{"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/atari-games","name":"Atari Games","slug":"atari-games","description_markdown":"The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Playing Atari with Deep Reinforcement Learning](https://arxiv.org/pdf/1312.5602v1.pdf) )</span>","categories":[{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":625,"papers_with_code":313,"benchmarks":65,"benchmark_tables_in_archive":65,"benchmark_tables_shown":65,"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":6,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","slug":"atari-games-on-atari-2600-freeway","dataset":"Atari 2600 Freeway","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":59,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO-hash","paper_title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","paper_url":"/paper/exploration-a-study-of-count-based","paper_date":"2016-11-15","arxiv_id":"1611.04717","code_links":[{"title":"uoe-agents/derl","url":"https://github.com/uoe-agents/derl"},{"title":"nhynes/abc","url":"https://github.com/nhynes/abc"},{"title":"clementbernardd/Count-Based-Exploration","url":"https://github.com/clementbernardd/Count-Based-Exploration"}],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","slug":"atari-games-on-atari-2600-breakout","dataset":"Atari 2600 Breakout","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":58,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3(200M frames)","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","slug":"atari-games-on-atari-2600-qbert","dataset":"Atari 2600 Q*Bert","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":57,"metrics":["Score","Best Score","Return"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","slug":"atari-games-on-atari-2600-seaquest","dataset":"Atari 2600 Seaquest","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":57,"metrics":["Score","Return"],"first_row_in_archive_order":{"model":"GDI-H3(200M frames)","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","slug":"atari-games-on-atari-2600-space-invaders","dataset":"Atari 2600 Space Invaders","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":55,"metrics":["Score","Best Score","Return"],"first_row_in_archive_order":{"model":"GDI-H3(200M frames)","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","slug":"atari-games-on-atari-2600-venture","dataset":"Atari 2600 Venture","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":55,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","slug":"atari-games-on-atari-2600-frostbite","dataset":"Atari 2600 Frostbite","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":53,"metrics":["Score","Best Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","slug":"atari-games-on-atari-2600-gravitar","dataset":"Atari 2600 Gravitar","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":53,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","slug":"atari-games-on-atari-2600-pong","dataset":"Atari 2600 Pong","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":52,"metrics":["Score"],"first_row_in_archive_order":{"model":"Duel noop","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_url":"/paper/dueling-network-architectures-for-deep","paper_date":"2015-11-20","arxiv_id":"1511.06581","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/dueling-network-architectures-for-deep#ran","syntology_url":"https://syntology.ai/paper/1511.06581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06581"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","slug":"atari-games-on-atari-2600-private-eye","dataset":"Atari 2600 Private Eye","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":52,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"First return, then explore","paper_url":"/paper/first-return-then-explore","paper_date":"2020-04-27","arxiv_id":"2004.12919","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/first-return-then-explore#ran","syntology_url":"https://syntology.ai/paper/2004.12919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12919"}},"official":{"repos":["uber-research/go-explore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","slug":"atari-games-on-atari-2600-montezumas-revenge","dataset":"Atari 2600 Montezuma's Revenge","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":50,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"First return, then explore","paper_url":"/paper/first-return-then-explore","paper_date":"2020-04-27","arxiv_id":"2004.12919","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/first-return-then-explore#ran","syntology_url":"https://syntology.ai/paper/2004.12919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12919"}},"official":{"repos":["uber-research/go-explore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/atari-games-on-atari-2600-alien","slug":"atari-games-on-atari-2600-alien","dataset":"Atari 2600 Alien","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":49,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","slug":"atari-games-on-atari-2600-asterix","dataset":"Atari 2600 Asterix","dataset_url":null,"rows_in_archive":49,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","slug":"atari-games-on-atari-2600-beam-rider","dataset":"Atari 2600 Beam Rider","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":49,"metrics":["Score","Return"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","slug":"atari-games-on-atari-2600-crazy-climber","dataset":"Atari 2600 Crazy Climber","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":49,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","slug":"atari-games-on-atari-2600-amidar","dataset":"Atari 2600 Amidar","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":48,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","slug":"atari-games-on-atari-2600-enduro","dataset":"Atari 2600 Enduro","dataset_url":null,"rows_in_archive":48,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-I3","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_url":"/paper/gdi-rethinking-what-makes-reinforcement","paper_date":"2021-06-11","arxiv_id":"2106.06232","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","slug":"atari-games-on-atari-2600-battle-zone","dataset":"Atari 2600 Battle Zone","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":47,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","slug":"atari-games-on-atari-2600-kangaroo","dataset":"Atari 2600 Kangaroo","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":47,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","slug":"atari-games-on-atari-2600-ms-pacman","dataset":"Atari 2600 Ms. Pacman","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":47,"metrics":["Score","Best Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","slug":"atari-games-on-atari-2600-demon-attack","dataset":"Atari 2600 Demon Attack","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":46,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","slug":"atari-games-on-atari-2600-assault","dataset":"Atari 2600 Assault","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","slug":"atari-games-on-atari-2600-bank-heist","dataset":"Atari 2600 Bank Heist","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero (Res2 Adam)","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/atari-games-on-atari-2600-boxing","slug":"atari-games-on-atari-2600-boxing","dataset":"Atari 2600 Boxing","dataset_url":null,"rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","slug":"atari-games-on-atari-2600-centipede","dataset":"Atari 2600 Centipede","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"First return, then explore","paper_url":"/paper/first-return-then-explore","paper_date":"2020-04-27","arxiv_id":"2004.12919","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/first-return-then-explore#ran","syntology_url":"https://syntology.ai/paper/2004.12919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12919"}},"official":{"repos":["uber-research/go-explore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","slug":"atari-games-on-atari-2600-chopper-command","dataset":"Atari 2600 Chopper Command","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_url":"/paper/gdi-rethinking-what-makes-reinforcement","paper_date":"2021-06-11","arxiv_id":"2106.06232","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","slug":"atari-games-on-atari-2600-james-bond","dataset":"Atari 2600 James Bond","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score","Medium Human-Normalized Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","slug":"atari-games-on-atari-2600-krull","dataset":"Atari 2600 Krull","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","slug":"atari-games-on-atari-2600-bowling","dataset":"Atari 2600 Bowling","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","slug":"atari-games-on-atari-2600-fishing-derby","dataset":"Atari 2600 Fishing Derby","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","slug":"atari-games-on-atari-2600-hero","dataset":"Atari 2600 HERO","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score","Best Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","slug":"atari-games-on-atari-2600-road-runner","dataset":"Atari 2600 Road Runner","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","slug":"atari-games-on-atari-2600-time-pilot","dataset":"Atari 2600 Time Pilot","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","slug":"atari-games-on-atari-2600-tutankham","dataset":"Atari 2600 Tutankham","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","slug":"atari-games-on-atari-2600-up-and-down","dataset":"Atari 2600 Up and Down","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-I3","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_url":"/paper/gdi-rethinking-what-makes-reinforcement","paper_date":"2021-06-11","arxiv_id":"2106.06232","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","slug":"atari-games-on-atari-2600-asteroids","dataset":"Atari 2600 Asteroids","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","slug":"atari-games-on-atari-2600-double-dunk","dataset":"Atari 2600 Double Dunk","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"UCT","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/the-arcade-learning-environment-an-evaluation#ran","syntology_url":"https://syntology.ai/paper/1207.4708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1207.4708"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","slug":"atari-games-on-atari-2600-gopher","dataset":"Atari 2600 Gopher","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-I3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","slug":"atari-games-on-atari-2600-ice-hockey","dataset":"Atari 2600 Ice Hockey","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","slug":"atari-games-on-atari-2600-kung-fu-master","dataset":"Atari 2600 Kung-Fu Master","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","slug":"atari-games-on-atari-2600-name-this-game","dataset":"Atari 2600 Name This Game","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","slug":"atari-games-on-atari-2600-star-gunner","dataset":"Atari 2600 Star Gunner","dataset_url":null,"rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","slug":"atari-games-on-atari-2600-tennis","dataset":"Atari 2600 Tennis","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-I3","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_url":"/paper/gdi-rethinking-what-makes-reinforcement","paper_date":"2021-06-11","arxiv_id":"2106.06232","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","slug":"atari-games-on-atari-2600-atlantis","dataset":"Atari 2600 Atlantis","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":42,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","slug":"atari-games-on-atari-2600-robotank","dataset":"Atari 2600 Robotank","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":42,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","slug":"atari-games-on-atari-2600-video-pinball","dataset":"Atari 2600 Video Pinball","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":42,"metrics":["Score"],"first_row_in_archive_order":{"model":"R2D2","paper_title":"Recurrent Experience Replay in Distributed Reinforcement Learning","paper_url":"/paper/recurrent-experience-replay-in-distributed","paper_date":"2019-05-01","arxiv_id":null,"code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/r2d2.py"},{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"garymm/earl","url":"https://github.com/garymm/earl/tree/master/earl/agents/r2d2"}],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","slug":"atari-games-on-atari-2600-river-raid","dataset":"Atari 2600 River Raid","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":41,"metrics":["Score","Best Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","slug":"atari-games-on-atari-2600-wizard-of-wor","dataset":"Atari 2600 Wizard of Wor","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":41,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","slug":"atari-games-on-atari-2600-zaxxon","dataset":"Atari 2600 Zaxxon","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":41,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-berzerk","slug":"atari-games-on-atari-2600-berzerk","dataset":"Atari 2600 Berzerk","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":39,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"First return, then explore","paper_url":"/paper/first-return-then-explore","paper_date":"2020-04-27","arxiv_id":"2004.12919","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/first-return-then-explore#ran","syntology_url":"https://syntology.ai/paper/2004.12919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12919"}},"official":{"repos":["uber-research/go-explore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/atari-games-on-atari-2600-pitfall","slug":"atari-games-on-atari-2600-pitfall","dataset":"Atari 2600 Pitfall!","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":23,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"Go-Explore: a New Approach for Hard-Exploration Problems","paper_url":"/paper/go-explore-a-new-approach-for-hard","paper_date":"2019-01-30","arxiv_id":"1901.10995","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"Adeikalam/Go-Explore","url":"https://github.com/Adeikalam/Go-Explore"},{"title":"Dorozhko-Anton/go-explore","url":"https://github.com/Dorozhko-Anton/go-explore"}],"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/go-explore-a-new-approach-for-hard#ran","syntology_url":"https://syntology.ai/paper/1901.10995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10995"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-skiing","slug":"atari-games-on-atari-2600-skiing","dataset":"Atari 2600 Skiing","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":23,"metrics":["Score"],"first_row_in_archive_order":{"model":"Best Learner","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/the-arcade-learning-environment-an-evaluation#ran","syntology_url":"https://syntology.ai/paper/1207.4708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1207.4708"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-solaris","slug":"atari-games-on-atari-2600-solaris","dataset":"Atari 2600 Solaris","dataset_url":null,"rows_in_archive":23,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-defender","slug":"atari-games-on-atari-2600-defender","dataset":"Atari 2600 Defender","dataset_url":null,"rows_in_archive":21,"metrics":["Score"],"first_row_in_archive_order":{"model":"CGP","paper_title":"Evolving simple programs for playing Atari games","paper_url":"/paper/evolving-simple-programs-for-playing-atari","paper_date":"2018-06-14","arxiv_id":"1806.05695","code_links":[{"title":"ShuhuaGao/gpFlappyBird","url":"https://github.com/ShuhuaGao/gpFlappyBird"},{"title":"JacobLaney/cgp-tetris","url":"https://github.com/JacobLaney/cgp-tetris"}],"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/evolving-simple-programs-for-playing-atari#ran","syntology_url":"https://syntology.ai/paper/1806.05695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05695"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-phoenix","slug":"atari-games-on-atari-2600-phoenix","dataset":"Atari 2600 Phoenix","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":21,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-yars-revenge","slug":"atari-games-on-atari-2600-yars-revenge","dataset":"Atari 2600 Yars Revenge","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":17,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-surround","slug":"atari-games-on-atari-2600-surround","dataset":"Atari 2600 Surround","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":15,"metrics":["Score"],"first_row_in_archive_order":{"model":"NoisyNet-Dueling","paper_title":"Noisy Networks for Exploration","paper_url":"/paper/noisy-networks-for-exploration","paper_date":"2017-06-30","arxiv_id":"1706.10295","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"Kaixhin/NoisyNet-A3C","url":"https://github.com/Kaixhin/NoisyNet-A3C"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"seungjaeryanlee/rldb","url":"https://github.com/seungjaeryanlee/rldb"},{"title":"behzadanksu/rl-attack","url":"https://github.com/behzadanksu/rl-attack"},{"title":"LilTwo/DRL-using-PyTorch","url":"https://github.com/LilTwo/DRL-using-PyTorch"},{"title":"hw9603/DQfD-PyTorch","url":"https://github.com/hw9603/DQfD-PyTorch"},{"title":"thomashirtz/noisy-networks","url":"https://github.com/thomashirtz/noisy-networks"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"YanSong97/Master-thesis","url":"https://github.com/YanSong97/Master-thesis"},{"title":"behzadanksu/rlattack-dev","url":"https://github.com/behzadanksu/rlattack-dev"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"}],"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/noisy-networks-for-exploration#ran","syntology_url":"https://syntology.ai/paper/1706.10295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.10295"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-games","slug":"atari-games-on-atari-games","dataset":"Atari games","dataset_url":null,"rows_in_archive":12,"metrics":["Mean Human Normalized Score","Medium Human-Normalized Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-57","slug":"atari-games-on-atari-57","dataset":"Atari-57","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":11,"metrics":["Mean Human Normalized Score","Human World Record Breakthrough"],"first_row_in_archive_order":{"model":"LBC","paper_title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","paper_url":"/paper/learnable-behavior-control-breaking-atari","paper_date":"2023-05-09","arxiv_id":"2305.05239","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-game","slug":"atari-games-on-atari-game","dataset":"atari game","dataset_url":null,"rows_in_archive":9,"metrics":["Human World Record Breakthrough"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-elevator-action","slug":"atari-games-on-atari-2600-elevator-action","dataset":"Atari 2600 Elevator Action","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":3,"metrics":["Score"],"first_row_in_archive_order":{"model":"Persistent AL","paper_title":"Increasing the Action Gap: New Operators for Reinforcement Learning","paper_url":"/paper/increasing-the-action-gap-new-operators-for","paper_date":"2015-12-15","arxiv_id":"1512.04860","code_links":[{"title":"janhuenermann/neurojs","url":"https://github.com/janhuenermann/neurojs"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"}],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-pooyan","slug":"atari-games-on-atari-2600-pooyan","dataset":"Atari 2600 Pooyan","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":3,"metrics":["Score"],"first_row_in_archive_order":{"model":"UCT","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/the-arcade-learning-environment-an-evaluation#ran","syntology_url":"https://syntology.ai/paper/1207.4708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1207.4708"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-carnival","slug":"atari-games-on-atari-2600-carnival","dataset":"Atari 2600 Carnival","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"UCT","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/the-arcade-learning-environment-an-evaluation#ran","syntology_url":"https://syntology.ai/paper/1207.4708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1207.4708"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-2600-journey-escape","slug":"atari-games-on-atari-2600-journey-escape","dataset":"Atari 2600 Journey Escape","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"UCT","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/the-arcade-learning-environment-an-evaluation#ran","syntology_url":"https://syntology.ai/paper/1207.4708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1207.4708"}},"official":null}}},{"leaderboard":"/sota/atari-games-on-atari-pong","slug":"atari-games-on-atari-pong","dataset":"Atari Pong","dataset_url":null,"rows_in_archive":1,"metrics":["Total Reward"],"first_row_in_archive_order":{"model":"GATN-TL-Atari Pong","paper_title":"Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains","paper_url":"/paper/generalized-adaptive-transfer-network","paper_date":"2025-07-02","arxiv_id":"2507.03026","code_links":[{"title":"abhi460729/GATN","url":"https://github.com/abhi460729/GATN"}],"syntology":null}}],"datasets":[{"url":"/dataset/arcade-learning-environment","name":"Arcade Learning Environment","full_name":"Arcade Learning Environment","num_papers_in_archive":366},{"url":"/dataset/dqn-replay-dataset","name":"DQN Replay Dataset","full_name":"","num_papers_in_archive":31},{"url":"/dataset/atari-head","name":"Atari-HEAD","full_name":null,"num_papers_in_archive":9},{"url":"/dataset/atari-grand-challenge","name":"Atari Grand Challenge","full_name":"","num_papers_in_archive":7},{"url":"/dataset/atariari","name":"AtariARI","full_name":"Atari Annotated RAM Interface","num_papers_in_archive":6},{"url":"/dataset/caglar","name":"RLU","full_name":"RL Unplugged","num_papers_in_archive":2}],"subtasks":[{"url":"/task/montezumas-revenge","name":"Montezuma's Revenge"}],"parent_tasks":[{"url":"/task/video-games","name":"Video Games"}],"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":7,"rows_per_page":100,"shown":100,"of":625,"of_with_code":313,"tagged_in_all":625,"counts":{"archive_papers_tagged":625,"with_a_code_link":313,"where_syntology_ran_a_sample":118,"not_listed_spam_title":0,"listed":625,"listed_where_code_ran":118,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":95,"every_run_a_failure_of_syntologys_instrument":23,"listed_with_a_run_with_no_instrument_failure":95,"listed_every_run_a_failure_of_syntologys_instrument":23,"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/playing-atari-with-deep-reinforcement","slug":"playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","arxiv_id":"1312.5602","repositories_listed":112,"syntology":{"n":117,"n_ran":64,"n_constructed":24,"n_ran_checked":46,"n_instrument":18,"n_unverified":53,"n_honours":5,"n_violates":0,"n_no_contract":41,"n_pointer_only":56,"phrase":"64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified","sample_list":"/paper/playing-atari-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1312.5602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1312.5602"}},"official":null}},{"url":"/paper/deep-reinforcement-learning-with-double-q","slug":"deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","arxiv_id":"1509.06461","repositories_listed":97,"syntology":{"n":106,"n_ran":56,"n_constructed":38,"n_ran_checked":55,"n_instrument":1,"n_unverified":50,"n_honours":0,"n_violates":0,"n_no_contract":55,"n_pointer_only":57,"phrase":"56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified","sample_list":"/paper/deep-reinforcement-learning-with-double-q#ran","syntology_url":"https://syntology.ai/paper/1509.06461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.06461"}},"official":null}},{"url":"/paper/prioritized-experience-replay","slug":"prioritized-experience-replay","title":"Prioritized Experience Replay","date":"2015-11-18","arxiv_id":"1511.05952","repositories_listed":77,"syntology":{"n":111,"n_ran":80,"n_constructed":62,"n_ran_checked":72,"n_instrument":8,"n_unverified":31,"n_honours":4,"n_violates":0,"n_no_contract":68,"n_pointer_only":43,"phrase":"80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified","sample_list":"/paper/prioritized-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1511.05952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.05952"}},"official":null}},{"url":"/paper/dueling-network-architectures-for-deep","slug":"dueling-network-architectures-for-deep","title":"Dueling Network Architectures for Deep Reinforcement Learning","date":"2015-11-20","arxiv_id":"1511.06581","repositories_listed":73,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/dueling-network-architectures-for-deep#ran","syntology_url":"https://syntology.ai/paper/1511.06581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06581"}},"official":null}},{"url":"/paper/asynchronous-methods-for-deep-reinforcement","slug":"asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","arxiv_id":"1602.01783","repositories_listed":70,"syntology":{"n":95,"n_ran":60,"n_constructed":20,"n_ran_checked":50,"n_instrument":10,"n_unverified":35,"n_honours":2,"n_violates":1,"n_no_contract":47,"n_pointer_only":20,"phrase":"60 ran (of which 20 constructed an object rather than computing a result; 50 with no instrument failure: 2 honoured, 1 violated, 47 with no contract checked; 10 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/asynchronous-methods-for-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1602.01783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.01783"}},"official":null}},{"url":"/paper/rainbow-combining-improvements-in-deep","slug":"rainbow-combining-improvements-in-deep","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","date":"2017-10-06","arxiv_id":"1710.02298","repositories_listed":34,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rainbow-combining-improvements-in-deep#ran","syntology_url":"https://syntology.ai/paper/1710.02298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.02298"}},"official":null}},{"url":"/paper/overcoming-catastrophic-forgetting-in-neural","slug":"overcoming-catastrophic-forgetting-in-neural","title":"Overcoming catastrophic forgetting in neural networks","date":"2016-12-02","arxiv_id":"1612.00796","repositories_listed":29,"syntology":{"n":22,"n_ran":16,"n_constructed":8,"n_ran_checked":12,"n_instrument":4,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":10,"n_pointer_only":4,"phrase":"16 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/overcoming-catastrophic-forgetting-in-neural#ran","syntology_url":"https://syntology.ai/paper/1612.00796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.00796"}},"official":null}},{"url":"/paper/an-intriguing-failing-of-convolutional-neural","slug":"an-intriguing-failing-of-convolutional-neural","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","date":"2018-07-09","arxiv_id":"1807.03247","repositories_listed":24,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-intriguing-failing-of-convolutional-neural#ran","syntology_url":"https://syntology.ai/paper/1807.03247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03247"}},"official":{"repos":["uber-research/coordconv"],"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/impala-scalable-distributed-deep-rl-with","slug":"impala-scalable-distributed-deep-rl-with","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","date":"2018-02-05","arxiv_id":"1802.01561","repositories_listed":24,"syntology":{"n":34,"n_ran":16,"n_constructed":6,"n_ran_checked":10,"n_instrument":6,"n_unverified":18,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":3,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/impala-scalable-distributed-deep-rl-with#ran","syntology_url":"https://syntology.ai/paper/1802.01561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.01561"}},"official":{"repos":["deepmind/scalable_agent"],"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/trust-region-policy-optimization","slug":"trust-region-policy-optimization","title":"Trust Region Policy Optimization","date":"2015-02-19","arxiv_id":"1502.05477","repositories_listed":24,"syntology":{"n":17,"n_ran":7,"n_constructed":2,"n_ran_checked":6,"n_instrument":1,"n_unverified":10,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/trust-region-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/1502.05477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.05477"}},"official":null}},{"url":"/paper/evolution-strategies-as-a-scalable","slug":"evolution-strategies-as-a-scalable","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","date":"2017-03-10","arxiv_id":"1703.03864","repositories_listed":23,"syntology":{"n":29,"n_ran":16,"n_constructed":0,"n_ran_checked":11,"n_instrument":5,"n_unverified":13,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":2,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/evolution-strategies-as-a-scalable#ran","syntology_url":"https://syntology.ai/paper/1703.03864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.03864"}},"official":{"repos":["openai/evolution-strategies-starter"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/exploration-by-random-network-distillation","slug":"exploration-by-random-network-distillation","title":"Exploration by Random Network Distillation","date":"2018-10-30","arxiv_id":"1810.12894","repositories_listed":22,"syntology":{"n":43,"n_ran":31,"n_constructed":12,"n_ran_checked":24,"n_instrument":7,"n_unverified":12,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":16,"phrase":"31 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/exploration-by-random-network-distillation#ran","syntology_url":"https://syntology.ai/paper/1810.12894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12894"}},"official":{"repos":["openai/random-network-distillation"],"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/a-distributional-perspective-on-reinforcement","slug":"a-distributional-perspective-on-reinforcement","title":"A Distributional Perspective on Reinforcement Learning","date":"2017-07-21","arxiv_id":"1707.06887","repositories_listed":22,"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/a-distributional-perspective-on-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1707.06887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06887"}},"official":null}},{"url":"/paper/decision-transformer-reinforcement-learning","slug":"decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","arxiv_id":"2106.01345","repositories_listed":20,"syntology":{"n":26,"n_ran":17,"n_constructed":10,"n_ran_checked":12,"n_instrument":5,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":8,"phrase":"17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/decision-transformer-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.01345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01345"}},"official":{"repos":["kzl/decision-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/implicit-quantile-networks-for-distributional","slug":"implicit-quantile-networks-for-distributional","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","date":"2018-06-14","arxiv_id":"1806.06923","repositories_listed":19,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/implicit-quantile-networks-for-distributional#ran","syntology_url":"https://syntology.ai/paper/1806.06923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.06923"}},"official":null}},{"url":"/paper/mastering-atari-go-chess-and-shogi-by","slug":"mastering-atari-go-chess-and-shogi-by","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","date":"2019-11-19","arxiv_id":"1911.08265","repositories_listed":18,"syntology":{"n":64,"n_ran":43,"n_constructed":36,"n_ran_checked":43,"n_instrument":0,"n_unverified":21,"n_honours":4,"n_violates":0,"n_no_contract":39,"n_pointer_only":62,"phrase":"43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}},"official":null}},{"url":"/paper/distributional-reinforcement-learning-with-1","slug":"distributional-reinforcement-learning-with-1","title":"Distributional Reinforcement Learning with Quantile Regression","date":"2017-10-27","arxiv_id":"1710.10044","repositories_listed":17,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/distributional-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/1710.10044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10044"}},"official":null}},{"url":"/paper/distributed-prioritized-experience-replay","slug":"distributed-prioritized-experience-replay","title":"Distributed Prioritized Experience Replay","date":"2018-03-02","arxiv_id":"1803.00933","repositories_listed":15,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"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) · 6 unverified","sample_list":"/paper/distributed-prioritized-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1803.00933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.00933"}},"official":null}},{"url":"/paper/noisy-networks-for-exploration","slug":"noisy-networks-for-exploration","title":"Noisy Networks for Exploration","date":"2017-06-30","arxiv_id":"1706.10295","repositories_listed":15,"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/noisy-networks-for-exploration#ran","syntology_url":"https://syntology.ai/paper/1706.10295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.10295"}},"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/soft-actor-critic-for-discrete-action","slug":"soft-actor-critic-for-discrete-action","title":"Soft Actor-Critic for Discrete Action Settings","date":"2019-10-16","arxiv_id":"1910.07207","repositories_listed":13,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":6,"n_honours":2,"n_violates":1,"n_no_contract":9,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/soft-actor-critic-for-discrete-action#ran","syntology_url":"https://syntology.ai/paper/1910.07207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07207"}},"official":{"repos":["p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/vizdoom-a-doom-based-ai-research-platform-for","slug":"vizdoom-a-doom-based-ai-research-platform-for","title":"ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning","date":"2016-05-06","arxiv_id":"1605.02097","repositories_listed":10,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vizdoom-a-doom-based-ai-research-platform-for#ran","syntology_url":"https://syntology.ai/paper/1605.02097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.02097"}},"official":{"repos":["mwydmuch/ViZDoom"],"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/mastering-atari-with-discrete-world-models-1","slug":"mastering-atari-with-discrete-world-models-1","title":"Mastering Atari with Discrete World Models","date":"2020-10-05","arxiv_id":"2010.02193","repositories_listed":9,"syntology":{"n":15,"n_ran":11,"n_constructed":1,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mastering-atari-with-discrete-world-models-1#ran","syntology_url":"https://syntology.ai/paper/2010.02193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02193"}},"official":{"repos":["danijar/dreamerv2"],"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/accelerated-methods-for-deep-reinforcement","slug":"accelerated-methods-for-deep-reinforcement","title":"Accelerated Methods for Deep Reinforcement Learning","date":"2018-03-07","arxiv_id":"1803.02811","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":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/accelerated-methods-for-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1803.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.02811"}},"official":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/human-level-control-through-deep","slug":"human-level-control-through-deep","title":"Human level control through deep reinforcement learning","date":"2015-02-25","arxiv_id":null,"repositories_listed":8,"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/unsupervised-state-representation-learning-in","slug":"unsupervised-state-representation-learning-in","title":"Unsupervised State Representation Learning in Atari","date":"2019-06-19","arxiv_id":"1906.08226","repositories_listed":7,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unsupervised-state-representation-learning-in#ran","syntology_url":"https://syntology.ai/paper/1906.08226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08226"}},"official":{"repos":["mila-iqia/atari-representation-learning"],"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/fractal-ai-a-fragile-theory-of-intelligence","slug":"fractal-ai-a-fragile-theory-of-intelligence","title":"Fractal AI: A fragile theory of intelligence","date":"2018-03-13","arxiv_id":"1803.05049","repositories_listed":7,"syntology":null},{"url":"/paper/revisiting-the-arcade-learning-environment","slug":"revisiting-the-arcade-learning-environment","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","date":"2017-09-18","arxiv_id":"1709.06009","repositories_listed":7,"syntology":null},{"url":"/paper/deep-reinforcement-learning-from-human","slug":"deep-reinforcement-learning-from-human","title":"Deep reinforcement learning from human preferences","date":"2017-06-12","arxiv_id":"1706.03741","repositories_listed":7,"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/deep-reinforcement-learning-from-human#ran","syntology_url":"https://syntology.ai/paper/1706.03741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.03741"}},"official":null}},{"url":"/paper/munchausen-reinforcement-learning","slug":"munchausen-reinforcement-learning","title":"Munchausen Reinforcement Learning","date":"2020-07-28","arxiv_id":"2007.14430","repositories_listed":6,"syntology":{"n":22,"n_ran":12,"n_constructed":11,"n_ran_checked":12,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/munchausen-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2007.14430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14430"}},"official":{"repos":["google-research/google-research"],"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/never-give-up-learning-directed-exploration-1","slug":"never-give-up-learning-directed-exploration-1","title":"Never Give Up: Learning Directed Exploration Strategies","date":"2020-02-14","arxiv_id":"2002.06038","repositories_listed":6,"syntology":{"n":14,"n_ran":7,"n_constructed":3,"n_ran_checked":5,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/never-give-up-learning-directed-exploration-1#ran","syntology_url":"https://syntology.ai/paper/2002.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06038"}},"official":null}},{"url":"/paper/fully-parameterized-quantile-function-for","slug":"fully-parameterized-quantile-function-for","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","date":"2019-11-05","arxiv_id":"1911.02140","repositories_listed":6,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/fully-parameterized-quantile-function-for#ran","syntology_url":"https://syntology.ai/paper/1911.02140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02140"}},"official":null}},{"url":"/paper/deep-exploration-via-bootstrapped-dqn","slug":"deep-exploration-via-bootstrapped-dqn","title":"Deep Exploration via Bootstrapped DQN","date":"2016-02-15","arxiv_id":"1602.04621","repositories_listed":6,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/deep-exploration-via-bootstrapped-dqn#ran","syntology_url":"https://syntology.ai/paper/1602.04621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.04621"}},"official":null}},{"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/going-beyond-linear-transformers-with","slug":"going-beyond-linear-transformers-with","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","date":"2021-06-11","arxiv_id":"2106.06295","repositories_listed":5,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"9 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/going-beyond-linear-transformers-with#ran","syntology_url":"https://syntology.ai/paper/2106.06295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06295"}},"official":{"repos":["IDSIA/recurrent-fwp"],"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/evolving-reinforcement-learning-algorithms-1","slug":"evolving-reinforcement-learning-algorithms-1","title":"Evolving Reinforcement Learning Algorithms","date":"2021-01-08","arxiv_id":"2101.03958","repositories_listed":5,"syntology":null},{"url":"/paper/agent57-outperforming-the-atari-human","slug":"agent57-outperforming-the-atari-human","title":"Agent57: Outperforming the Atari Human Benchmark","date":"2020-03-30","arxiv_id":"2003.13350","repositories_listed":5,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}},"official":null}},{"url":"/paper/large-scale-study-of-curiosity-driven","slug":"large-scale-study-of-curiosity-driven","title":"Large-Scale Study of Curiosity-Driven Learning","date":"2018-08-13","arxiv_id":"1808.04355","repositories_listed":5,"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/large-scale-study-of-curiosity-driven#ran","syntology_url":"https://syntology.ai/paper/1808.04355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.04355"}},"official":{"repos":["openai/large-scale-curiosity"],"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/deep-recurrent-q-learning-for-partially","slug":"deep-recurrent-q-learning-for-partially","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","date":"2015-07-23","arxiv_id":"1507.06527","repositories_listed":5,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/deep-recurrent-q-learning-for-partially#ran","syntology_url":"https://syntology.ai/paper/1507.06527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1507.06527"}},"official":null}},{"url":"/paper/recurrent-rational-networks","slug":"recurrent-rational-networks","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09407","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recurrent-rational-networks#ran","syntology_url":"https://syntology.ai/paper/2102.09407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.09407"}},"official":{"repos":["ml-research/rational_activations","ml-research/rational_rl","ml-research/rational_sl","k4ntz/activation-functions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-imitation-learning","slug":"self-imitation-learning","title":"Self-Imitation Learning","date":"2018-06-14","arxiv_id":"1806.05635","repositories_listed":4,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1806.05635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05635"}},"official":{"repos":["junhyukoh/self-imitation-learning"],"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/a-deeper-look-at-experience-replay","slug":"a-deeper-look-at-experience-replay","title":"A Deeper Look at Experience Replay","date":"2017-12-04","arxiv_id":"1712.01275","repositories_listed":4,"syntology":null},{"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/hyperagent-a-simple-scalable-efficient-and","slug":"hyperagent-a-simple-scalable-efficient-and","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","date":"2024-02-05","arxiv_id":"2402.10228","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperagent-a-simple-scalable-efficient-and#ran","syntology_url":"https://syntology.ai/paper/2402.10228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10228"}},"official":{"repos":["szrlee/hyperagent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/minedojo-building-open-ended-embodied-agents","slug":"minedojo-building-open-ended-embodied-agents","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","date":"2022-06-17","arxiv_id":"2206.08853","repositories_listed":3,"syntology":{"n":28,"n_ran":14,"n_constructed":2,"n_ran_checked":10,"n_instrument":4,"n_unverified":14,"n_honours":0,"n_violates":3,"n_no_contract":7,"n_pointer_only":0,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 3 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/minedojo-building-open-ended-embodied-agents#ran","syntology_url":"https://syntology.ai/paper/2206.08853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08853"}},"official":{"repos":["MineDojo/MineDojo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mastering-atari-games-with-limited-data","slug":"mastering-atari-games-with-limited-data","title":"Mastering Atari Games with Limited Data","date":"2021-10-30","arxiv_id":"2111.00210","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mastering-atari-games-with-limited-data#ran","syntology_url":"https://syntology.ai/paper/2111.00210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00210"}},"official":{"repos":["werner-duvaud/muzero-general","yewr/efficientzero"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-learning-of-structured-world-1","slug":"contrastive-learning-of-structured-world-1","title":"Contrastive Learning of Structured World Models","date":"2019-11-27","arxiv_id":"1911.12247","repositories_listed":3,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/contrastive-learning-of-structured-world-1#ran","syntology_url":"https://syntology.ai/paper/1911.12247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12247"}},"official":{"repos":["tkipf/c-swm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/recurrent-independent-mechanisms","slug":"recurrent-independent-mechanisms","title":"Recurrent Independent Mechanisms","date":"2019-09-24","arxiv_id":"1909.10893","repositories_listed":3,"syntology":{"n":20,"n_ran":14,"n_constructed":9,"n_ran_checked":14,"n_instrument":0,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":20,"phrase":"14 ran (of which 9 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) · 6 unverified","sample_list":"/paper/recurrent-independent-mechanisms#ran","syntology_url":"https://syntology.ai/paper/1909.10893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10893"}},"official":null}},{"url":"/paper/recurrent-experience-replay-in-distributed","slug":"recurrent-experience-replay-in-distributed","title":"Recurrent Experience Replay in Distributed Reinforcement Learning","date":"2019-05-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/improved-robustness-of-reinforcement-learning","slug":"improved-robustness-of-reinforcement-learning","title":"Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to ATARI games","date":"2019-03-26","arxiv_id":"1903.11012","repositories_listed":3,"syntology":null},{"url":"/paper/minatar-an-atari-inspired-testbed-for-more","slug":"minatar-an-atari-inspired-testbed-for-more","title":"MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments","date":"2019-03-07","arxiv_id":"1903.03176","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":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/minatar-an-atari-inspired-testbed-for-more#ran","syntology_url":"https://syntology.ai/paper/1903.03176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03176"}},"official":{"repos":["kenjyoung/MinAtar"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/obstacle-tower-a-generalization-challenge-in","slug":"obstacle-tower-a-generalization-challenge-in","title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","date":"2019-02-04","arxiv_id":"1902.01378","repositories_listed":3,"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":0,"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/obstacle-tower-a-generalization-challenge-in#ran","syntology_url":"https://syntology.ai/paper/1902.01378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01378"}},"official":{"repos":["Unity-Technologies/obstacle-tower-env"],"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/go-explore-a-new-approach-for-hard","slug":"go-explore-a-new-approach-for-hard","title":"Go-Explore: a New Approach for Hard-Exploration Problems","date":"2019-01-30","arxiv_id":"1901.10995","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/go-explore-a-new-approach-for-hard#ran","syntology_url":"https://syntology.ai/paper/1901.10995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10995"}},"official":null}},{"url":"/paper/toybox-better-atari-environments-for-testing","slug":"toybox-better-atari-environments-for-testing","title":"ToyBox: Better Atari Environments for Testing Reinforcement Learning Agents","date":"2018-12-06","arxiv_id":"1812.02850","repositories_listed":3,"syntology":null},{"url":"/paper/scalable-agent-alignment-via-reward-modeling","slug":"scalable-agent-alignment-via-reward-modeling","title":"Scalable agent alignment via reward modeling: a research direction","date":"2018-11-19","arxiv_id":"1811.07871","repositories_listed":3,"syntology":null},{"url":"/paper/deep-quality-value-dqv-learning","slug":"deep-quality-value-dqv-learning","title":"Deep Quality-Value (DQV) Learning","date":"2018-09-30","arxiv_id":"1810.00368","repositories_listed":3,"syntology":null},{"url":"/paper/surprising-negative-results-for-generative","slug":"surprising-negative-results-for-generative","title":"Surprising Negative Results for Generative Adversarial Tree Search","date":"2018-06-15","arxiv_id":"1806.05780","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/safe-and-efficient-off-policy-reinforcement","slug":"safe-and-efficient-off-policy-reinforcement","title":"Safe and Efficient Off-Policy Reinforcement Learning","date":"2016-06-08","arxiv_id":"1606.02647","repositories_listed":3,"syntology":null},{"url":"/paper/learning-from-the-memory-of-atari-2600","slug":"learning-from-the-memory-of-atari-2600","title":"Learning from the memory of Atari 2600","date":"2016-05-04","arxiv_id":"1605.01335","repositories_listed":3,"syntology":null},{"url":"/paper/deep-attention-recurrent-q-network","slug":"deep-attention-recurrent-q-network","title":"Deep Attention Recurrent Q-Network","date":"2015-12-05","arxiv_id":"1512.01693","repositories_listed":3,"syntology":null},{"url":"/paper/actor-mimic-deep-multitask-and-transfer","slug":"actor-mimic-deep-multitask-and-transfer","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","date":"2015-11-19","arxiv_id":"1511.06342","repositories_listed":3,"syntology":null},{"url":"/paper/massively-parallel-methods-for-deep","slug":"massively-parallel-methods-for-deep","title":"Massively Parallel Methods for Deep Reinforcement Learning","date":"2015-07-15","arxiv_id":"1507.04296","repositories_listed":3,"syntology":null},{"url":"/paper/the-arcade-learning-environment-an-evaluation","slug":"the-arcade-learning-environment-an-evaluation","title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","date":"2012-07-19","arxiv_id":"1207.4708","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/the-arcade-learning-environment-an-evaluation#ran","syntology_url":"https://syntology.ai/paper/1207.4708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1207.4708"}},"official":null}},{"url":"/paper/text-m-text-3-a-modular-world-model-over","slug":"text-m-text-3-a-modular-world-model-over","title":"Uncovering Untapped Potential in Sample-Efficient World Model Agents","date":"2025-02-17","arxiv_id":"2502.11537","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/text-m-text-3-a-modular-world-model-over#ran","syntology_url":"https://syntology.ai/paper/2502.11537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11537"}},"official":{"repos":["leor-c/m3","leor-c/simulus"],"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/active-reinforcement-learning-for-robust","slug":"active-reinforcement-learning-for-robust","title":"Active Reinforcement Learning for Robust Building Control","date":"2023-12-16","arxiv_id":"2312.10289","repositories_listed":2,"syntology":null},{"url":"/paper/exploration-by-self-supervised-exploitation","slug":"exploration-by-self-supervised-exploitation","title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","date":"2023-02-22","arxiv_id":"2302.11563","repositories_listed":2,"syntology":null},{"url":"/paper/a-deep-reinforcement-learning-approach-for-13","slug":"a-deep-reinforcement-learning-approach-for-13","title":"A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games","date":"2022-07-18","arxiv_id":"2207.08894","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-deep-reinforcement-learning-approach-for-13#ran","syntology_url":"https://syntology.ai/paper/2207.08894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08894"}},"official":{"repos":["quantumiracle/mars","quantumiracle/nash-dqn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/large-batch-experience-replay","slug":"large-batch-experience-replay","title":"Large Batch Experience Replay","date":"2021-10-04","arxiv_id":"2110.01528","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":4,"n_ran_checked":4,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/large-batch-experience-replay#ran","syntology_url":"https://syntology.ai/paper/2110.01528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01528"}},"official":{"repos":["sureli/laber"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/crop-certifying-robust-policies-for","slug":"crop-certifying-robust-policies-for","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","date":"2021-06-17","arxiv_id":"2106.09292","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crop-certifying-robust-policies-for#ran","syntology_url":"https://syntology.ai/paper/2106.09292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09292"}},"official":{"repos":["ai-secure/crop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mico-learning-improved-representations-via","slug":"mico-learning-improved-representations-via","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","date":"2021-06-03","arxiv_id":"2106.08229","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mico-learning-improved-representations-via#ran","syntology_url":"https://syntology.ai/paper/2106.08229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08229"}},"official":{"repos":["google-research/google-research"],"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/action-advising-with-advice-imitation-in-deep","slug":"action-advising-with-advice-imitation-in-deep","title":"Action Advising with Advice Imitation in Deep Reinforcement Learning","date":"2021-04-17","arxiv_id":"2104.08441","repositories_listed":2,"syntology":null},{"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/revisiting-prioritized-experience-replay-a-1","slug":"revisiting-prioritized-experience-replay-a-1","title":"Revisiting Prioritized Experience Replay: A Value Perspective","date":"2021-02-05","arxiv_id":"2102.03261","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/augmenting-policy-learning-with-routines","slug":"augmenting-policy-learning-with-routines","title":"Augmenting Policy Learning with Routines Discovered from a Single Demonstration","date":"2020-12-23","arxiv_id":"2012.12469","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/augmenting-policy-learning-with-routines#ran","syntology_url":"https://syntology.ai/paper/2012.12469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.12469"}},"official":{"repos":["sjtuytc/-AAAI21-RoutineAugmentedPolicyLearning-RAPL-","sjtuytc/AAAI21-RoutineAugmentedPolicyLearning"],"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/revisiting-rainbow-promoting-more-insightful","slug":"revisiting-rainbow-promoting-more-insightful","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","date":"2020-11-20","arxiv_id":"2011.14826","repositories_listed":2,"syntology":null},{"url":"/paper/ranking-policy-decisions","slug":"ranking-policy-decisions","title":"Ranking Policy Decisions","date":"2020-08-31","arxiv_id":"2008.13607","repositories_listed":2,"syntology":null},{"url":"/paper/robust-deep-reinforcement-learning-through","slug":"robust-deep-reinforcement-learning-through","title":"Robust Deep Reinforcement Learning through Adversarial Loss","date":"2020-08-05","arxiv_id":"2008.01976","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-through#ran","syntology_url":"https://syntology.ai/paper/2008.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01976"}},"official":{"repos":["tuomaso/radial_rl","tuomaso/radial_rl_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/discovering-reinforcement-learning-algorithms","slug":"discovering-reinforcement-learning-algorithms","title":"Discovering Reinforcement Learning Algorithms","date":"2020-07-17","arxiv_id":"2007.08794","repositories_listed":2,"syntology":null},{"url":"/paper/rl-unplugged-benchmarks-for-offline","slug":"rl-unplugged-benchmarks-for-offline","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","date":"2020-06-24","arxiv_id":"2006.13888","repositories_listed":2,"syntology":null},{"url":"/paper/first-return-then-explore","slug":"first-return-then-explore","title":"First return, then explore","date":"2020-04-27","arxiv_id":"2004.12919","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/first-return-then-explore#ran","syntology_url":"https://syntology.ai/paper/2004.12919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12919"}},"official":{"repos":["uber-research/go-explore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-unknown-states-with-action-balance","slug":"exploring-unknown-states-with-action-balance","title":"Exploring Unknown States with Action Balance","date":"2020-03-10","arxiv_id":"2003.04518","repositories_listed":2,"syntology":null},{"url":"/paper/explain-your-move-understanding-agent-actions-1","slug":"explain-your-move-understanding-agent-actions-1","title":"Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution","date":"2019-12-23","arxiv_id":"1912.12191","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/explain-your-move-understanding-agent-actions-1#ran","syntology_url":"https://syntology.ai/paper/1912.12191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.12191"}},"official":{"repos":["rl-interpretation/understandingRL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/r2d2-reliable-and-repeatable-detector-and","slug":"r2d2-reliable-and-repeatable-detector-and","title":"R2D2: Reliable and Repeatable Detector and Descriptor","date":"2019-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/zpd-teaching-strategies-for-deep","slug":"zpd-teaching-strategies-for-deep","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","date":"2019-10-26","arxiv_id":"1910.12154","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zpd-teaching-strategies-for-deep#ran","syntology_url":"https://syntology.ai/paper/1910.12154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12154"}},"official":null}},{"url":"/paper/performing-deep-recurrent-double-q-learning","slug":"performing-deep-recurrent-double-q-learning","title":"Performing Deep Recurrent Double Q-Learning for Atari Games","date":"2019-08-16","arxiv_id":"1908.06040","repositories_listed":2,"syntology":null},{"url":"/paper/gpu-accelerated-atari-emulation-for","slug":"gpu-accelerated-atari-emulation-for","title":"Accelerating Reinforcement Learning through GPU Atari Emulation","date":"2019-07-19","arxiv_id":"1907.08467","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/gpu-accelerated-atari-emulation-for#ran","syntology_url":"https://syntology.ai/paper/1907.08467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.08467"}},"official":{"repos":["NVLABs/cule"],"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":["official"]}}},{"url":"/paper/model-based-reinforcement-learning-for-atari","slug":"model-based-reinforcement-learning-for-atari","title":"Model-Based Reinforcement Learning for Atari","date":"2019-03-01","arxiv_id":"1903.00374","repositories_listed":2,"syntology":{"n":21,"n_ran":16,"n_constructed":8,"n_ran_checked":10,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":17,"phrase":"16 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/model-based-reinforcement-learning-for-atari#ran","syntology_url":"https://syntology.ai/paper/1903.00374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.00374"}},"official":{"repos":["tensorflow/tensor2tensor"],"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":["listed","official"]}}},{"url":"/paper/revisiting-the-softmax-bellman-operator","slug":"revisiting-the-softmax-bellman-operator","title":"Revisiting the Softmax Bellman Operator: New Benefits and New Perspective","date":"2018-12-02","arxiv_id":"1812.00456","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/revisiting-the-softmax-bellman-operator#ran","syntology_url":"https://syntology.ai/paper/1812.00456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00456"}},"official":{"repos":["zhao-song/Softmax-DQN"],"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/reward-learning-from-human-preferences-and","slug":"reward-learning-from-human-preferences-and","title":"Reward learning from human preferences and demonstrations in Atari","date":"2018-11-15","arxiv_id":"1811.06521","repositories_listed":2,"syntology":null},{"url":"/paper/temporal-regularization-in-markov-decision","slug":"temporal-regularization-in-markov-decision","title":"Temporal Regularization in Markov Decision Process","date":"2018-11-01","arxiv_id":"1811.00429","repositories_listed":2,"syntology":null},{"url":"/paper/fast-deep-reinforcement-learning-using-online","slug":"fast-deep-reinforcement-learning-using-online","title":"Fast deep reinforcement learning using online adjustments from the past","date":"2018-10-18","arxiv_id":"1810.08163","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/fast-deep-reinforcement-learning-using-online#ran","syntology_url":"https://syntology.ai/paper/1810.08163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.08163"}},"official":null}},{"url":"/paper/multi-task-deep-reinforcement-learning-with","slug":"multi-task-deep-reinforcement-learning-with","title":"Multi-task Deep Reinforcement Learning with PopArt","date":"2018-09-12","arxiv_id":"1809.04474","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":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-deep-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/1809.04474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.04474"}},"official":null}},{"url":"/paper/count-based-exploration-with-the-successor","slug":"count-based-exploration-with-the-successor","title":"Count-Based Exploration with the Successor Representation","date":"2018-07-31","arxiv_id":"1807.11622","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/count-based-exploration-with-the-successor#ran","syntology_url":"https://syntology.ai/paper/1807.11622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.11622"}},"official":{"repos":["mcmachado/count_based_exploration_sr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-optimization-with-penalized-point","slug":"policy-optimization-with-penalized-point","title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","date":"2018-07-02","arxiv_id":"1807.00442","repositories_listed":2,"syntology":null},{"url":"/paper/rudder-return-decomposition-for-delayed","slug":"rudder-return-decomposition-for-delayed","title":"RUDDER: Return Decomposition for Delayed Rewards","date":"2018-06-20","arxiv_id":"1806.07857","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rudder-return-decomposition-for-delayed#ran","syntology_url":"https://syntology.ai/paper/1806.07857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.07857"}},"official":{"repos":["ml-jku/baselines-rudder","ml-jku/rudder"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}}],"syntology_records":67,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":118,"papers_where_code_ran_first_page":"/task/atari-games/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":7,"url":"/task/atari-games/papers/2","json":"/task/atari-games/papers/2.json","rows":100},{"order":"archive","page":3,"of":7,"url":"/task/atari-games/papers/3","json":"/task/atari-games/papers/3.json","rows":100},{"order":"archive","page":4,"of":7,"url":"/task/atari-games/papers/4","json":"/task/atari-games/papers/4.json","rows":100},{"order":"archive","page":5,"of":7,"url":"/task/atari-games/papers/5","json":"/task/atari-games/papers/5.json","rows":100},{"order":"archive","page":6,"of":7,"url":"/task/atari-games/papers/6","json":"/task/atari-games/papers/6.json","rows":100},{"order":"archive","page":7,"of":7,"url":"/task/atari-games/papers/7","json":"/task/atari-games/papers/7.json","rows":25},{"order":"ran","page":1,"of":2,"url":"/task/atari-games/papers/ran/1","json":"/task/atari-games/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/atari-games/papers/ran/2","json":"/task/atari-games/papers/ran/2.json","rows":18}],"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":"2239a83bc344cc7627fca93da5f84f3dfdce9576f3f426f0f5499122fbfc2f1e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}