{"url":"/task/continuous-control","name":"Continuous Control","slug":"continuous-control","description_markdown":"Continuous control in the context of playing games, especially within artificial intelligence (AI) and machine learning (ML), refers to the ability to make a series of smooth, ongoing adjustments or actions to control a game or a simulation. This is in contrast to discrete control, where the actions are limited to a set of specific, distinct choices. Continuous control is crucial in environments where precision, timing, and the magnitude of actions matter, such as driving a car in a racing game, controlling a character in a simulation, or managing the flight of an aircraft in a flight simulator.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Playing Games","url":"/area/playing-games"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1161,"papers_with_code":494,"benchmarks":73,"benchmark_tables_in_archive":73,"benchmark_tables_shown":73,"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":10,"subtasks":3,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/continuous-control-on-pybullet-ant","slug":"continuous-control-on-pybullet-ant","dataset":"PyBullet Ant","dataset_url":"/dataset/pybullet","rows_in_archive":8,"metrics":["Return"],"first_row_in_archive_order":{"model":"SAC gSDE","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","paper_url":"/paper/generalized-state-dependent-exploration-for","paper_date":"2020-05-12","arxiv_id":"2005.05719","code_links":[{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"facebookresearch/rl","url":"https://github.com/facebookresearch/rl"},{"title":"araffin/sbx","url":"https://github.com/araffin/sbx"},{"title":"markub3327/rl-toolkit","url":"https://github.com/markub3327/rl-toolkit"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-pybullet-halfcheetah","slug":"continuous-control-on-pybullet-halfcheetah","dataset":"PyBullet HalfCheetah","dataset_url":"/dataset/pybullet","rows_in_archive":8,"metrics":["Return"],"first_row_in_archive_order":{"model":"SAC","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","paper_url":"/paper/generalized-state-dependent-exploration-for","paper_date":"2020-05-12","arxiv_id":"2005.05719","code_links":[{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"facebookresearch/rl","url":"https://github.com/facebookresearch/rl"},{"title":"araffin/sbx","url":"https://github.com/araffin/sbx"},{"title":"markub3327/rl-toolkit","url":"https://github.com/markub3327/rl-toolkit"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-pybullet-hopper","slug":"continuous-control-on-pybullet-hopper","dataset":"PyBullet Hopper","dataset_url":"/dataset/pybullet","rows_in_archive":8,"metrics":["Return"],"first_row_in_archive_order":{"model":"SAC gSDE","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","paper_url":"/paper/generalized-state-dependent-exploration-for","paper_date":"2020-05-12","arxiv_id":"2005.05719","code_links":[{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"facebookresearch/rl","url":"https://github.com/facebookresearch/rl"},{"title":"araffin/sbx","url":"https://github.com/araffin/sbx"},{"title":"markub3327/rl-toolkit","url":"https://github.com/markub3327/rl-toolkit"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-pybullet-walker2d","slug":"continuous-control-on-pybullet-walker2d","dataset":"PyBullet Walker2D","dataset_url":"/dataset/pybullet","rows_in_archive":8,"metrics":["Return"],"first_row_in_archive_order":{"model":"SAC gSDE","paper_title":"Smooth Exploration for Robotic Reinforcement Learning","paper_url":"/paper/generalized-state-dependent-exploration-for","paper_date":"2020-05-12","arxiv_id":"2005.05719","code_links":[{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"facebookresearch/rl","url":"https://github.com/facebookresearch/rl"},{"title":"araffin/sbx","url":"https://github.com/araffin/sbx"},{"title":"markub3327/rl-toolkit","url":"https://github.com/markub3327/rl-toolkit"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-lunar-lander-openai-gym","slug":"continuous-control-on-lunar-lander-openai-gym","dataset":"Lunar Lander (OpenAI Gym)","dataset_url":"/dataset/openai-gym","rows_in_archive":5,"metrics":["Score"],"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_unverified":57,"n_pointer_only":66}}},{"leaderboard":"/sota/continuous-control-on-deepmind-cheetah-run","slug":"continuous-control-on-deepmind-cheetah-run","dataset":"DeepMind Cheetah Run (Images)","dataset_url":"/dataset/deepmind-control-suite","rows_in_archive":4,"metrics":["Return"],"first_row_in_archive_order":{"model":"DreamerV1","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-cartpole-balance-sparse","slug":"continuous-control-on-cartpole-balance-sparse","dataset":"cartpole.balance_sparse","dataset_url":null,"rows_in_archive":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-cartpole-swingup-2","slug":"continuous-control-on-cartpole-swingup-2","dataset":"cartpole.swingup","dataset_url":null,"rows_in_archive":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-cheetah-run-2","slug":"continuous-control-on-cheetah-run-2","dataset":"cheetah.run","dataset_url":null,"rows_in_archive":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-deepmind-cup-catch","slug":"continuous-control-on-deepmind-cup-catch","dataset":"DeepMind Cup Catch (Images)","dataset_url":"/dataset/deepmind-control-suite","rows_in_archive":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"DrQ","paper_title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","paper_url":"/paper/image-augmentation-is-all-you-need","paper_date":"2020-04-28","arxiv_id":"2004.13649","code_links":[{"title":"denisyarats/drq","url":"https://github.com/denisyarats/drq"},{"title":"xingyu-lin/softagent","url":"https://github.com/xingyu-lin/softagent"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"YaoMarkMu/DRQTRANS","url":"https://github.com/YaoMarkMu/DRQTRANS"}],"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":8}}},{"leaderboard":"/sota/continuous-control-on-deepmind-walker-walk","slug":"continuous-control-on-deepmind-walker-walk","dataset":"DeepMind Walker Walk (Images)","dataset_url":"/dataset/deepmind-control-suite","rows_in_archive":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"DrQ","paper_title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","paper_url":"/paper/image-augmentation-is-all-you-need","paper_date":"2020-04-28","arxiv_id":"2004.13649","code_links":[{"title":"denisyarats/drq","url":"https://github.com/denisyarats/drq"},{"title":"xingyu-lin/softagent","url":"https://github.com/xingyu-lin/softagent"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"YaoMarkMu/DRQTRANS","url":"https://github.com/YaoMarkMu/DRQTRANS"}],"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":8}}},{"leaderboard":"/sota/continuous-control-on-finger-turn-hard","slug":"continuous-control-on-finger-turn-hard","dataset":"finger.turn_hard","dataset_url":null,"rows_in_archive":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-walker-stand","slug":"continuous-control-on-walker-stand","dataset":"walker.stand","dataset_url":null,"rows_in_archive":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-walker-walk-2","slug":"continuous-control-on-walker-walk-2","dataset":"walker.walk","dataset_url":null,"rows_in_archive":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-2d-walker","slug":"continuous-control-on-2d-walker","dataset":"2D Walker","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-acrobot","slug":"continuous-control-on-acrobot","dataset":"Acrobot","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-acrobot-limited-sensors","slug":"continuous-control-on-acrobot-limited-sensors","dataset":"Acrobot (limited sensors)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-acrobot-noisy","slug":"continuous-control-on-acrobot-noisy","dataset":"Acrobot (noisy observations)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-acrobot-swingup","slug":"continuous-control-on-acrobot-swingup","dataset":"acrobot.swingup","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-acrobot-system","slug":"continuous-control-on-acrobot-system","dataset":"Acrobot (system identifications)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-ant","slug":"continuous-control-on-ant","dataset":"Ant","dataset_url":"/dataset/omniverse-isaac-gym","rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-ant-gathering","slug":"continuous-control-on-ant-gathering","dataset":"Ant + Gathering","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-ant-maze","slug":"continuous-control-on-ant-maze","dataset":"Ant + Maze","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-ball-in-cup-catch","slug":"continuous-control-on-ball-in-cup-catch","dataset":"Ball in cup, catch (DMControl500k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-ball-in-cup-catch-1","slug":"continuous-control-on-ball-in-cup-catch-1","dataset":"Ball in cup, catch (DMControl100k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-ball-in-cup-catch-2","slug":"continuous-control-on-ball-in-cup-catch-2","dataset":"ball_in_cup.catch","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-cart-pole-balancing","slug":"continuous-control-on-cart-pole-balancing","dataset":"Cart-Pole Balancing","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-cart-pole-balancing-1","slug":"continuous-control-on-cart-pole-balancing-1","dataset":"Cart-Pole Balancing (limited sensors)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-cart-pole-balancing-2","slug":"continuous-control-on-cart-pole-balancing-2","dataset":"Cart-Pole Balancing (noisy observations)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-cart-pole-balancing-3","slug":"continuous-control-on-cart-pole-balancing-3","dataset":"Cart-Pole Balancing (system identifications)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-cart-pole-openai-gym","slug":"continuous-control-on-cart-pole-openai-gym","dataset":"Cart Pole (OpenAI Gym)","dataset_url":"/dataset/openai-gym","rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"MAC","paper_title":"Mean Actor Critic","paper_url":"/paper/mean-actor-critic","paper_date":"2017-09-01","arxiv_id":"1709.00503","code_links":[{"title":"kavosh8/MAC","url":"https://github.com/kavosh8/MAC"},{"title":"camall3n/atari-MAC","url":"https://github.com/camall3n/atari-MAC"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-cartpole-balance","slug":"continuous-control-on-cartpole-balance","dataset":"cartpole.balance","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-cartpole-swingup","slug":"continuous-control-on-cartpole-swingup","dataset":"Cartpole, swingup (DMControl500k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-cartpole-swingup-1","slug":"continuous-control-on-cartpole-swingup-1","dataset":"Cartpole, swingup (DMControl100k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-cartpole-swingup-sparse","slug":"continuous-control-on-cartpole-swingup-sparse","dataset":"cartpole.swingup_sparse","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-cheetah-run","slug":"continuous-control-on-cheetah-run","dataset":"Cheetah, run (DMControl500k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-cheetah-run-1","slug":"continuous-control-on-cheetah-run-1","dataset":"Cheetah, run (DMControl100k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-double-inverted","slug":"continuous-control-on-double-inverted","dataset":"Double Inverted Pendulum","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-finger-spin","slug":"continuous-control-on-finger-spin","dataset":"Finger, spin (DMControl500k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-finger-spin-1","slug":"continuous-control-on-finger-spin-1","dataset":"Finger, spin (DMControl100k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-finger-spin-2","slug":"continuous-control-on-finger-spin-2","dataset":"finger.spin","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-finger-turn-easy","slug":"continuous-control-on-finger-turn-easy","dataset":"finger.turn_easy","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-fish-swim","slug":"continuous-control-on-fish-swim","dataset":"fish.swim","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"MuZero Unplugged","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_url":"/paper/online-and-offline-reinforcement-learning-by","paper_date":"2021-04-13","arxiv_id":"2104.06294","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-full-humanoid","slug":"continuous-control-on-full-humanoid","dataset":"Full Humanoid","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-half-cheetah","slug":"continuous-control-on-half-cheetah","dataset":"Half-Cheetah","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-hopper","slug":"continuous-control-on-hopper","dataset":"Hopper","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-hopper-hop","slug":"continuous-control-on-hopper-hop","dataset":"hopper.hop","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-hopper-stand","slug":"continuous-control-on-hopper-stand","dataset":"hopper.stand","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-humanoid-run","slug":"continuous-control-on-humanoid-run","dataset":"humanoid.run","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"MuZero Unplugged","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_url":"/paper/online-and-offline-reinforcement-learning-by","paper_date":"2021-04-13","arxiv_id":"2104.06294","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-inverted-pendulum","slug":"continuous-control-on-inverted-pendulum","dataset":"Inverted Pendulum","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-inverted-pendulum-1","slug":"continuous-control-on-inverted-pendulum-1","dataset":"Inverted Pendulum (limited sensors)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-inverted-pendulum-2","slug":"continuous-control-on-inverted-pendulum-2","dataset":"Inverted Pendulum (system identifications)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-inverted-pendulum-noisy","slug":"continuous-control-on-inverted-pendulum-noisy","dataset":"Inverted Pendulum (noisy observations)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-manipulator-insert-ball","slug":"continuous-control-on-manipulator-insert-ball","dataset":"manipulator.insert_ball","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"MuZero Unplugged","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_url":"/paper/online-and-offline-reinforcement-learning-by","paper_date":"2021-04-13","arxiv_id":"2104.06294","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-manipulator-insert-peg","slug":"continuous-control-on-manipulator-insert-peg","dataset":"manipulator.insert_peg","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"MuZero Unplugged","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_url":"/paper/online-and-offline-reinforcement-learning-by","paper_date":"2021-04-13","arxiv_id":"2104.06294","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-mountain-car","slug":"continuous-control-on-mountain-car","dataset":"Mountain Car","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-mountain-car-limited","slug":"continuous-control-on-mountain-car-limited","dataset":"Mountain Car (limited sensors)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-mountain-car-noisy","slug":"continuous-control-on-mountain-car-noisy","dataset":"Mountain Car (noisy observations)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-mountain-car-system","slug":"continuous-control-on-mountain-car-system","dataset":"Mountain Car (system identifications)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-pendulum-swingup","slug":"continuous-control-on-pendulum-swingup","dataset":"pendulum.swingup","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-quadruped-run","slug":"continuous-control-on-quadruped-run","dataset":"quadruped.run","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-quadruped-walk","slug":"continuous-control-on-quadruped-walk","dataset":"quadruped.walk","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-reacher-easy","slug":"continuous-control-on-reacher-easy","dataset":"Reacher, easy (DMControl500k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-reacher-easy-1","slug":"continuous-control-on-reacher-easy-1","dataset":"Reacher, easy (DMControl100k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-reacher-easy-2","slug":"continuous-control-on-reacher-easy-2","dataset":"reacher.easy","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-reacher-hard","slug":"continuous-control-on-reacher-hard","dataset":"reacher.hard","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-simple-humanoid","slug":"continuous-control-on-simple-humanoid","dataset":"Simple Humanoid","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-swimmer","slug":"continuous-control-on-swimmer","dataset":"Swimmer","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-swimmer-gathering","slug":"continuous-control-on-swimmer-gathering","dataset":"Swimmer + Gathering","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-swimmer-maze","slug":"continuous-control-on-swimmer-maze","dataset":"Swimmer + Maze","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper_title":"Benchmarking Deep Reinforcement Learning for Continuous Control","paper_url":"/paper/benchmarking-deep-reinforcement-learning-for","paper_date":"2016-04-22","arxiv_id":"1604.06778","code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}],"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-walker-run","slug":"continuous-control-on-walker-run","dataset":"walker.run","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"SMuZero","paper_title":"Learning and Planning in Complex Action Spaces","paper_url":"/paper/learning-and-planning-in-complex-action","paper_date":"2021-04-13","arxiv_id":"2104.06303","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"syntology":null}},{"leaderboard":"/sota/continuous-control-on-walker-walk","slug":"continuous-control-on-walker-walk","dataset":"Walker, walk (DMControl500k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/continuous-control-on-walker-walk-1","slug":"continuous-control-on-walker-walk-1","dataset":"Walker, walk (DMControl100k)","dataset_url":null,"rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"CURL","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","paper_url":"/paper/curl-contrastive-unsupervised-representations","paper_date":"2020-04-08","arxiv_id":"2004.04136","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"MishaLaskin/curl","url":"https://github.com/MishaLaskin/curl"},{"title":"aravindsrinivas/curl_rainbow","url":"https://github.com/aravindsrinivas/curl_rainbow"},{"title":"KarlXing/RL-Visual-Continuous-Control","url":"https://github.com/KarlXing/RL-Visual-Continuous-Control"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"gijskoning/ReproducingCURL","url":"https://github.com/gijskoning/ReproducingCURL"},{"title":"asparius/barlowrl","url":"https://github.com/asparius/barlowrl"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/openai-gym","name":"OpenAI Gym","full_name":"OpenAI Gym","num_papers_in_archive":1305},{"url":"/dataset/d4rl","name":"D4RL","full_name":"D4RL","num_papers_in_archive":538},{"url":"/dataset/deepmind-control-suite","name":"DeepMind Control Suite","full_name":"DeepMind Control Suite","num_papers_in_archive":364},{"url":"/dataset/omniverse-isaac-gym","name":"Omniverse Isaac Gym","full_name":"","num_papers_in_archive":240},{"url":"/dataset/lani","name":"Lani","full_name":null,"num_papers_in_archive":12},{"url":"/dataset/mo-gymnasium","name":"MO-Gymnasium","full_name":"","num_papers_in_archive":8},{"url":"/dataset/mocapact","name":"MoCapAct","full_name":"Motion Capture with Actions","num_papers_in_archive":4},{"url":"/dataset/pybullet","name":"PyBullet","full_name":"","num_papers_in_archive":3},{"url":"/dataset/caglar","name":"RLU","full_name":"RL Unplugged","num_papers_in_archive":2},{"url":"/dataset/rllab-framework","name":"RLLab Framework","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/car-racing","name":"Car Racing"},{"url":"/task/drone-controller","name":"Drone Controller"},{"url":"/task/steering-control","name":"Steering Control"}],"parent_tasks":[{"url":"/task/3d-face-modeling","name":"3D Face Modelling"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":494,"tagged_in_all":1161,"items":[{"url":"/paper/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_unverified":77,"n_pointer_only":94}},{"url":"/paper/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":158,"n_unverified":148,"n_pointer_only":163}},{"url":"/paper/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":158,"n_unverified":148,"n_pointer_only":163}},{"url":"/paper/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_unverified":57,"n_pointer_only":66}},{"url":"/paper/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":9,"n_unverified":27,"n_pointer_only":20}},{"url":"/paper/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/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/simple-random-search-provides-a-competitive","title":"Simple random search provides a competitive approach to reinforcement learning","date":"2018-03-19","arxiv_id":"1803.07055","repositories_listed":26,"syntology":{"n":15,"n_ran":3,"n_unverified":12,"n_pointer_only":3}},{"url":"/paper/simple-random-search-provides-a-competitive","title":"Simple random search provides a competitive approach to reinforcement learning","date":"2018-03-19","arxiv_id":"1803.07055","repositories_listed":26,"syntology":{"n":15,"n_ran":3,"n_unverified":12,"n_pointer_only":3}},{"url":"/paper/dream-to-control-learning-behaviors-by-latent","title":"Dream to Control: Learning Behaviors by Latent Imagination","date":"2019-12-03","arxiv_id":"1912.01603","repositories_listed":21,"syntology":{"n":62,"n_ran":43,"n_unverified":19,"n_pointer_only":9}},{"url":"/paper/conservative-q-learning-for-offline","title":"Conservative Q-Learning for Offline Reinforcement Learning","date":"2020-06-08","arxiv_id":"2006.04779","repositories_listed":18,"syntology":{"n":34,"n_ran":24,"n_unverified":10,"n_pointer_only":5}},{"url":"/paper/conservative-q-learning-for-offline","title":"Conservative Q-Learning for Offline Reinforcement Learning","date":"2020-06-08","arxiv_id":"2006.04779","repositories_listed":18,"syntology":{"n":34,"n_ran":24,"n_unverified":10,"n_pointer_only":5}},{"url":"/paper/high-dimensional-continuous-control-using","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","date":"2015-06-08","arxiv_id":"1506.02438","repositories_listed":17,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/high-dimensional-continuous-control-using","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","date":"2015-06-08","arxiv_id":"1506.02438","repositories_listed":17,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","arxiv_id":"1604.06778","repositories_listed":15,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","arxiv_id":"1604.06778","repositories_listed":15,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/off-policy-deep-reinforcement-learning","title":"Off-Policy Deep Reinforcement Learning without Exploration","date":"2018-12-07","arxiv_id":"1812.02900","repositories_listed":10,"syntology":{"n":14,"n_ran":13,"n_unverified":1,"n_pointer_only":9}},{"url":"/paper/off-policy-deep-reinforcement-learning","title":"Off-Policy Deep Reinforcement Learning without Exploration","date":"2018-12-07","arxiv_id":"1812.02900","repositories_listed":10,"syntology":{"n":14,"n_ran":13,"n_unverified":1,"n_pointer_only":9}},{"url":"/paper/parameter-space-noise-for-exploration","title":"Parameter Space Noise for Exploration","date":"2017-06-06","arxiv_id":"1706.01905","repositories_listed":10,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/parameter-space-noise-for-exploration","title":"Parameter Space Noise for Exploration","date":"2017-06-06","arxiv_id":"1706.01905","repositories_listed":10,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/stochastic-latent-actor-critic-deep","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","date":"2019-07-01","arxiv_id":"1907.00953","repositories_listed":9,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/stochastic-latent-actor-critic-deep","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","date":"2019-07-01","arxiv_id":"1907.00953","repositories_listed":9,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/learning-latent-dynamics-for-planning-from","title":"Learning Latent Dynamics for Planning from Pixels","date":"2018-11-12","arxiv_id":"1811.04551","repositories_listed":9,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":1}},{"url":"/paper/learning-latent-dynamics-for-planning-from","title":"Learning Latent Dynamics for Planning from Pixels","date":"2018-11-12","arxiv_id":"1811.04551","repositories_listed":9,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":1}},{"url":"/paper/mastering-visual-continuous-control-improved","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","date":"2021-07-20","arxiv_id":"2107.09645","repositories_listed":8,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/mastering-visual-continuous-control-improved","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","date":"2021-07-20","arxiv_id":"2107.09645","repositories_listed":8,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/deepmind-control-suite","title":"DeepMind Control Suite","date":"2018-01-02","arxiv_id":"1801.00690","repositories_listed":8,"syntology":null},{"url":"/paper/deepmind-control-suite","title":"DeepMind Control Suite","date":"2018-01-02","arxiv_id":"1801.00690","repositories_listed":8,"syntology":null},{"url":"/paper/scalable-trust-region-method-for-deep","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","date":"2017-08-17","arxiv_id":"1708.05144","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/scalable-trust-region-method-for-deep","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","date":"2017-08-17","arxiv_id":"1708.05144","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}],"syntology_records":26,"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"},"description_links":{"kept":0,"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}