet-interpretable-and-verifiable","slug":"moet-interpretable-and-verifiable","title":"MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning","date":"2019-06-16","arxiv_id":"1906.06717","repositories_listed":2,"syntology":null},{"url":"/paper/190600535","slug":"190600535","title":"Towards Interactive Training of Non-Player Characters in Video Games","date":"2019-06-03","arxiv_id":"1906.00535","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reinforcement-learning-with-feedback","slug":"deep-reinforcement-learning-with-feedback","title":"Deep Reinforcement Learning with Feedback-based Exploration","date":"2019-03-14","arxiv_id":"1903.06151","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-general-video","slug":"deep-reinforcement-learning-for-general-video","title":"Deep Reinforcement Learning for General Video Game AI","date":"2018-06-06","arxiv_id":"1806.02448","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-reinforcement-learning-for-general-video#ran","syntology_url":"https://syntology.ai/paper/1806.02448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02448"}},"official":{"repos":["rubenrtorrado/GVGAI_GYM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/monte-carlo-tree-search-for-asymmetric-trees","slug":"monte-carlo-tree-search-for-asymmetric-trees","title":"Monte Carlo Tree Search for Asymmetric Trees","date":"2018-05-23","arxiv_id":"1805.09218","repositories_listed":2,"syntology":null},{"url":"/paper/recurrent-predictive-state-policy-networks","slug":"recurrent-predictive-state-policy-networks","title":"Recurrent Predictive State Policy Networks","date":"2018-03-05","arxiv_id":"1803.01489","repositories_listed":2,"syntology":null},{"url":"/paper/a-benchmark-environment-motivated-by","slug":"a-benchmark-environment-motivated-by","title":"A Benchmark Environment Motivated by Industrial Control Problems","date":"2017-09-27","arxiv_id":"1709.09480","repositories_listed":2,"syntology":null},{"url":"/paper/hddlgym-a-tool-for-studying-multi-agent","slug":"hddlgym-a-tool-for-studying-multi-agent","title":"HDDLGym: A Tool for Studying Multi-Agent Hierarchical Problems Defined in HDDL with OpenAI Gym","date":"2025-05-28","arxiv_id":"2505.22597","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10861","slug":"2505-10861","title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","date":"2025-05-16","arxiv_id":"2505.10861","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2505-10861#ran","syntology_url":"https://syntology.ai/paper/2505.10861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.10861"}},"official":{"repos":["duongnhatthang/llamagym"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mining-gym-a-configurable-rl-benchmarking","slug":"mining-gym-a-configurable-rl-benchmarking","title":"Mining-Gym: A Configurable RL Benchmarking Environment for Truck Dispatch Scheduling","date":"2025-03-24","arxiv_id":"2503.19195","repositories_listed":1,"syntology":null},{"url":"/paper/a-quantum-classical-reinforcement-learning","slug":"a-quantum-classical-reinforcement-learning","title":"A quantum-classical reinforcement learning model to play Atari games","date":"2024-12-11","arxiv_id":"2412.08725","repositories_listed":1,"syntology":null},{"url":"/paper/creating-hierarchical-dispositions-of-needs","slug":"creating-hierarchical-dispositions-of-needs","title":"Creating Hierarchical Dispositions of Needs in an Agent","date":"2024-11-23","arxiv_id":"2412.00044","repositories_listed":1,"syntology":null},{"url":"/paper/double-successive-over-relaxation-q-learning","slug":"double-successive-over-relaxation-q-learning","title":"Double Successive Over-Relaxation Q-Learning with an Extension to Deep Reinforcement Learning","date":"2024-09-10","arxiv_id":"2409.06356","repositories_listed":1,"syntology":null},{"url":"/paper/histogym-a-reinforcement-learning-environment","slug":"histogym-a-reinforcement-learning-environment","title":"HistoGym: A Reinforcement Learning Environment for Histopathological Image Analysis","date":"2024-08-16","arxiv_id":"2408.08847","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-as-decision-maker-exploring-multi-scale","slug":"mamba-as-decision-maker-exploring-multi-scale","title":"Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning","date":"2024-06-04","arxiv_id":"2406.02013","repositories_listed":1,"syntology":null},{"url":"/paper/ompo-a-unified-framework-for-rl-under-policy","slug":"ompo-a-unified-framework-for-rl-under-policy","title":"OMPO: A Unified Framework for RL under Policy and Dynamics Shifts","date":"2024-05-29","arxiv_id":"2405.19080","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ompo-a-unified-framework-for-rl-under-policy#ran","syntology_url":"https://syntology.ai/paper/2405.19080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19080"}},"official":{"repos":["roythuly/ompo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/maximum-entropy-reinforcement-learning-via","slug":"maximum-entropy-reinforcement-learning-via","title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","date":"2024-05-22","arxiv_id":"2405.13629","repositories_listed":1,"syntology":null},{"url":"/paper/swiftrl-towards-efficient-reinforcement","slug":"swiftrl-towards-efficient-reinforcement","title":"SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems","date":"2024-05-07","arxiv_id":"2405.03967","repositories_listed":1,"syntology":null},{"url":"/paper/more-3s-multimodal-based-offline","slug":"more-3s-multimodal-based-offline","title":"MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces","date":"2024-02-20","arxiv_id":"2402.12845","repositories_listed":1,"syntology":null},{"url":"/paper/decision-making-in-non-stationary-1","slug":"decision-making-in-non-stationary-1","title":"Decision Making in Non-Stationary Environments with Policy-Augmented Search","date":"2024-01-06","arxiv_id":"2401.03197","repositories_listed":1,"syntology":null},{"url":"/paper/rfrl-gym-a-reinforcement-learning-testbed-for","slug":"rfrl-gym-a-reinforcement-learning-testbed-for","title":"RFRL Gym: A Reinforcement Learning Testbed for Cognitive Radio Applications","date":"2023-12-20","arxiv_id":"2401.05406","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-performance-and-reliability","slug":"investigating-the-performance-and-reliability","title":"Investigating the Performance and Reliability, of the Q-Learning Algorithm in Various Unknown Environments","date":"2023-12-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/peer-learning-learning-complex-policies-in","slug":"peer-learning-learning-complex-policies-in","title":"Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations","date":"2023-12-15","arxiv_id":"2312.09950","repositories_listed":1,"syntology":null},{"url":"/paper/llf-bench-benchmark-for-interactive-learning","slug":"llf-bench-benchmark-for-interactive-learning","title":"LLF-Bench: Benchmark for Interactive Learning from Language Feedback","date":"2023-12-11","arxiv_id":"2312.06853","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llf-bench-benchmark-for-interactive-learning#ran","syntology_url":"https://syntology.ai/paper/2312.06853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06853"}},"official":null}},{"url":"/paper/optimizing-distributed-reinforcement-learning","slug":"optimizing-distributed-reinforcement-learning","title":"Efficient Parallel Reinforcement Learning Framework using the Reactor Model","date":"2023-12-07","arxiv_id":"2312.04704","repositories_listed":1,"syntology":null},{"url":"/paper/can-language-agents-be-alternatives-to-ppo-a","slug":"can-language-agents-be-alternatives-to-ppo-a","title":"Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym","date":"2023-12-06","arxiv_id":"2312.03290","repositories_listed":1,"syntology":null},{"url":"/paper/controlgym-large-scale-safety-critical","slug":"controlgym-large-scale-safety-critical","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","date":"2023-11-30","arxiv_id":"2311.18736","repositories_listed":1,"syntology":null},{"url":"/paper/guaranteeing-control-requirements-via-reward","slug":"guaranteeing-control-requirements-via-reward","title":"Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning","date":"2023-11-16","arxiv_id":"2311.10026","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-dimensions-confident-reachability","slug":"bridging-dimensions-confident-reachability","title":"Bridging Dimensions: Confident Reachability for High-Dimensional Controllers","date":"2023-11-08","arxiv_id":"2311.04843","repositories_listed":1,"syntology":null},{"url":"/paper/repairing-learning-enabled-controllers-while","slug":"repairing-learning-enabled-controllers-while","title":"Repairing Learning-Enabled Controllers While Preserving What Works","date":"2023-11-06","arxiv_id":"2311.03477","repositories_listed":1,"syntology":null},{"url":"/paper/sdgym-low-code-reinforcement-learning","slug":"sdgym-low-code-reinforcement-learning","title":"SDGym: Low-Code Reinforcement Learning Environments using System Dynamics Models","date":"2023-10-19","arxiv_id":"2310.12494","repositories_listed":1,"syntology":null},{"url":"/paper/offline-retraining-for-online-rl-decoupled","slug":"offline-retraining-for-online-rl-decoupled","title":"Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias","date":"2023-10-12","arxiv_id":"2310.08558","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/offline-retraining-for-online-rl-decoupled#ran","syntology_url":"https://syntology.ai/paper/2310.08558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08558"}},"official":{"repos":["MaxSobolMark/OOO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/qgym-a-gym-for-training-and-benchmarking-rl","slug":"qgym-a-gym-for-training-and-benchmarking-rl","title":"qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation","date":"2023-08-01","arxiv_id":"2308.02536","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-observation-policies-in-observation","slug":"dynamic-observation-policies-in-observation","title":"Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning","date":"2023-07-05","arxiv_id":"2307.02620","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/dynamic-observation-policies-in-observation#ran","syntology_url":"https://syntology.ai/paper/2307.02620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02620"}},"official":{"repos":["cbellinger27/learning-when-to-observe-in-rl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/sample-efficient-on-policy-imitation-learning","slug":"sample-efficient-on-policy-imitation-learning","title":"Mimicking Better by Matching the Approximate Action Distribution","date":"2023-06-16","arxiv_id":"2306.09805","repositories_listed":1,"syntology":null},{"url":"/paper/risk-aware-reward-shaping-of-reinforcement","slug":"risk-aware-reward-shaping-of-reinforcement","title":"Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving","date":"2023-06-05","arxiv_id":"2306.03220","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/risk-aware-reward-shaping-of-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2306.03220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03220"}},"official":{"repos":["zhang-zengjie/code_2023_iecon_shaping_wu"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/temporally-layered-architecture-for-efficient","slug":"temporally-layered-architecture-for-efficient","title":"Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures","date":"2023-05-30","arxiv_id":"2305.18701","repositories_listed":1,"syntology":null},{"url":"/paper/signal-novelty-detection-as-an-intrinsic","slug":"signal-novelty-detection-as-an-intrinsic","title":"Signal Novelty Detection as an Intrinsic Reward for Robotics","date":"2023-04-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generative-adversarial-neuroevolution-for","slug":"generative-adversarial-neuroevolution-for","title":"Generative Adversarial Neuroevolution for Control Behaviour Imitation","date":"2023-04-03","arxiv_id":"2304.12432","repositories_listed":1,"syntology":null},{"url":"/paper/neuroevolution-of-recurrent-architectures-on","slug":"neuroevolution-of-recurrent-architectures-on","title":"Neuroevolution of Recurrent Architectures on Control Tasks","date":"2023-04-03","arxiv_id":"2304.12431","repositories_listed":1,"syntology":null},{"url":"/paper/soft-bellman-equilibrium-in-affine-markov","slug":"soft-bellman-equilibrium-in-affine-markov","title":"Soft-Bellman Equilibrium in Affine Markov Games: Forward Solutions and Inverse Learning","date":"2023-03-31","arxiv_id":"2304.00163","repositories_listed":1,"syntology":null},{"url":"/paper/evox-a-distributed-gpu-accelerated-library","slug":"evox-a-distributed-gpu-accelerated-library","title":"EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computation","date":"2023-01-29","arxiv_id":"2301.12457","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evox-a-distributed-gpu-accelerated-library#ran","syntology_url":"https://syntology.ai/paper/2301.12457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12457"}},"official":{"repos":["emi-group/evox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pushworld-a-benchmark-for-manipulation","slug":"pushworld-a-benchmark-for-manipulation","title":"PushWorld: A benchmark for manipulation planning with tools and movable obstacles","date":"2023-01-24","arxiv_id":"2301.10289","repositories_listed":1,"syntology":null},{"url":"/paper/robust-policy-optimization-in-deep","slug":"robust-policy-optimization-in-deep","title":"Robust Policy Optimization in Deep Reinforcement Learning","date":"2022-12-14","arxiv_id":"2212.07536","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-policy-optimization-in-deep#ran","syntology_url":"https://syntology.ai/paper/2212.07536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07536"}},"official":{"repos":["vwxyzjn/cleanrl"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/design-process-is-a-reinforcement-learning","slug":"design-process-is-a-reinforcement-learning","title":"Design Process is a Reinforcement Learning Problem","date":"2022-11-06","arxiv_id":"2211.03136","repositories_listed":1,"syntology":null},{"url":"/paper/diambra-arena-a-new-reinforcement-learning","slug":"diambra-arena-a-new-reinforcement-learning","title":"DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation","date":"2022-10-19","arxiv_id":"2210.10595","repositories_listed":1,"syntology":null},{"url":"/paper/cairl-a-high-performance-reinforcement","slug":"cairl-a-high-performance-reinforcement","title":"CaiRL: A High-Performance Reinforcement Learning Environment Toolkit","date":"2022-10-03","arxiv_id":"2210.01235","repositories_listed":1,"syntology":null},{"url":"/paper/project-proposal-a-modular-reinforcement","slug":"project-proposal-a-modular-reinforcement","title":"Project proposal: A modular reinforcement learning based automated theorem prover","date":"2022-09-06","arxiv_id":"2209.02562","repositories_listed":1,"syntology":null},{"url":"/paper/safe-and-robust-experience-sharing-for","slug":"safe-and-robust-experience-sharing-for","title":"Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms","date":"2022-07-27","arxiv_id":"2207.13453","repositories_listed":1,"syntology":null},{"url":"/paper/unified-distributed-environment","slug":"unified-distributed-environment","title":"Unified Distributed Environment","date":"2022-05-14","arxiv_id":"2205.06946","repositories_listed":1,"syntology":null},{"url":"/paper/jorldy-a-fully-customizable-open-source","slug":"jorldy-a-fully-customizable-open-source","title":"JORLDY: a fully customizable open source framework for reinforcement learning","date":"2022-04-11","arxiv_id":"2204.04892","repositories_listed":1,"syntology":null},{"url":"/paper/andes-gym-a-versatile-environment-for-deep","slug":"andes-gym-a-versatile-environment-for-deep","title":"Andes_gym: A Versatile Environment for Deep Reinforcement Learning in Power Systems","date":"2022-03-02","arxiv_id":"2203.01292","repositories_listed":1,"syntology":null},{"url":"/paper/avalanche-rl-a-continual-reinforcement","slug":"avalanche-rl-a-continual-reinforcement","title":"Avalanche RL: a Continual Reinforcement Learning Library","date":"2022-02-28","arxiv_id":"2202.13657","repositories_listed":1,"syntology":null},{"url":"/paper/quadsim-a-quadcopter-rotational-dynamics","slug":"quadsim-a-quadcopter-rotational-dynamics","title":"QuadSim: A Quadcopter Rotational Dynamics Simulation Framework For Reinforcement Learning Algorithms","date":"2022-02-14","arxiv_id":"2202.07021","repositories_listed":1,"syntology":null},{"url":"/paper/skrl-modular-and-flexible-library-for","slug":"skrl-modular-and-flexible-library-for","title":"skrl: Modular and Flexible Library for Reinforcement Learning","date":"2022-02-08","arxiv_id":"2202.03825","repositories_listed":1,"syntology":null},{"url":"/paper/deep-q-learning-a-robust-control-approach","slug":"deep-q-learning-a-robust-control-approach","title":"Deep Q-learning: a robust control approach","date":"2022-01-21","arxiv_id":"2201.08610","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-control-with-ensemble-deep-1","slug":"continuous-control-with-ensemble-deep-1","title":"Continuous Control With Ensemble Deep Deterministic Policy Gradients","date":"2021-11-30","arxiv_id":"2111.15382","repositories_listed":1,"syntology":null},{"url":"/paper/adaptively-calibrated-critic-estimates-for","slug":"adaptively-calibrated-critic-estimates-for","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","date":"2021-11-24","arxiv_id":"2111.12673","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptively-calibrated-critic-estimates-for#ran","syntology_url":"https://syntology.ai/paper/2111.12673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12673"}},"official":{"repos":["nicolinho/acc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tmm-fast-a-transfer-matrix-computation","slug":"tmm-fast-a-transfer-matrix-computation","title":"TMM-Fast: A Transfer Matrix Computation Package for Multilayer Thin-Film Optimization","date":"2021-11-24","arxiv_id":"2111.13667","repositories_listed":1,"syntology":null},{"url":"/paper/abides-gym-gym-environments-for-multi-agent","slug":"abides-gym-gym-environments-for-multi-agent","title":"ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Markets","date":"2021-10-27","arxiv_id":"2110.14771","repositories_listed":1,"syntology":null},{"url":"/paper/stackelberg-actor-critic-game-theoretic","slug":"stackelberg-actor-critic-game-theoretic","title":"Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms","date":"2021-09-25","arxiv_id":"2109.12286","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stackelberg-actor-critic-game-theoretic#ran","syntology_url":"https://syntology.ai/paper/2109.12286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12286"}},"official":{"repos":["leozhengzly/stackelberg-actor-critic-algos"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/estimation-error-correction-in-deep","slug":"estimation-error-correction-in-deep","title":"Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods","date":"2021-09-22","arxiv_id":"2109.10736","repositories_listed":1,"syntology":null},{"url":"/paper/compilergym-robust-performant-compiler","slug":"compilergym-robust-performant-compiler","title":"CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research","date":"2021-09-17","arxiv_id":"2109.08267","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/compilergym-robust-performant-compiler#ran","syntology_url":"https://syntology.ai/paper/2109.08267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08267"}},"official":{"repos":["facebookresearch/CompilerGym"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/powergym-a-reinforcement-learning-environment","slug":"powergym-a-reinforcement-learning-environment","title":"PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems","date":"2021-09-08","arxiv_id":"2109.03970","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/powergym-a-reinforcement-learning-environment#ran","syntology_url":"https://syntology.ai/paper/2109.03970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03970"}},"official":{"repos":["siemens/powergym"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}}],"syntology_records":27,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/openai-gym-on-mountain-car","since_archive":"/sota/openai-gym-on-mountain-car#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":43,"papers_where_code_ran_first_page":"/task/openai-gym/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/openai-gym/papers/2","json":"/task/openai-gym/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/openai-gym/papers/3","json":"/task/openai-gym/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/openai-gym/papers/4","json":"/task/openai-gym/papers/4.json","rows":82},{"order":"ran","page":1,"of":1,"url":"/task/openai-gym/papers/ran/1","json":"/task/openai-gym/papers/ran/1.json","rows":43}],"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"be3523db1e71d66fe8205c75291705a6a3ea7a1335935a4ecfdcf6ca1b5ddfa7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}