{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/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":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-state-dependent-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2005.05719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05719"}},"official":{"repos":["DLR-RM/stable-baselines3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-state-dependent-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2005.05719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05719"}},"official":{"repos":["DLR-RM/stable-baselines3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-state-dependent-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2005.05719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05719"}},"official":{"repos":["DLR-RM/stable-baselines3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-state-dependent-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2005.05719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05719"}},"official":{"repos":["DLR-RM/stable-baselines3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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_constructed":61,"n_ran_checked":73,"n_instrument":18,"n_unverified":57,"n_honours":3,"n_violates":1,"n_no_contract":69,"n_pointer_only":66,"phrase":"91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified","sample_list":"/paper/soft-actor-critic-off-policy-maximum-entropy#ran","syntology_url":"https://syntology.ai/paper/1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"}},"official":{"repos":["haarnoja/sac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/image-augmentation-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2004.13649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13649"}},"official":{"repos":["denisyarats/drq"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}}},{"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_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/image-augmentation-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2004.13649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13649"}},"official":{"repos":["denisyarats/drq"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}}},{"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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"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":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}}],"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":12,"rows_per_page":100,"shown":100,"of":1161,"of_with_code":494,"tagged_in_all":1161,"counts":{"archive_papers_tagged":1161,"with_a_code_link":494,"where_syntology_ran_a_sample":193,"not_listed_spam_title":0,"listed":1161,"listed_where_code_ran":193,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":158,"every_run_a_failure_of_syntologys_instrument":35,"listed_with_a_run_with_no_instrument_failure":158,"listed_every_run_a_failure_of_syntologys_instrument":35,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/proximal-policy-optimization-algorithms","slug":"proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","arxiv_id":"1707.06347","repositories_listed":188,"syntology":{"n":176,"n_ran":99,"n_constructed":53,"n_ran_checked":71,"n_instrument":28,"n_unverified":77,"n_honours":7,"n_violates":2,"n_no_contract":62,"n_pointer_only":94,"phrase":"99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified","sample_list":"/paper/proximal-policy-optimization-algorithms#ran","syntology_url":"https://syntology.ai/paper/1707.06347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06347"}},"official":null}},{"url":"/paper/continuous-control-with-deep-reinforcement","slug":"continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","arxiv_id":"1509.02971","repositories_listed":161,"syntology":{"n":306,"n_ran":163,"n_constructed":126,"n_ran_checked":152,"n_instrument":11,"n_unverified":143,"n_honours":3,"n_violates":0,"n_no_contract":149,"n_pointer_only":163,"phrase":"163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified","sample_list":"/paper/continuous-control-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1509.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.02971"}},"official":null}},{"url":"/paper/soft-actor-critic-off-policy-maximum-entropy","slug":"soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","arxiv_id":"1801.01290","repositories_listed":86,"syntology":{"n":148,"n_ran":91,"n_constructed":61,"n_ran_checked":73,"n_instrument":18,"n_unverified":57,"n_honours":3,"n_violates":1,"n_no_contract":69,"n_pointer_only":66,"phrase":"91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified","sample_list":"/paper/soft-actor-critic-off-policy-maximum-entropy#ran","syntology_url":"https://syntology.ai/paper/1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"}},"official":{"repos":["haarnoja/sac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/addressing-function-approximation-error-in","slug":"addressing-function-approximation-error-in","title":"Addressing Function Approximation Error in Actor-Critic Methods","date":"2018-02-26","arxiv_id":"1802.09477","repositories_listed":67,"syntology":{"n":36,"n_ran":26,"n_constructed":0,"n_ran_checked":20,"n_instrument":6,"n_unverified":10,"n_honours":1,"n_violates":2,"n_no_contract":17,"n_pointer_only":21,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 2 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/addressing-function-approximation-error-in#ran","syntology_url":"https://syntology.ai/paper/1802.09477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09477"}},"official":{"repos":["sfujim/TD3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/multi-goal-reinforcement-learning-challenging","slug":"multi-goal-reinforcement-learning-challenging","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","date":"2018-02-26","arxiv_id":"1802.09464","repositories_listed":28,"syntology":null},{"url":"/paper/simple-random-search-provides-a-competitive","slug":"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":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/simple-random-search-provides-a-competitive#ran","syntology_url":"https://syntology.ai/paper/1803.07055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.07055"}},"official":{"repos":["modestyachts/ARS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/dream-to-control-learning-behaviors-by-latent","slug":"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":52,"n_constructed":33,"n_ran_checked":45,"n_instrument":7,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":44,"n_pointer_only":9,"phrase":"52 ran (of which 33 constructed an object rather than computing a result; 45 with no instrument failure: 1 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/dream-to-control-learning-behaviors-by-latent#ran","syntology_url":"https://syntology.ai/paper/1912.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.01603"}},"official":{"repos":["danijar/dreamer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/conservative-q-learning-for-offline","slug":"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":31,"n_constructed":5,"n_ran_checked":22,"n_instrument":9,"n_unverified":3,"n_honours":5,"n_violates":2,"n_no_contract":15,"n_pointer_only":19,"phrase":"31 ran (of which 5 constructed an object rather than computing a result; 22 with no instrument failure: 5 honoured, 2 violated, 15 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/conservative-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2006.04779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04779"}},"official":{"repos":["aviralkumar2907/CQL"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/high-dimensional-continuous-control-using","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/high-dimensional-continuous-control-using#ran","syntology_url":"https://syntology.ai/paper/1506.02438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.02438"}},"official":null}},{"url":"/paper/benchmarking-deep-reinforcement-learning-for","slug":"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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/off-policy-deep-reinforcement-learning","slug":"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":14,"n_constructed":12,"n_ran_checked":14,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":9,"phrase":"14 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/off-policy-deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1812.02900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.02900"}},"official":{"repos":["sfujim/BCQ"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/parameter-space-noise-for-exploration","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/parameter-space-noise-for-exploration#ran","syntology_url":"https://syntology.ai/paper/1706.01905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.01905"}},"official":null}},{"url":"/paper/stochastic-latent-actor-critic-deep","slug":"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":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stochastic-latent-actor-critic-deep#ran","syntology_url":"https://syntology.ai/paper/1907.00953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.00953"}},"official":null}},{"url":"/paper/learning-latent-dynamics-for-planning-from","slug":"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":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-latent-dynamics-for-planning-from#ran","syntology_url":"https://syntology.ai/paper/1811.04551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04551"}},"official":{"repos":["google-research/planet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mastering-visual-continuous-control-improved","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mastering-visual-continuous-control-improved#ran","syntology_url":"https://syntology.ai/paper/2107.09645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09645"}},"official":{"repos":["facebookresearch/drqv2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deepmind-control-suite","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scalable-trust-region-method-for-deep#ran","syntology_url":"https://syntology.ai/paper/1708.05144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.05144"}},"official":{"repos":["openai/baselines"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/continuous-deep-q-learning-with-model-based","slug":"continuous-deep-q-learning-with-model-based","title":"Continuous Deep Q-Learning with Model-based Acceleration","date":"2016-03-02","arxiv_id":"1603.00748","repositories_listed":8,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continuous-deep-q-learning-with-model-based#ran","syntology_url":"https://syntology.ai/paper/1603.00748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.00748"}},"official":null}},{"url":"/paper/controlling-overestimation-bias-with","slug":"controlling-overestimation-bias-with","title":"Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics","date":"2020-05-08","arxiv_id":"2005.04269","repositories_listed":7,"syntology":null},{"url":"/paper/curl-contrastive-unsupervised-representations","slug":"curl-contrastive-unsupervised-representations","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","date":"2020-04-08","arxiv_id":"2004.04136","repositories_listed":7,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}},"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/sample-efficient-actor-critic-with-experience","slug":"sample-efficient-actor-critic-with-experience","title":"Sample Efficient Actor-Critic with Experience Replay","date":"2016-11-03","arxiv_id":"1611.01224","repositories_listed":7,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/sample-efficient-actor-critic-with-experience#ran","syntology_url":"https://syntology.ai/paper/1611.01224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01224"}},"official":null}},{"url":"/paper/mopo-model-based-offline-policy-optimization","slug":"mopo-model-based-offline-policy-optimization","title":"MOPO: Model-based Offline Policy Optimization","date":"2020-05-27","arxiv_id":"2005.13239","repositories_listed":6,"syntology":{"n":8,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mopo-model-based-offline-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2005.13239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.13239"}},"official":{"repos":["tianheyu927/mopo"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/advantage-weighted-regression-simple-and","slug":"advantage-weighted-regression-simple-and","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","date":"2019-10-01","arxiv_id":"1910.00177","repositories_listed":6,"syntology":null},{"url":"/paper/near-optimal-representation-learning-for","slug":"near-optimal-representation-learning-for","title":"Near-Optimal Representation Learning for Hierarchical Reinforcement Learning","date":"2018-10-02","arxiv_id":"1810.01257","repositories_listed":6,"syntology":null},{"url":"/paper/evolution-guided-policy-gradient-in","slug":"evolution-guided-policy-gradient-in","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","date":"2018-05-21","arxiv_id":"1805.07917","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/evolution-guided-policy-gradient-in#ran","syntology_url":"https://syntology.ai/paper/1805.07917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07917"}},"official":{"repos":["ShawK91/erl_paper_nips18"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/iq-learn-inverse-soft-q-learning-for","slug":"iq-learn-inverse-soft-q-learning-for","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","date":"2021-06-23","arxiv_id":"2106.12142","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/iq-learn-inverse-soft-q-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.12142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12142"}},"official":{"repos":["Div99/IQ-Learn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/crossnorm-normalization-for-off-policy-td","slug":"crossnorm-normalization-for-off-policy-td","title":"CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity","date":"2019-02-14","arxiv_id":"1902.05605","repositories_listed":5,"syntology":null},{"url":"/paper/variational-discriminator-bottleneck","slug":"variational-discriminator-bottleneck","title":"Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow","date":"2018-10-01","arxiv_id":"1810.00821","repositories_listed":5,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/variational-discriminator-bottleneck#ran","syntology_url":"https://syntology.ai/paper/1810.00821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.00821"}},"official":null}},{"url":"/paper/distributed-distributional-deterministic","slug":"distributed-distributional-deterministic","title":"Distributed Distributional Deterministic Policy Gradients","date":"2018-04-23","arxiv_id":"1804.08617","repositories_listed":5,"syntology":null},{"url":"/paper/action-branching-architectures-for-deep","slug":"action-branching-architectures-for-deep","title":"Action Branching Architectures for Deep Reinforcement Learning","date":"2017-11-24","arxiv_id":"1711.08946","repositories_listed":5,"syntology":null},{"url":"/paper/generalized-state-dependent-exploration-for","slug":"generalized-state-dependent-exploration-for","title":"Smooth Exploration for Robotic Reinforcement Learning","date":"2020-05-12","arxiv_id":"2005.05719","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-state-dependent-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2005.05719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05719"}},"official":{"repos":["DLR-RM/stable-baselines3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/image-augmentation-is-all-you-need","slug":"image-augmentation-is-all-you-need","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","date":"2020-04-28","arxiv_id":"2004.13649","repositories_listed":4,"syntology":{"n":10,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/image-augmentation-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2004.13649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13649"}},"official":{"repos":["denisyarats/drq"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-reinforcement-learning-that-matters","slug":"deep-reinforcement-learning-that-matters","title":"Deep Reinforcement Learning that Matters","date":"2017-09-19","arxiv_id":"1709.06560","repositories_listed":4,"syntology":null},{"url":"/paper/rebel-reinforcement-learning-via-regressing","slug":"rebel-reinforcement-learning-via-regressing","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","date":"2024-04-25","arxiv_id":"2404.16767","repositories_listed":3,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":8,"n_instrument":8,"n_unverified":4,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":6,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rebel-reinforcement-learning-via-regressing#ran","syntology_url":"https://syntology.ai/paper/2404.16767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16767"}},"official":{"repos":["Owen-Oertell/rlcm","zhaolingao/rebel"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/td-mpc2-scalable-robust-world-models-for","slug":"td-mpc2-scalable-robust-world-models-for","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","date":"2023-10-25","arxiv_id":"2310.16828","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":4,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"12 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/td-mpc2-scalable-robust-world-models-for#ran","syntology_url":"https://syntology.ai/paper/2310.16828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16828"}},"official":null}},{"url":"/paper/myosuite-a-contact-rich-simulation-suite-for","slug":"myosuite-a-contact-rich-simulation-suite-for","title":"MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control","date":"2022-05-26","arxiv_id":"2205.13600","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/myosuite-a-contact-rich-simulation-suite-for#ran","syntology_url":"https://syntology.ai/paper/2205.13600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13600"}},"official":{"repos":["facebookresearch/myosuite"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/adversarially-trained-actor-critic-for","slug":"adversarially-trained-actor-critic-for","title":"Adversarially Trained Actor Critic for Offline Reinforcement Learning","date":"2022-02-05","arxiv_id":"2202.02446","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarially-trained-actor-critic-for#ran","syntology_url":"https://syntology.ai/paper/2202.02446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02446"}},"official":{"repos":["microsoft/atac"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/benchmarks-for-deep-off-policy-evaluation-1","slug":"benchmarks-for-deep-off-policy-evaluation-1","title":"Benchmarks for Deep Off-Policy Evaluation","date":"2021-03-30","arxiv_id":"2103.16596","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarks-for-deep-off-policy-evaluation-1#ran","syntology_url":"https://syntology.ai/paper/2103.16596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16596"}},"official":{"repos":["google-research/deep_ope"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/reinforcement-learning-with-random-delays-1","slug":"reinforcement-learning-with-random-delays-1","title":"Reinforcement Learning with Random Delays","date":"2020-10-06","arxiv_id":"2010.02966","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":2,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reinforcement-learning-with-random-delays-1#ran","syntology_url":"https://syntology.ai/paper/2010.02966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02966"}},"official":{"repos":["rmst/rlrd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deep-reinforcement-learning-for-real","slug":"deep-reinforcement-learning-for-real","title":"Deep Reinforcement learning for real autonomous mobile robot navigation in indoor environments","date":"2020-05-28","arxiv_id":"2005.13857","repositories_listed":3,"syntology":null},{"url":"/paper/how-to-learn-a-useful-critic-model-based","slug":"how-to-learn-a-useful-critic-model-based","title":"How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization","date":"2020-04-29","arxiv_id":"2004.14309","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/how-to-learn-a-useful-critic-model-based#ran","syntology_url":"https://syntology.ai/paper/2004.14309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14309"}},"official":{"repos":["nnaisense/MAGE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/addressing-value-estimation-errors-in","slug":"addressing-value-estimation-errors-in","title":"Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors","date":"2020-01-09","arxiv_id":"2001.02811","repositories_listed":3,"syntology":null},{"url":"/paper/real-time-reinforcement-learning","slug":"real-time-reinforcement-learning","title":"Real-Time Reinforcement Learning","date":"2019-11-11","arxiv_id":"1911.04448","repositories_listed":3,"syntology":{"n":16,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/real-time-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1911.04448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04448"}},"official":{"repos":["rmst/rtrl","elementai/avenue"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-divergence-minimization-perspective-on","slug":"a-divergence-minimization-perspective-on","title":"A Divergence Minimization Perspective on Imitation Learning Methods","date":"2019-11-06","arxiv_id":"1911.02256","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-divergence-minimization-perspective-on#ran","syntology_url":"https://syntology.ai/paper/1911.02256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02256"}},"official":{"repos":["KamyarGh/rl_swiss"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-simplicity-in-deep-reinforcement-1","slug":"towards-simplicity-in-deep-reinforcement-1","title":"Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling","date":"2019-10-05","arxiv_id":"1910.02208","repositories_listed":3,"syntology":null},{"url":"/paper/190600949","slug":"190600949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","date":"2019-06-03","arxiv_id":"1906.00949","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/190600949#ran","syntology_url":"https://syntology.ai/paper/1906.00949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00949"}},"official":null}},{"url":"/paper/distributional-policy-optimization-an","slug":"distributional-policy-optimization-an","title":"Distributional Policy Optimization: An Alternative Approach for Continuous Control","date":"2019-05-23","arxiv_id":"1905.09855","repositories_listed":3,"syntology":null},{"url":"/paper/compositional-imitation-learning-explaining","slug":"compositional-imitation-learning-explaining","title":"CompILE: Compositional Imitation Learning and Execution","date":"2018-12-04","arxiv_id":"1812.01483","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/compositional-imitation-learning-explaining#ran","syntology_url":"https://syntology.ai/paper/1812.01483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01483"}},"official":{"repos":["tkipf/compile"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/sample-efficient-imitation-learning-via","slug":"sample-efficient-imitation-learning-via","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","date":"2018-09-06","arxiv_id":"1809.02064","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sample-efficient-imitation-learning-via#ran","syntology_url":"https://syntology.ai/paper/1809.02064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.02064"}},"official":{"repos":["lionelblonde/sam-tf"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/maximum-a-posteriori-policy-optimisation","slug":"maximum-a-posteriori-policy-optimisation","title":"Maximum a Posteriori Policy Optimisation","date":"2018-06-14","arxiv_id":"1806.06920","repositories_listed":3,"syntology":null},{"url":"/paper/overcoming-exploration-in-reinforcement","slug":"overcoming-exploration-in-reinforcement","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","date":"2017-09-28","arxiv_id":"1709.10089","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/overcoming-exploration-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1709.10089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.10089"}},"official":null}},{"url":"/paper/virtual-to-real-deep-reinforcement-learning","slug":"virtual-to-real-deep-reinforcement-learning","title":"Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation","date":"2017-03-01","arxiv_id":"1703.00420","repositories_listed":3,"syntology":null},{"url":"/paper/exploration-a-study-of-count-based","slug":"exploration-a-study-of-count-based","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","date":"2016-11-15","arxiv_id":"1611.04717","repositories_listed":3,"syntology":null},{"url":"/paper/memory-based-control-with-recurrent-neural","slug":"memory-based-control-with-recurrent-neural","title":"Memory-based control with recurrent neural networks","date":"2015-12-14","arxiv_id":"1512.04455","repositories_listed":3,"syntology":null},{"url":"/paper/learning-continuous-control-policies-by","slug":"learning-continuous-control-policies-by","title":"Learning Continuous Control Policies by Stochastic Value Gradients","date":"2015-10-30","arxiv_id":"1510.09142","repositories_listed":3,"syntology":null},{"url":"/paper/bootstrapped-model-predictive-control","slug":"bootstrapped-model-predictive-control","title":"Bootstrapped Model Predictive Control","date":"2025-03-24","arxiv_id":"2503.18871","repositories_listed":2,"syntology":null},{"url":"/paper/the-curse-of-diversity-in-ensemble-based","slug":"the-curse-of-diversity-in-ensemble-based","title":"The Curse of Diversity in Ensemble-Based Exploration","date":"2024-05-07","arxiv_id":"2405.04342","repositories_listed":2,"syntology":{"n":16,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":13,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/the-curse-of-diversity-in-ensemble-based#ran","syntology_url":"https://syntology.ai/paper/2405.04342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04342"}},"official":{"repos":["zhixuan-lin/ensemble-rl-continuous","zhixuan-lin/ensemble-rl-discrete"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":13,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-as-a-catalyst-for","slug":"reinforcement-learning-as-a-catalyst-for","title":"FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning","date":"2024-02-08","arxiv_id":"2402.05541","repositories_listed":2,"syntology":null},{"url":"/paper/synergizing-quality-diversity-with-descriptor","slug":"synergizing-quality-diversity-with-descriptor","title":"Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning","date":"2023-12-10","arxiv_id":"2401.08632","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/synergizing-quality-diversity-with-descriptor#ran","syntology_url":"https://syntology.ai/paper/2401.08632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08632"}},"official":{"repos":["adaptive-intelligent-robotics/DCRL-MAP-Elites"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/drm-mastering-visual-reinforcement-learning","slug":"drm-mastering-visual-reinforcement-learning","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","date":"2023-10-30","arxiv_id":"2310.19668","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":3,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/drm-mastering-visual-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2310.19668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19668"}},"official":{"repos":["XuGW-Kevin/DrM"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/for-sale-state-action-representation-learning-1","slug":"for-sale-state-action-representation-learning-1","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","date":"2023-06-04","arxiv_id":"2306.02451","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/for-sale-state-action-representation-learning-1#ran","syntology_url":"https://syntology.ai/paper/2306.02451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02451"}},"official":{"repos":["sfujim/td7"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/policy-gradient-methods-in-the-presence-of","slug":"policy-gradient-methods-in-the-presence-of","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","date":"2023-05-09","arxiv_id":"2305.05666","repositories_listed":2,"syntology":null},{"url":"/paper/explaining-rl-decisions-with-trajectories","slug":"explaining-rl-decisions-with-trajectories","title":"Explaining RL Decisions with Trajectories","date":"2023-05-06","arxiv_id":"2305.04073","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/explaining-rl-decisions-with-trajectories#ran","syntology_url":"https://syntology.ai/paper/2305.04073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04073"}},"official":{"repos":["shripaddeshmukh/xrl_with_trajectories"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/structured-state-space-models-for-in-context-1","slug":"structured-state-space-models-for-in-context-1","title":"Structured State Space Models for In-Context Reinforcement Learning","date":"2023-03-07","arxiv_id":"2303.03982","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/structured-state-space-models-for-in-context-1#ran","syntology_url":"https://syntology.ai/paper/2303.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03982"}},"official":{"repos":["luchris429/popjaxrl","luchris429/s5rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cflownets-continuous-control-with-generative","slug":"cflownets-continuous-control-with-generative","title":"CFlowNets: Continuous Control with Generative Flow Networks","date":"2023-03-04","arxiv_id":"2303.02430","repositories_listed":2,"syntology":null},{"url":"/paper/understanding-expertise-through","slug":"understanding-expertise-through","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","date":"2023-02-15","arxiv_id":"2302.07457","repositories_listed":2,"syntology":null},{"url":"/paper/deep-intrinsically-motivated-exploration-in","slug":"deep-intrinsically-motivated-exploration-in","title":"Deep Intrinsically Motivated Exploration in Continuous Control","date":"2022-10-01","arxiv_id":"2210.00293","repositories_listed":2,"syntology":null},{"url":"/paper/bsac-bayesian-strategy-network-based-soft","slug":"bsac-bayesian-strategy-network-based-soft","title":"Bayesian Soft Actor-Critic: A Directed Acyclic Strategy Graph Based Deep Reinforcement Learning","date":"2022-08-11","arxiv_id":"2208.06033","repositories_listed":2,"syntology":null},{"url":"/paper/goal-conditioned-generators-of-deep-policies","slug":"goal-conditioned-generators-of-deep-policies","title":"Goal-Conditioned Generators of Deep Policies","date":"2022-07-04","arxiv_id":"2207.01570","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/goal-conditioned-generators-of-deep-policies#ran","syntology_url":"https://syntology.ai/paper/2207.01570","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01570"}},"official":{"repos":["idsia/gogepo"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/generalized-policy-improvement-algorithms","slug":"generalized-policy-improvement-algorithms","title":"Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse","date":"2022-06-28","arxiv_id":"2206.13714","repositories_listed":2,"syntology":null},{"url":"/paper/challenges-and-opportunities-in-offline","slug":"challenges-and-opportunities-in-offline","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","date":"2022-06-09","arxiv_id":"2206.04779","repositories_listed":2,"syntology":null},{"url":"/paper/task-agnostic-continual-reinforcement","slug":"task-agnostic-continual-reinforcement","title":"Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges","date":"2022-05-28","arxiv_id":"2205.14495","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/task-agnostic-continual-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2205.14495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14495"}},"official":{"repos":["amazon-science/replay-based-recurrent-rl","amazon-research/replay-based-recurrent-rl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-difference-learning-for-model","slug":"temporal-difference-learning-for-model","title":"Temporal Difference Learning for Model Predictive Control","date":"2022-03-09","arxiv_id":"2203.04955","repositories_listed":2,"syntology":null},{"url":"/paper/an-experimental-design-perspective-on-model","slug":"an-experimental-design-perspective-on-model","title":"An Experimental Design Perspective on Model-Based Reinforcement Learning","date":"2021-12-09","arxiv_id":"2112.05244","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-experimental-design-perspective-on-model#ran","syntology_url":"https://syntology.ai/paper/2112.05244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05244"}},"official":null}},{"url":"/paper/context-meta-reinforcement-learning-via","slug":"context-meta-reinforcement-learning-via","title":"Context Meta-Reinforcement Learning via Neuromodulation","date":"2021-10-30","arxiv_id":"2111.00134","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/context-meta-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2111.00134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00134"}},"official":{"repos":["dlpbc/nm-metarl","soltoggio/ct-graph"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/planning-from-pixels-in-environments-with","slug":"planning-from-pixels-in-environments-with","title":"Planning from Pixels in Environments with Combinatorially Hard Search Spaces","date":"2021-10-12","arxiv_id":"2110.06149","repositories_listed":2,"syntology":null},{"url":"/paper/gradient-information-matters-in-policy","slug":"gradient-information-matters-in-policy","title":"Gradient Information Matters in Policy Optimization by Back-propagating through Model","date":"2021-09-29","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-learning-of-keypoint","slug":"end-to-end-learning-of-keypoint","title":"Learning of feature points without additional supervision improves reinforcement learning from images","date":"2021-06-15","arxiv_id":"2106.07995","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-learning-of-keypoint#ran","syntology_url":"https://syntology.ai/paper/2106.07995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07995"}},"official":{"repos":["rinuboney/fpac","rinuboney/keyq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/temporl-learning-when-to-act","slug":"temporl-learning-when-to-act","title":"TempoRL: Learning When to Act","date":"2021-06-09","arxiv_id":"2106.05262","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/temporl-learning-when-to-act#ran","syntology_url":"https://syntology.ai/paper/2106.05262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05262"}},"official":{"repos":["automl/TempoRL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/muesli-combining-improvements-in-policy","slug":"muesli-combining-improvements-in-policy","title":"Muesli: Combining Improvements in Policy Optimization","date":"2021-04-13","arxiv_id":"2104.06159","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/muesli-combining-improvements-in-policy#ran","syntology_url":"https://syntology.ai/paper/2104.06159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06159"}},"official":null}},{"url":"/paper/online-and-offline-reinforcement-learning-by","slug":"online-and-offline-reinforcement-learning-by","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","date":"2021-04-13","arxiv_id":"2104.06294","repositories_listed":2,"syntology":null},{"url":"/paper/tasac-temporally-abstract-soft-actor-critic","slug":"tasac-temporally-abstract-soft-actor-critic","title":"TAAC: Temporally Abstract Actor-Critic for Continuous Control","date":"2021-04-13","arxiv_id":"2104.06521","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tasac-temporally-abstract-soft-actor-critic#ran","syntology_url":"https://syntology.ai/paper/2104.06521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06521"}},"official":{"repos":["HorizonRobotics/alf","hnyu/taac"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/discovering-diverse-solutions-in-deep","slug":"discovering-diverse-solutions-in-deep","title":"Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information","date":"2021-03-12","arxiv_id":"2103.07084","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reinforcement-learning-with-dynamic","slug":"deep-reinforcement-learning-with-dynamic","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","date":"2021-02-07","arxiv_id":"2102.03765","repositories_listed":2,"syntology":null},{"url":"/paper/robust-reinforcement-learning-on-state-1","slug":"robust-reinforcement-learning-on-state-1","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","date":"2021-01-21","arxiv_id":"2101.08452","repositories_listed":2,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/robust-reinforcement-learning-on-state-1#ran","syntology_url":"https://syntology.ai/paper/2101.08452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08452"}},"official":{"repos":["huanzhang12/ATLA_robust_RL"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/es-enas-combining-evolution-strategies-with","slug":"es-enas-combining-evolution-strategies-with","title":"ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces","date":"2021-01-19","arxiv_id":"2101.07415","repositories_listed":2,"syntology":null},{"url":"/paper/reinforcement-learning-with-latent-flow-1","slug":"reinforcement-learning-with-latent-flow-1","title":"Reinforcement Learning with Latent Flow","date":"2021-01-06","arxiv_id":"2101.01857","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-with-latent-flow-1#ran","syntology_url":"https://syntology.ai/paper/2101.01857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.01857"}},"official":{"repos":["WendyShang/flare","WendyShang/dqn_zoo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/plas-latent-action-space-for-offline","slug":"plas-latent-action-space-for-offline","title":"PLAS: Latent Action Space for Offline Reinforcement Learning","date":"2020-11-14","arxiv_id":"2011.07213","repositories_listed":2,"syntology":null},{"url":"/paper/softmax-deep-double-deterministic-policy","slug":"softmax-deep-double-deterministic-policy","title":"Softmax Deep Double Deterministic Policy Gradients","date":"2020-10-19","arxiv_id":"2010.09177","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/softmax-deep-double-deterministic-policy#ran","syntology_url":"https://syntology.ai/paper/2010.09177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09177"}},"official":{"repos":["ling-pan/SD3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-visual-generalization-in-continuous-1","slug":"measuring-visual-generalization-in-continuous-1","title":"Measuring Visual Generalization in Continuous Control from Pixels","date":"2020-10-13","arxiv_id":"2010.06740","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-visual-generalization-in-continuous-1#ran","syntology_url":"https://syntology.ai/paper/2010.06740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06740"}},"official":{"repos":["QData/dmc_remastered","jakegrigsby/dmc_remastered"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-prioritized-replay-sampling-states-in","slug":"beyond-prioritized-replay-sampling-states-in","title":"Understanding and Mitigating the Limitations of Prioritized Experience Replay","date":"2020-07-19","arxiv_id":"2007.09569","repositories_listed":2,"syntology":null},{"url":"/paper/off-dynamics-reinforcement-learning-training","slug":"off-dynamics-reinforcement-learning-training","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","date":"2020-06-24","arxiv_id":"2006.13916","repositories_listed":2,"syntology":{"n":23,"n_ran":21,"n_constructed":4,"n_ran_checked":14,"n_instrument":7,"n_unverified":2,"n_honours":5,"n_violates":1,"n_no_contract":8,"n_pointer_only":7,"phrase":"21 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 5 honoured, 1 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/off-dynamics-reinforcement-learning-training#ran","syntology_url":"https://syntology.ai/paper/2006.13916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13916"}},"official":null}},{"url":"/paper/analytic-manifold-learning-unifying-and","slug":"analytic-manifold-learning-unifying-and","title":"Analytic Manifold Learning: Unifying and Evaluating Representations for Continuous Control","date":"2020-06-15","arxiv_id":"2006.08718","repositories_listed":2,"syntology":null},{"url":"/paper/what-matters-in-on-policy-reinforcement","slug":"what-matters-in-on-policy-reinforcement","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","date":"2020-06-10","arxiv_id":"2006.05990","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-matters-in-on-policy-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2006.05990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.05990"}},"official":null}},{"url":"/paper/ar-dae-towards-unbiased-neural-entropy","slug":"ar-dae-towards-unbiased-neural-entropy","title":"AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation","date":"2020-06-09","arxiv_id":"2006.05164","repositories_listed":2,"syntology":{"n":13,"n_ran":13,"n_constructed":2,"n_ran_checked":4,"n_instrument":9,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":13,"phrase":"13 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ar-dae-towards-unbiased-neural-entropy#ran","syntology_url":"https://syntology.ai/paper/2006.05164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.05164"}},"official":null}},{"url":"/paper/primal-wasserstein-imitation-learning","slug":"primal-wasserstein-imitation-learning","title":"Primal Wasserstein Imitation Learning","date":"2020-06-08","arxiv_id":"2006.04678","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/primal-wasserstein-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2006.04678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04678"}},"official":{"repos":["google-research/google-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/disagreement-regularized-imitation-learning","slug":"disagreement-regularized-imitation-learning","title":"Disagreement-Regularized Imitation Learning","date":"2020-05-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/constrained-physics-informed-deep-learning","slug":"constrained-physics-informed-deep-learning","title":"Learning Constrained Adaptive Differentiable Predictive Control Policies With Guarantees","date":"2020-04-23","arxiv_id":"2004.11184","repositories_listed":2,"syntology":null},{"url":"/paper/controllable-person-image-synthesis-with","slug":"controllable-person-image-synthesis-with","title":"Controllable Person Image Synthesis with Attribute-Decomposed GAN","date":"2020-03-27","arxiv_id":"2003.12267","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/controllable-person-image-synthesis-with#ran","syntology_url":"https://syntology.ai/paper/2003.12267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.12267"}},"official":null}},{"url":"/paper/learning-state-abstractions-for-transfer-in","slug":"learning-state-abstractions-for-transfer-in","title":"Learning State Abstractions for Transfer in Continuous Control","date":"2020-02-08","arxiv_id":"2002.05518","repositories_listed":2,"syntology":null}],"syntology_records":60,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":9,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/continuous-control-on-cartpole-balance-sparse","since_archive":"/sota/continuous-control-on-cartpole-balance-sparse#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/continuous-control-on-cartpole-swingup-2","since_archive":"/sota/continuous-control-on-cartpole-swingup-2#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/continuous-control-on-cheetah-run-2","since_archive":"/sota/continuous-control-on-cheetah-run-2#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/continuous-control-on-finger-turn-hard","since_archive":"/sota/continuous-control-on-finger-turn-hard#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/continuous-control-on-walker-stand","since_archive":"/sota/continuous-control-on-walker-stand#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/continuous-control-on-walker-walk-2","since_archive":"/sota/continuous-control-on-walker-walk-2#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/continuous-control-on-acrobot","since_archive":"/sota/continuous-control-on-acrobot#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/continuous-control-on-ant","since_archive":"/sota/continuous-control-on-ant#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/continuous-control-on-hopper","since_archive":"/sota/continuous-control-on-hopper#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/continuous-control-on-humanoid-run","since_archive":"/sota/continuous-control-on-humanoid-run#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/continuous-control-on-mountain-car","since_archive":"/sota/continuous-control-on-mountain-car#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/continuous-control-on-quadruped-run","since_archive":"/sota/continuous-control-on-quadruped-run#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/continuous-control-on-quadruped-walk","since_archive":"/sota/continuous-control-on-quadruped-walk#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/continuous-control-on-reacher-easy-2","since_archive":"/sota/continuous-control-on-reacher-easy-2#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/continuous-control-on-reacher-hard","since_archive":"/sota/continuous-control-on-reacher-hard#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/continuous-control-on-walker-run","since_archive":"/sota/continuous-control-on-walker-run#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":193,"papers_where_code_ran_first_page":"/task/continuous-control/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":12,"url":"/task/continuous-control/papers/2","json":"/task/continuous-control/papers/2.json","rows":100},{"order":"archive","page":3,"of":12,"url":"/task/continuous-control/papers/3","json":"/task/continuous-control/papers/3.json","rows":100},{"order":"archive","page":4,"of":12,"url":"/task/continuous-control/papers/4","json":"/task/continuous-control/papers/4.json","rows":100},{"order":"archive","page":5,"of":12,"url":"/task/continuous-control/papers/5","json":"/task/continuous-control/papers/5.json","rows":100},{"order":"archive","page":6,"of":12,"url":"/task/continuous-control/papers/6","json":"/task/continuous-control/papers/6.json","rows":100},{"order":"archive","page":7,"of":12,"url":"/task/continuous-control/papers/7","json":"/task/continuous-control/papers/7.json","rows":100},{"order":"archive","page":8,"of":12,"url":"/task/continuous-control/papers/8","json":"/task/continuous-control/papers/8.json","rows":100},{"order":"archive","page":9,"of":12,"url":"/task/continuous-control/papers/9","json":"/task/continuous-control/papers/9.json","rows":100},{"order":"archive","page":10,"of":12,"url":"/task/continuous-control/papers/10","json":"/task/continuous-control/papers/10.json","rows":100},{"order":"archive","page":11,"of":12,"url":"/task/continuous-control/papers/11","json":"/task/continuous-control/papers/11.json","rows":100},{"order":"archive","page":12,"of":12,"url":"/task/continuous-control/papers/12","json":"/task/continuous-control/papers/12.json","rows":61},{"order":"ran","page":1,"of":2,"url":"/task/continuous-control/papers/ran/1","json":"/task/continuous-control/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/continuous-control/papers/ran/2","json":"/task/continuous-control/papers/ran/2.json","rows":93}],"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":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"723af16db780a7a411576ecbf3971a3e6edd7cfeccb8f497d8773bdb3c0415c3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}