{"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/reinforcement-learning-2","name":"reinforcement-learning","slug":"reinforcement-learning-2","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":13427,"papers_with_code":4119,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/nasa-c-mapss","name":"NASA C-MAPSS","full_name":"Turbofan Engine Degradation Simulation Data Set","num_papers_in_archive":7}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":135,"rows_per_page":100,"shown":100,"of":13427,"of_with_code":4119,"tagged_in_all":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":957,"every_run_a_failure_of_syntologys_instrument":208,"listed_with_a_run_with_no_instrument_failure":957,"listed_every_run_a_failure_of_syntologys_instrument":208,"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/soft-actor-critic-off-policy-maximum-entropy","slug":"soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","arxiv_id":"1801.01290","repositories_listed":86,"syntology":{"n":148,"n_ran":91,"n_constructed":61,"n_ran_checked":73,"n_instrument":18,"n_unverified":57,"n_honours":3,"n_violates":1,"n_no_contract":69,"n_pointer_only":66,"phrase":"91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified","sample_list":"/paper/soft-actor-critic-off-policy-maximum-entropy#ran","syntology_url":"https://syntology.ai/paper/1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"}},"official":{"repos":["haarnoja/sac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/multi-agent-actor-critic-for-mixed","slug":"multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","arxiv_id":"1706.02275","repositories_listed":86,"syntology":{"n":143,"n_ran":75,"n_constructed":54,"n_ran_checked":68,"n_instrument":7,"n_unverified":68,"n_honours":2,"n_violates":0,"n_no_contract":66,"n_pointer_only":99,"phrase":"75 ran (of which 54 constructed an object rather than computing a result; 68 with no instrument failure: 2 honoured, 0 violated, 66 with no contract checked; 7 where Syntology's instrument failed) · 68 unverified","sample_list":"/paper/multi-agent-actor-critic-for-mixed#ran","syntology_url":"https://syntology.ai/paper/1706.02275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02275"}},"official":{"repos":["openai/multiagent-particle-envs"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/model-agnostic-meta-learning-for-fast","slug":"model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","arxiv_id":"1703.03400","repositories_listed":85,"syntology":{"n":154,"n_ran":103,"n_constructed":35,"n_ran_checked":72,"n_instrument":31,"n_unverified":51,"n_honours":6,"n_violates":1,"n_no_contract":65,"n_pointer_only":57,"phrase":"103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified","sample_list":"/paper/model-agnostic-meta-learning-for-fast#ran","syntology_url":"https://syntology.ai/paper/1703.03400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.03400"}},"official":{"repos":["cbfinn/maml","cbfinn/maml_rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"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/addressing-function-approximation-error-in","slug":"addressing-function-approximation-error-in","title":"Addressing Function Approximation Error in Actor-Critic Methods","date":"2018-02-26","arxiv_id":"1802.09477","repositories_listed":67,"syntology":{"n":36,"n_ran":26,"n_constructed":0,"n_ran_checked":20,"n_instrument":6,"n_unverified":10,"n_honours":1,"n_violates":2,"n_no_contract":17,"n_pointer_only":21,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 2 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/addressing-function-approximation-error-in#ran","syntology_url":"https://syntology.ai/paper/1802.09477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09477"}},"official":{"repos":["sfujim/TD3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mastering-chess-and-shogi-by-self-play-with-a","slug":"mastering-chess-and-shogi-by-self-play-with-a","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","date":"2017-12-05","arxiv_id":"1712.01815","repositories_listed":62,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":4,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":9,"phrase":"13 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; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mastering-chess-and-shogi-by-self-play-with-a#ran","syntology_url":"https://syntology.ai/paper/1712.01815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.01815"}},"official":null}},{"url":"/paper/darts-differentiable-architecture-search","slug":"darts-differentiable-architecture-search","title":"DARTS: Differentiable Architecture Search","date":"2018-06-24","arxiv_id":"1806.09055","repositories_listed":59,"syntology":{"n":156,"n_ran":74,"n_constructed":30,"n_ran_checked":59,"n_instrument":15,"n_unverified":82,"n_honours":10,"n_violates":1,"n_no_contract":48,"n_pointer_only":54,"phrase":"74 ran (of which 30 constructed an object rather than computing a result; 59 with no instrument failure: 10 honoured, 1 violated, 48 with no contract checked; 15 where Syntology's instrument failed) · 82 unverified","sample_list":"/paper/darts-differentiable-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1806.09055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.09055"}},"official":{"repos":["quark0/darts"],"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/soft-actor-critic-algorithms-and-applications","slug":"soft-actor-critic-algorithms-and-applications","title":"Soft Actor-Critic Algorithms and Applications","date":"2018-12-13","arxiv_id":"1812.05905","repositories_listed":52,"syntology":{"n":40,"n_ran":38,"n_constructed":0,"n_ran_checked":35,"n_instrument":3,"n_unverified":2,"n_honours":4,"n_violates":1,"n_no_contract":30,"n_pointer_only":5,"phrase":"38 ran (of which 0 constructed an object rather than computing a result; 35 with no instrument failure: 4 honoured, 1 violated, 30 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/soft-actor-critic-algorithms-and-applications#ran","syntology_url":"https://syntology.ai/paper/1812.05905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05905"}},"official":{"repos":["rail-berkeley/softlearning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/openai-gym","slug":"openai-gym","title":"OpenAI Gym","date":"2016-06-05","arxiv_id":"1606.01540","repositories_listed":45,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/openai-gym#ran","syntology_url":"https://syntology.ai/paper/1606.01540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.01540"}},"official":null}},{"url":"/paper/weight-uncertainty-in-neural-networks","slug":"weight-uncertainty-in-neural-networks","title":"Weight Uncertainty in Neural Networks","date":"2015-05-20","arxiv_id":"1505.05424","repositories_listed":38,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":3,"n_honours":4,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/weight-uncertainty-in-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1505.05424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.05424"}},"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/self-critical-sequence-training-for-image","slug":"self-critical-sequence-training-for-image","title":"Self-critical Sequence Training for Image Captioning","date":"2016-12-02","arxiv_id":"1612.00563","repositories_listed":31,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":3,"phrase":"12 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; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-critical-sequence-training-for-image#ran","syntology_url":"https://syntology.ai/paper/1612.00563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.00563"}},"official":null}},{"url":"/paper/a-deep-reinforcement-learning-framework-for","slug":"a-deep-reinforcement-learning-framework-for","title":"A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem","date":"2017-06-30","arxiv_id":"1706.10059","repositories_listed":30,"syntology":null},{"url":"/paper/direct-preference-optimization-your-language","slug":"direct-preference-optimization-your-language","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","date":"2023-05-29","arxiv_id":"2305.18290","repositories_listed":29,"syntology":{"n":31,"n_ran":25,"n_constructed":1,"n_ran_checked":21,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":21,"n_pointer_only":2,"phrase":"25 ran (of which 1 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/direct-preference-optimization-your-language#ran","syntology_url":"https://syntology.ai/paper/2305.18290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18290"}},"official":null}},{"url":"/paper/multi-goal-reinforcement-learning-challenging","slug":"multi-goal-reinforcement-learning-challenging","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","date":"2018-02-26","arxiv_id":"1802.09464","repositories_listed":28,"syntology":null},{"url":"/paper/simple-random-search-provides-a-competitive","slug":"simple-random-search-provides-a-competitive","title":"Simple random search provides a competitive approach to reinforcement learning","date":"2018-03-19","arxiv_id":"1803.07055","repositories_listed":26,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/simple-random-search-provides-a-competitive#ran","syntology_url":"https://syntology.ai/paper/1803.07055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.07055"}},"official":{"repos":["modestyachts/ARS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/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/parlai-a-dialog-research-software-platform","slug":"parlai-a-dialog-research-software-platform","title":"ParlAI: A Dialog Research Software Platform","date":"2017-05-18","arxiv_id":"1705.06476","repositories_listed":23,"syntology":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/world-models","slug":"world-models","title":"World Models","date":"2018-03-27","arxiv_id":"1803.10122","repositories_listed":22,"syntology":{"n":38,"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":17,"n_honours":1,"n_violates":0,"n_no_contract":15,"n_pointer_only":3,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/world-models#ran","syntology_url":"https://syntology.ai/paper/1803.10122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10122"}},"official":null}},{"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/dream-to-control-learning-behaviors-by-latent","slug":"dream-to-control-learning-behaviors-by-latent","title":"Dream to Control: Learning Behaviors by Latent Imagination","date":"2019-12-03","arxiv_id":"1912.01603","repositories_listed":21,"syntology":{"n":62,"n_ran":52,"n_constructed":33,"n_ran_checked":45,"n_instrument":7,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":44,"n_pointer_only":9,"phrase":"52 ran (of which 33 constructed an object rather than computing a result; 45 with no instrument failure: 1 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/dream-to-control-learning-behaviors-by-latent#ran","syntology_url":"https://syntology.ai/paper/1912.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.01603"}},"official":{"repos":["danijar/dreamer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/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/the-surprising-effectiveness-of-mappo-in","slug":"the-surprising-effectiveness-of-mappo-in","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","date":"2021-03-02","arxiv_id":"2103.01955","repositories_listed":19,"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/the-surprising-effectiveness-of-mappo-in#ran","syntology_url":"https://syntology.ai/paper/2103.01955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01955"}},"official":{"repos":["marlbenchmark/on-policy"],"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/rl2-fast-reinforcement-learning-via-slow","slug":"rl2-fast-reinforcement-learning-via-slow","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","date":"2016-11-09","arxiv_id":"1611.02779","repositories_listed":19,"syntology":{"n":21,"n_ran":11,"n_constructed":6,"n_ran_checked":8,"n_instrument":3,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/rl2-fast-reinforcement-learning-via-slow#ran","syntology_url":"https://syntology.ai/paper/1611.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.02779"}},"official":null}},{"url":"/paper/conservative-q-learning-for-offline","slug":"conservative-q-learning-for-offline","title":"Conservative Q-Learning for Offline Reinforcement Learning","date":"2020-06-08","arxiv_id":"2006.04779","repositories_listed":18,"syntology":{"n":34,"n_ran":31,"n_constructed":5,"n_ran_checked":22,"n_instrument":9,"n_unverified":3,"n_honours":5,"n_violates":2,"n_no_contract":15,"n_pointer_only":19,"phrase":"31 ran (of which 5 constructed an object rather than computing a result; 22 with no instrument failure: 5 honoured, 2 violated, 15 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/conservative-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2006.04779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04779"}},"official":{"repos":["aviralkumar2907/CQL"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/qmix-monotonic-value-function-factorisation","slug":"qmix-monotonic-value-function-factorisation","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","date":"2018-03-30","arxiv_id":"1803.11485","repositories_listed":18,"syntology":{"n":11,"n_ran":9,"n_constructed":7,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qmix-monotonic-value-function-factorisation#ran","syntology_url":"https://syntology.ai/paper/1803.11485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.11485"}},"official":{"repos":["oxwhirl/pymarl"],"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/generative-adversarial-imitation-learning","slug":"generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","date":"2016-06-10","arxiv_id":"1606.03476","repositories_listed":18,"syntology":{"n":36,"n_ran":24,"n_constructed":6,"n_ran_checked":22,"n_instrument":2,"n_unverified":12,"n_honours":2,"n_violates":1,"n_no_contract":19,"n_pointer_only":15,"phrase":"24 ran (of which 6 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 2 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/generative-adversarial-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1606.03476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.03476"}},"official":null}},{"url":"/paper/offline-reinforcement-learning-with-implicit","slug":"offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","arxiv_id":"2110.06169","repositories_listed":17,"syntology":{"n":58,"n_ran":45,"n_constructed":23,"n_ran_checked":36,"n_instrument":9,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":36,"n_pointer_only":23,"phrase":"45 ran (of which 23 constructed an object rather than computing a result; 36 with no instrument failure: 0 honoured, 0 violated, 36 with no contract checked; 9 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/offline-reinforcement-learning-with-implicit#ran","syntology_url":"https://syntology.ai/paper/2110.06169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06169"}},"official":{"repos":["rail-berkeley/rlkit","ikostrikov/implicit_q_learning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"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/openspiel-a-framework-for-reinforcement","slug":"openspiel-a-framework-for-reinforcement","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","date":"2019-08-26","arxiv_id":"1908.09453","repositories_listed":16,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/openspiel-a-framework-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1908.09453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09453"}},"official":{"repos":["deepmind/open_spiel"],"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/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/seq2sql-generating-structured-queries-from","slug":"seq2sql-generating-structured-queries-from","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","date":"2017-08-31","arxiv_id":"1709.00103","repositories_listed":15,"syntology":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/a-tutorial-on-bayesian-optimization-of","slug":"a-tutorial-on-bayesian-optimization-of","title":"A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning","date":"2010-12-12","arxiv_id":"1012.2599","repositories_listed":15,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-tutorial-on-bayesian-optimization-of#ran","syntology_url":"https://syntology.ai/paper/1012.2599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1012.2599"}},"official":null}},{"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/dopamine-a-research-framework-for-deep","slug":"dopamine-a-research-framework-for-deep","title":"Dopamine: A Research Framework for Deep Reinforcement Learning","date":"2018-12-14","arxiv_id":"1812.06110","repositories_listed":13,"syntology":{"n":16,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":13,"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) · 13 unverified","sample_list":"/paper/dopamine-a-research-framework-for-deep#ran","syntology_url":"https://syntology.ai/paper/1812.06110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.06110"}},"official":{"repos":["google/dopamine"],"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/sqlnet-generating-structured-queries-from","slug":"sqlnet-generating-structured-queries-from","title":"SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning","date":"2017-11-13","arxiv_id":"1711.04436","repositories_listed":13,"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/sqlnet-generating-structured-queries-from#ran","syntology_url":"https://syntology.ai/paper/1711.04436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.04436"}},"official":null}},{"url":"/paper/data-efficient-hierarchical-reinforcement","slug":"data-efficient-hierarchical-reinforcement","title":"Data-Efficient Hierarchical Reinforcement Learning","date":"2018-05-21","arxiv_id":"1805.08296","repositories_listed":12,"syntology":null},{"url":"/paper/neural-architecture-search-with-reinforcement","slug":"neural-architecture-search-with-reinforcement","title":"Neural Architecture Search with Reinforcement Learning","date":"2016-11-05","arxiv_id":"1611.01578","repositories_listed":12,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-architecture-search-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1611.01578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01578"}},"official":{"repos":["tensorflow/models"],"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/progressive-neural-networks","slug":"progressive-neural-networks","title":"Progressive Neural Networks","date":"2016-06-15","arxiv_id":"1606.04671","repositories_listed":12,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/progressive-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1606.04671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.04671"}},"official":null}},{"url":"/paper/trust-region-policy-optimisation-in-multi","slug":"trust-region-policy-optimisation-in-multi","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","date":"2021-09-23","arxiv_id":"2109.11251","repositories_listed":11,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/trust-region-policy-optimisation-in-multi#ran","syntology_url":"https://syntology.ai/paper/2109.11251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11251"}},"official":{"repos":["cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","anonymous-iclr22/trust-region-in-multi-agent-reinforcement-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/when-to-trust-your-model-model-based-policy","slug":"when-to-trust-your-model-model-based-policy","title":"When to Trust Your Model: Model-Based Policy Optimization","date":"2019-06-19","arxiv_id":"1906.08253","repositories_listed":11,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"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; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-to-trust-your-model-model-based-policy#ran","syntology_url":"https://syntology.ai/paper/1906.08253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08253"}},"official":{"repos":["JannerM/mbpo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/off-policy-deep-reinforcement-learning","slug":"off-policy-deep-reinforcement-learning","title":"Off-Policy Deep Reinforcement Learning without Exploration","date":"2018-12-07","arxiv_id":"1812.02900","repositories_listed":10,"syntology":{"n":14,"n_ran":14,"n_constructed":12,"n_ran_checked":14,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":9,"phrase":"14 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/off-policy-deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1812.02900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.02900"}},"official":{"repos":["sfujim/BCQ"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/starcraft-ii-a-new-challenge-for","slug":"starcraft-ii-a-new-challenge-for","title":"StarCraft II: A New Challenge for Reinforcement Learning","date":"2017-08-16","arxiv_id":"1708.04782","repositories_listed":10,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/starcraft-ii-a-new-challenge-for#ran","syntology_url":"https://syntology.ai/paper/1708.04782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.04782"}},"official":{"repos":["deepmind/pysc2"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/value-decomposition-networks-for-cooperative","slug":"value-decomposition-networks-for-cooperative","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","date":"2017-06-16","arxiv_id":"1706.05296","repositories_listed":10,"syntology":null},{"url":"/paper/parameter-space-noise-for-exploration","slug":"parameter-space-noise-for-exploration","title":"Parameter Space Noise for Exploration","date":"2017-06-06","arxiv_id":"1706.01905","repositories_listed":10,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/parameter-space-noise-for-exploration#ran","syntology_url":"https://syntology.ai/paper/1706.01905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.01905"}},"official":null}},{"url":"/paper/a-user-simulator-for-task-completion","slug":"a-user-simulator-for-task-completion","title":"A User Simulator for Task-Completion Dialogues","date":"2016-12-17","arxiv_id":"1612.05688","repositories_listed":10,"syntology":null},{"url":"/paper/neural-combinatorial-optimization-with","slug":"neural-combinatorial-optimization-with","title":"Neural Combinatorial Optimization with Reinforcement Learning","date":"2016-11-29","arxiv_id":"1611.09940","repositories_listed":10,"syntology":{"n":20,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":7,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/neural-combinatorial-optimization-with#ran","syntology_url":"https://syntology.ai/paper/1611.09940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.09940"}},"official":null}},{"url":"/paper/the-option-critic-architecture","slug":"the-option-critic-architecture","title":"The Option-Critic Architecture","date":"2016-09-16","arxiv_id":"1609.05140","repositories_listed":10,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-option-critic-architecture#ran","syntology_url":"https://syntology.ai/paper/1609.05140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.05140"}},"official":null}},{"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/comparative-evaluation-of-multi-agent-deep","slug":"comparative-evaluation-of-multi-agent-deep","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","date":"2020-06-14","arxiv_id":"2006.07869","repositories_listed":9,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/comparative-evaluation-of-multi-agent-deep#ran","syntology_url":"https://syntology.ai/paper/2006.07869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07869"}},"official":{"repos":["uoe-agents/epymarl","uoe-agents/robotic-warehouse","uoe-agents/lb-foraging"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/meta-world-a-benchmark-and-evaluation-for","slug":"meta-world-a-benchmark-and-evaluation-for","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","date":"2019-10-24","arxiv_id":"1910.10897","repositories_listed":9,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"7 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/meta-world-a-benchmark-and-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/1910.10897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10897"}},"official":{"repos":["rlworkgroup/metaworld"],"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/rlcard-a-toolkit-for-reinforcement-learning","slug":"rlcard-a-toolkit-for-reinforcement-learning","title":"RLCard: A Toolkit for Reinforcement Learning in Card Games","date":"2019-10-10","arxiv_id":"1910.04376","repositories_listed":9,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/rlcard-a-toolkit-for-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1910.04376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04376"}},"official":{"repos":["datamllab/rlcard"],"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/rlpyt-a-research-code-base-for-deep","slug":"rlpyt-a-research-code-base-for-deep","title":"rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch","date":"2019-09-03","arxiv_id":"1909.01500","repositories_listed":9,"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/rlpyt-a-research-code-base-for-deep#ran","syntology_url":"https://syntology.ai/paper/1909.01500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01500"}},"official":{"repos":["astooke/rlpyt"],"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/stochastic-latent-actor-critic-deep","slug":"stochastic-latent-actor-critic-deep","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","date":"2019-07-01","arxiv_id":"1907.00953","repositories_listed":9,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stochastic-latent-actor-critic-deep#ran","syntology_url":"https://syntology.ai/paper/1907.00953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.00953"}},"official":null}},{"url":"/paper/practical-deep-reinforcement-learning","slug":"practical-deep-reinforcement-learning","title":"Practical Deep Reinforcement Learning Approach for Stock Trading","date":"2018-11-19","arxiv_id":"1811.07522","repositories_listed":9,"syntology":null},{"url":"/paper/deep-reinforcement-learning-in-a-handful-of","slug":"deep-reinforcement-learning-in-a-handful-of","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","date":"2018-05-30","arxiv_id":"1805.12114","repositories_listed":9,"syntology":{"n":19,"n_ran":12,"n_constructed":5,"n_ran_checked":7,"n_instrument":5,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":17,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/deep-reinforcement-learning-in-a-handful-of#ran","syntology_url":"https://syntology.ai/paper/1805.12114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.12114"}},"official":{"repos":["kchua/handful-of-trials"],"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/solving-the-rubiks-cube-without-human","slug":"solving-the-rubiks-cube-without-human","title":"Solving the Rubik's Cube Without Human Knowledge","date":"2018-05-18","arxiv_id":"1805.07470","repositories_listed":9,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/solving-the-rubiks-cube-without-human#ran","syntology_url":"https://syntology.ai/paper/1805.07470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07470"}},"official":null}},{"url":"/paper/neural-network-dynamics-for-model-based-deep","slug":"neural-network-dynamics-for-model-based-deep","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","date":"2017-08-08","arxiv_id":"1708.02596","repositories_listed":9,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-network-dynamics-for-model-based-deep#ran","syntology_url":"https://syntology.ai/paper/1708.02596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02596"}},"official":null}},{"url":"/paper/meta-sgd-learning-to-learn-quickly-for-few","slug":"meta-sgd-learning-to-learn-quickly-for-few","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","date":"2017-07-31","arxiv_id":"1707.09835","repositories_listed":9,"syntology":null},{"url":"/paper/learning-to-reinforcement-learn","slug":"learning-to-reinforcement-learn","title":"Learning to reinforcement learn","date":"2016-11-17","arxiv_id":"1611.05763","repositories_listed":9,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"8 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; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/learning-to-reinforcement-learn#ran","syntology_url":"https://syntology.ai/paper/1611.05763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.05763"}},"official":null}},{"url":"/paper/weight-normalization-a-simple","slug":"weight-normalization-a-simple","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","date":"2016-02-25","arxiv_id":"1602.07868","repositories_listed":9,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 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; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/weight-normalization-a-simple#ran","syntology_url":"https://syntology.ai/paper/1602.07868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.07868"}},"official":{"repos":["TimSalimans/weight_norm"],"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-visual-continuous-control-improved","slug":"mastering-visual-continuous-control-improved","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","date":"2021-07-20","arxiv_id":"2107.09645","repositories_listed":8,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mastering-visual-continuous-control-improved#ran","syntology_url":"https://syntology.ai/paper/2107.09645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09645"}},"official":{"repos":["facebookresearch/drqv2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-minimalist-approach-to-offline","slug":"a-minimalist-approach-to-offline","title":"A Minimalist Approach to Offline Reinforcement Learning","date":"2021-06-12","arxiv_id":"2106.06860","repositories_listed":8,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-minimalist-approach-to-offline#ran","syntology_url":"https://syntology.ai/paper/2106.06860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06860"}},"official":{"repos":["sfujim/TD3_BC"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/learning-to-drive-in-a-day","slug":"learning-to-drive-in-a-day","title":"Learning to Drive in a Day","date":"2018-07-01","arxiv_id":"1807.00412","repositories_listed":8,"syntology":{"n":22,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/learning-to-drive-in-a-day#ran","syntology_url":"https://syntology.ai/paper/1807.00412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.00412"}},"official":null}},{"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/deepmind-control-suite","slug":"deepmind-control-suite","title":"DeepMind Control Suite","date":"2018-01-02","arxiv_id":"1801.00690","repositories_listed":8,"syntology":null},{"url":"/paper/scalable-trust-region-method-for-deep","slug":"scalable-trust-region-method-for-deep","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","date":"2017-08-17","arxiv_id":"1708.05144","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scalable-trust-region-method-for-deep#ran","syntology_url":"https://syntology.ai/paper/1708.05144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.05144"}},"official":{"repos":["openai/baselines"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-reinforcement-learning-for-dialogue","slug":"deep-reinforcement-learning-for-dialogue","title":"Deep Reinforcement Learning for Dialogue Generation","date":"2016-06-05","arxiv_id":"1606.01541","repositories_listed":8,"syntology":null},{"url":"/paper/continuous-deep-q-learning-with-model-based","slug":"continuous-deep-q-learning-with-model-based","title":"Continuous Deep Q-Learning with Model-based Acceleration","date":"2016-03-02","arxiv_id":"1603.00748","repositories_listed":8,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continuous-deep-q-learning-with-model-based#ran","syntology_url":"https://syntology.ai/paper/1603.00748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.00748"}},"official":null}},{"url":"/paper/value-iteration-networks","slug":"value-iteration-networks","title":"Value Iteration Networks","date":"2016-02-09","arxiv_id":"1602.02867","repositories_listed":8,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/value-iteration-networks#ran","syntology_url":"https://syntology.ai/paper/1602.02867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.02867"}},"official":{"repos":["avivt/VIN"],"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/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/mastering-diverse-domains-through-world","slug":"mastering-diverse-domains-through-world","title":"Mastering Diverse Domains through World Models","date":"2023-01-10","arxiv_id":"2301.04104","repositories_listed":7,"syntology":{"n":34,"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/mastering-diverse-domains-through-world#ran","syntology_url":"https://syntology.ai/paper/2301.04104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.04104"}},"official":{"repos":["danijar/dreamerv3"],"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/is-independent-learning-all-you-need-in-the","slug":"is-independent-learning-all-you-need-in-the","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","date":"2020-11-18","arxiv_id":"2011.09533","repositories_listed":7,"syntology":null},{"url":"/paper/datasets-for-data-driven-reinforcement","slug":"datasets-for-data-driven-reinforcement","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","date":"2020-04-15","arxiv_id":"2004.07219","repositories_listed":7,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":6,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 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; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/datasets-for-data-driven-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2004.07219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07219"}},"official":{"repos":["rail-berkeley/d4rl","rail-berkeley/offline_rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/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/gridmask-data-augmentation","slug":"gridmask-data-augmentation","title":"GridMask Data Augmentation","date":"2020-01-13","arxiv_id":"2001.04086","repositories_listed":7,"syntology":null},{"url":"/paper/training-agents-using-upside-down","slug":"training-agents-using-upside-down","title":"Training Agents using Upside-Down Reinforcement Learning","date":"2019-12-05","arxiv_id":"1912.02877","repositories_listed":7,"syntology":null},{"url":"/paper/efficient-off-policy-meta-reinforcement","slug":"efficient-off-policy-meta-reinforcement","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","date":"2019-03-19","arxiv_id":"1903.08254","repositories_listed":7,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-off-policy-meta-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1903.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.08254"}},"official":{"repos":["katerakelly/oyster"],"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/optimization-of-molecules-via-deep","slug":"optimization-of-molecules-via-deep","title":"Optimization of Molecules via Deep Reinforcement Learning","date":"2018-10-19","arxiv_id":"1810.08678","repositories_listed":7,"syntology":null},{"url":"/paper/crowd-robot-interaction-crowd-aware-robot","slug":"crowd-robot-interaction-crowd-aware-robot","title":"Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning","date":"2018-09-24","arxiv_id":"1809.08835","repositories_listed":7,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crowd-robot-interaction-crowd-aware-robot#ran","syntology_url":"https://syntology.ai/paper/1809.08835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.08835"}},"official":{"repos":["vita-epfl/CrowdNav","vita-epfl/DyNav"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vizdoom-competitions-playing-doom-from-pixels","slug":"vizdoom-competitions-playing-doom-from-pixels","title":"ViZDoom Competitions: Playing Doom from Pixels","date":"2018-09-10","arxiv_id":"1809.03470","repositories_listed":7,"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":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/vizdoom-competitions-playing-doom-from-pixels#ran","syntology_url":"https://syntology.ai/paper/1809.03470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.03470"}},"official":{"repos":["mwydmuch/ViZDoom"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/relational-deep-reinforcement-learning","slug":"relational-deep-reinforcement-learning","title":"Relational Deep Reinforcement Learning","date":"2018-06-05","arxiv_id":"1806.01830","repositories_listed":7,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"5 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/relational-deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1806.01830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01830"}},"official":null}},{"url":"/paper/some-considerations-on-learning-to-explore","slug":"some-considerations-on-learning-to-explore","title":"Some Considerations on Learning to Explore via Meta-Reinforcement Learning","date":"2018-03-03","arxiv_id":"1803.01118","repositories_listed":7,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-list-wise","slug":"deep-reinforcement-learning-for-list-wise","title":"Deep Reinforcement Learning for List-wise Recommendations","date":"2017-12-30","arxiv_id":"1801.00209","repositories_listed":7,"syntology":null},{"url":"/paper/backpropagation-through-the-void-optimizing","slug":"backpropagation-through-the-void-optimizing","title":"Backpropagation through the Void: Optimizing control variates for black-box gradient estimation","date":"2017-10-31","arxiv_id":"1711.00123","repositories_listed":7,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":3,"n_pointer_only":12,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/backpropagation-through-the-void-optimizing#ran","syntology_url":"https://syntology.ai/paper/1711.00123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00123"}},"official":{"repos":["duvenaud/relax"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-robust-rewards-with-adversarial","slug":"learning-robust-rewards-with-adversarial","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","date":"2017-10-30","arxiv_id":"1710.11248","repositories_listed":7,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/learning-robust-rewards-with-adversarial#ran","syntology_url":"https://syntology.ai/paper/1710.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11248"}},"official":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/time-contrastive-networks-self-supervised","slug":"time-contrastive-networks-self-supervised","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","date":"2017-04-23","arxiv_id":"1704.06888","repositories_listed":7,"syntology":null},{"url":"/paper/learning-cooperative-visual-dialog-agents","slug":"learning-cooperative-visual-dialog-agents","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","date":"2017-03-20","arxiv_id":"1703.06585","repositories_listed":7,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-cooperative-visual-dialog-agents#ran","syntology_url":"https://syntology.ai/paper/1703.06585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06585"}},"official":null}},{"url":"/paper/robust-adversarial-reinforcement-learning","slug":"robust-adversarial-reinforcement-learning","title":"Robust Adversarial Reinforcement Learning","date":"2017-03-08","arxiv_id":"1703.02702","repositories_listed":7,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/robust-adversarial-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1703.02702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.02702"}},"official":null}},{"url":"/paper/sample-efficient-actor-critic-with-experience","slug":"sample-efficient-actor-critic-with-experience","title":"Sample Efficient Actor-Critic with Experience Replay","date":"2016-11-03","arxiv_id":"1611.01224","repositories_listed":7,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/sample-efficient-actor-critic-with-experience#ran","syntology_url":"https://syntology.ai/paper/1611.01224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01224"}},"official":null}},{"url":"/paper/playing-fps-games-with-deep-reinforcement","slug":"playing-fps-games-with-deep-reinforcement","title":"Playing FPS Games with Deep Reinforcement Learning","date":"2016-09-18","arxiv_id":"1609.05521","repositories_listed":7,"syntology":null},{"url":"/paper/deep-reinforcement-learning-from-self-play-in","slug":"deep-reinforcement-learning-from-self-play-in","title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","date":"2016-03-03","arxiv_id":"1603.01121","repositories_listed":7,"syntology":null}],"syntology_records":79,"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":1165,"papers_where_code_ran_first_page":"/task/reinforcement-learning-2/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":135,"url":"/task/reinforcement-learning-2/papers/2","json":"/task/reinforcement-learning-2/papers/2.json","rows":100},{"order":"archive","page":3,"of":135,"url":"/task/reinforcement-learning-2/papers/3","json":"/task/reinforcement-learning-2/papers/3.json","rows":100},{"order":"archive","page":4,"of":135,"url":"/task/reinforcement-learning-2/papers/4","json":"/task/reinforcement-learning-2/papers/4.json","rows":100},{"order":"archive","page":5,"of":135,"url":"/task/reinforcement-learning-2/papers/5","json":"/task/reinforcement-learning-2/papers/5.json","rows":100},{"order":"archive","page":6,"of":135,"url":"/task/reinforcement-learning-2/papers/6","json":"/task/reinforcement-learning-2/papers/6.json","rows":100},{"order":"archive","page":7,"of":135,"url":"/task/reinforcement-learning-2/papers/7","json":"/task/reinforcement-learning-2/papers/7.json","rows":100},{"order":"archive","page":8,"of":135,"url":"/task/reinforcement-learning-2/papers/8","json":"/task/reinforcement-learning-2/papers/8.json","rows":100},{"order":"archive","page":9,"of":135,"url":"/task/reinforcement-learning-2/papers/9","json":"/task/reinforcement-learning-2/papers/9.json","rows":100},{"order":"archive","page":10,"of":135,"url":"/task/reinforcement-learning-2/papers/10","json":"/task/reinforcement-learning-2/papers/10.json","rows":100},{"order":"archive","page":11,"of":135,"url":"/task/reinforcement-learning-2/papers/11","json":"/task/reinforcement-learning-2/papers/11.json","rows":100},{"order":"archive","page":12,"of":135,"url":"/task/reinforcement-learning-2/papers/12","json":"/task/reinforcement-learning-2/papers/12.json","rows":100},{"order":"archive","page":13,"of":135,"url":"/task/reinforcement-learning-2/papers/13","json":"/task/reinforcement-learning-2/papers/13.json","rows":100},{"order":"archive","page":14,"of":135,"url":"/task/reinforcement-learning-2/papers/14","json":"/task/reinforcement-learning-2/papers/14.json","rows":100},{"order":"archive","page":15,"of":135,"url":"/task/reinforcement-learning-2/papers/15","json":"/task/reinforcement-learning-2/papers/15.json","rows":100},{"order":"archive","page":16,"of":135,"url":"/task/reinforcement-learning-2/papers/16","json":"/task/reinforcement-learning-2/papers/16.json","rows":100},{"order":"archive","page":17,"of":135,"url":"/task/reinforcement-learning-2/papers/17","json":"/task/reinforcement-learning-2/papers/17.json","rows":100},{"order":"archive","page":18,"of":135,"url":"/task/reinforcement-learning-2/papers/18","json":"/task/reinforcement-learning-2/papers/18.json","rows":100},{"order":"archive","page":19,"of":135,"url":"/task/reinforcement-learning-2/papers/19","json":"/task/reinforcement-learning-2/papers/19.json","rows":100},{"order":"archive","page":20,"of":135,"url":"/task/reinforcement-learning-2/papers/20","json":"/task/reinforcement-learning-2/papers/20.json","rows":100},{"order":"archive","page":21,"of":135,"url":"/task/reinforcement-learning-2/papers/21","json":"/task/reinforcement-learning-2/papers/21.json","rows":100},{"order":"archive","page":22,"of":135,"url":"/task/reinforcement-learning-2/papers/22","json":"/task/reinforcement-learning-2/papers/22.json","rows":100},{"order":"archive","page":23,"of":135,"url":"/task/reinforcement-learning-2/papers/23","json":"/task/reinforcement-learning-2/papers/23.json","rows":100},{"order":"archive","page":24,"of":135,"url":"/task/reinforcement-learning-2/papers/24","json":"/task/reinforcement-learning-2/papers/24.json","rows":100},{"order":"archive","page":25,"of":135,"url":"/task/reinforcement-learning-2/papers/25","json":"/task/reinforcement-learning-2/papers/25.json","rows":100},{"order":"archive","page":26,"of":135,"url":"/task/reinforcement-learning-2/papers/26","json":"/task/reinforcement-learning-2/papers/26.json","rows":100},{"order":"archive","page":27,"of":135,"url":"/task/reinforcement-learning-2/papers/27","json":"/task/reinforcement-learning-2/papers/27.json","rows":100},{"order":"archive","page":28,"of":135,"url":"/task/reinforcement-learning-2/papers/28","json":"/task/reinforcement-learning-2/papers/28.json","rows":100},{"order":"archive","page":29,"of":135,"url":"/task/reinforcement-learning-2/papers/29","json":"/task/reinforcement-learning-2/papers/29.json","rows":100},{"order":"archive","page":30,"of":135,"url":"/task/reinforcement-learning-2/papers/30","json":"/task/reinforcement-learning-2/papers/30.json","rows":100},{"order":"archive","page":31,"of":135,"url":"/task/reinforcement-learning-2/papers/31","json":"/task/reinforcement-learning-2/papers/31.json","rows":100},{"order":"archive","page":32,"of":135,"url":"/task/reinforcement-learning-2/papers/32","json":"/task/reinforcement-learning-2/papers/32.json","rows":100},{"order":"archive","page":33,"of":135,"url":"/task/reinforcement-learning-2/papers/33","json":"/task/reinforcement-learning-2/papers/33.json","rows":100},{"order":"archive","page":34,"of":135,"url":"/task/reinforcement-learning-2/papers/34","json":"/task/reinforcement-learning-2/papers/34.json","rows":100},{"order":"archive","page":35,"of":135,"url":"/task/reinforcement-learning-2/papers/35","json":"/task/reinforcement-learning-2/papers/35.json","rows":100},{"order":"archive","page":36,"of":135,"url":"/task/reinforcement-learning-2/papers/36","json":"/task/reinforcement-learning-2/papers/36.json","rows":100},{"order":"archive","page":37,"of":135,"url":"/task/reinforcement-learning-2/papers/37","json":"/task/reinforcement-learning-2/papers/37.json","rows":100},{"order":"archive","page":38,"of":135,"url":"/task/reinforcement-learning-2/papers/38","json":"/task/reinforcement-learning-2/papers/38.json","rows":100},{"order":"archive","page":39,"of":135,"url":"/task/reinforcement-learning-2/papers/39","json":"/task/reinforcement-learning-2/papers/39.json","rows":100},{"order":"archive","page":40,"of":135,"url":"/task/reinforcement-learning-2/papers/40","json":"/task/reinforcement-learning-2/papers/40.json","rows":100},{"order":"archive","page":41,"of":135,"url":"/task/reinforcement-learning-2/papers/41","json":"/task/reinforcement-learning-2/papers/41.json","rows":100},{"order":"archive","page":42,"of":135,"url":"/task/reinforcement-learning-2/papers/42","json":"/task/reinforcement-learning-2/papers/42.json","rows":100},{"order":"archive","page":43,"of":135,"url":"/task/reinforcement-learning-2/papers/43","json":"/task/reinforcement-learning-2/papers/43.json","rows":100},{"order":"archive","page":44,"of":135,"url":"/task/reinforcement-learning-2/papers/44","json":"/task/reinforcement-learning-2/papers/44.json","rows":100},{"order":"archive","page":45,"of":135,"url":"/task/reinforcement-learning-2/papers/45","json":"/task/reinforcement-learning-2/papers/45.json","rows":100},{"order":"archive","page":46,"of":135,"url":"/task/reinforcement-learning-2/papers/46","json":"/task/reinforcement-learning-2/papers/46.json","rows":100},{"order":"archive","page":47,"of":135,"url":"/task/reinforcement-learning-2/papers/47","json":"/task/reinforcement-learning-2/papers/47.json","rows":100},{"order":"archive","page":48,"of":135,"url":"/task/reinforcement-learning-2/papers/48","json":"/task/reinforcement-learning-2/papers/48.json","rows":100},{"order":"archive","page":49,"of":135,"url":"/task/reinforcement-learning-2/papers/49","json":"/task/reinforcement-learning-2/papers/49.json","rows":100},{"order":"archive","page":50,"of":135,"url":"/task/reinforcement-learning-2/papers/50","json":"/task/reinforcement-learning-2/papers/50.json","rows":100},{"order":"archive","page":51,"of":135,"url":"/task/reinforcement-learning-2/papers/51","json":"/task/reinforcement-learning-2/papers/51.json","rows":100},{"order":"archive","page":52,"of":135,"url":"/task/reinforcement-learning-2/papers/52","json":"/task/reinforcement-learning-2/papers/52.json","rows":100},{"order":"archive","page":53,"of":135,"url":"/task/reinforcement-learning-2/papers/53","json":"/task/reinforcement-learning-2/papers/53.json","rows":100},{"order":"archive","page":54,"of":135,"url":"/task/reinforcement-learning-2/papers/54","json":"/task/reinforcement-learning-2/papers/54.json","rows":100},{"order":"archive","page":55,"of":135,"url":"/task/reinforcement-learning-2/papers/55","json":"/task/reinforcement-learning-2/papers/55.json","rows":100},{"order":"archive","page":56,"of":135,"url":"/task/reinforcement-learning-2/papers/56","json":"/task/reinforcement-learning-2/papers/56.json","rows":100},{"order":"archive","page":57,"of":135,"url":"/task/reinforcement-learning-2/papers/57","json":"/task/reinforcement-learning-2/papers/57.json","rows":100},{"order":"archive","page":58,"of":135,"url":"/task/reinforcement-learning-2/papers/58","json":"/task/reinforcement-learning-2/papers/58.json","rows":100},{"order":"archive","page":59,"of":135,"url":"/task/reinforcement-learning-2/papers/59","json":"/task/reinforcement-learning-2/papers/59.json","rows":100},{"order":"archive","page":60,"of":135,"url":"/task/reinforcement-learning-2/papers/60","json":"/task/reinforcement-learning-2/papers/60.json","rows":100},{"order":"archive","page":61,"of":135,"url":"/task/reinforcement-learning-2/papers/61","json":"/task/reinforcement-learning-2/papers/61.json","rows":100},{"order":"archive","page":62,"of":135,"url":"/task/reinforcement-learning-2/papers/62","json":"/task/reinforcement-learning-2/papers/62.json","rows":100},{"order":"archive","page":63,"of":135,"url":"/task/reinforcement-learning-2/papers/63","json":"/task/reinforcement-learning-2/papers/63.json","rows":100},{"order":"archive","page":64,"of":135,"url":"/task/reinforcement-learning-2/papers/64","json":"/task/reinforcement-learning-2/papers/64.json","rows":100},{"order":"archive","page":65,"of":135,"url":"/task/reinforcement-learning-2/papers/65","json":"/task/reinforcement-learning-2/papers/65.json","rows":100},{"order":"archive","page":66,"of":135,"url":"/task/reinforcement-learning-2/papers/66","json":"/task/reinforcement-learning-2/papers/66.json","rows":100},{"order":"archive","page":67,"of":135,"url":"/task/reinforcement-learning-2/papers/67","json":"/task/reinforcement-learning-2/papers/67.json","rows":100},{"order":"archive","page":68,"of":135,"url":"/task/reinforcement-learning-2/papers/68","json":"/task/reinforcement-learning-2/papers/68.json","rows":100},{"order":"archive","page":69,"of":135,"url":"/task/reinforcement-learning-2/papers/69","json":"/task/reinforcement-learning-2/papers/69.json","rows":100},{"order":"archive","page":70,"of":135,"url":"/task/reinforcement-learning-2/papers/70","json":"/task/reinforcement-learning-2/papers/70.json","rows":100},{"order":"archive","page":71,"of":135,"url":"/task/reinforcement-learning-2/papers/71","json":"/task/reinforcement-learning-2/papers/71.json","rows":100},{"order":"archive","page":72,"of":135,"url":"/task/reinforcement-learning-2/papers/72","json":"/task/reinforcement-learning-2/papers/72.json","rows":100},{"order":"archive","page":73,"of":135,"url":"/task/reinforcement-learning-2/papers/73","json":"/task/reinforcement-learning-2/papers/73.json","rows":100},{"order":"archive","page":74,"of":135,"url":"/task/reinforcement-learning-2/papers/74","json":"/task/reinforcement-learning-2/papers/74.json","rows":100},{"order":"archive","page":75,"of":135,"url":"/task/reinforcement-learning-2/papers/75","json":"/task/reinforcement-learning-2/papers/75.json","rows":100},{"order":"archive","page":76,"of":135,"url":"/task/reinforcement-learning-2/papers/76","json":"/task/reinforcement-learning-2/papers/76.json","rows":100},{"order":"archive","page":77,"of":135,"url":"/task/reinforcement-learning-2/papers/77","json":"/task/reinforcement-learning-2/papers/77.json","rows":100},{"order":"archive","page":78,"of":135,"url":"/task/reinforcement-learning-2/papers/78","json":"/task/reinforcement-learning-2/papers/78.json","rows":100},{"order":"archive","page":79,"of":135,"url":"/task/reinforcement-learning-2/papers/79","json":"/task/reinforcement-learning-2/papers/79.json","rows":100},{"order":"archive","page":80,"of":135,"url":"/task/reinforcement-learning-2/papers/80","json":"/task/reinforcement-learning-2/papers/80.json","rows":100},{"order":"archive","page":81,"of":135,"url":"/task/reinforcement-learning-2/papers/81","json":"/task/reinforcement-learning-2/papers/81.json","rows":100},{"order":"archive","page":82,"of":135,"url":"/task/reinforcement-learning-2/papers/82","json":"/task/reinforcement-learning-2/papers/82.json","rows":100},{"order":"archive","page":83,"of":135,"url":"/task/reinforcement-learning-2/papers/83","json":"/task/reinforcement-learning-2/papers/83.json","rows":100},{"order":"archive","page":84,"of":135,"url":"/task/reinforcement-learning-2/papers/84","json":"/task/reinforcement-learning-2/papers/84.json","rows":100},{"order":"archive","page":85,"of":135,"url":"/task/reinforcement-learning-2/papers/85","json":"/task/reinforcement-learning-2/papers/85.json","rows":100},{"order":"archive","page":86,"of":135,"url":"/task/reinforcement-learning-2/papers/86","json":"/task/reinforcement-learning-2/papers/86.json","rows":100},{"order":"archive","page":87,"of":135,"url":"/task/reinforcement-learning-2/papers/87","json":"/task/reinforcement-learning-2/papers/87.json","rows":100},{"order":"archive","page":88,"of":135,"url":"/task/reinforcement-learning-2/papers/88","json":"/task/reinforcement-learning-2/papers/88.json","rows":100},{"order":"archive","page":89,"of":135,"url":"/task/reinforcement-learning-2/papers/89","json":"/task/reinforcement-learning-2/papers/89.json","rows":100},{"order":"archive","page":90,"of":135,"url":"/task/reinforcement-learning-2/papers/90","json":"/task/reinforcement-learning-2/papers/90.json","rows":100},{"order":"archive","page":91,"of":135,"url":"/task/reinforcement-learning-2/papers/91","json":"/task/reinforcement-learning-2/papers/91.json","rows":100},{"order":"archive","page":92,"of":135,"url":"/task/reinforcement-learning-2/papers/92","json":"/task/reinforcement-learning-2/papers/92.json","rows":100},{"order":"archive","page":93,"of":135,"url":"/task/reinforcement-learning-2/papers/93","json":"/task/reinforcement-learning-2/papers/93.json","rows":100},{"order":"archive","page":94,"of":135,"url":"/task/reinforcement-learning-2/papers/94","json":"/task/reinforcement-learning-2/papers/94.json","rows":100},{"order":"archive","page":95,"of":135,"url":"/task/reinforcement-learning-2/papers/95","json":"/task/reinforcement-learning-2/papers/95.json","rows":100},{"order":"archive","page":96,"of":135,"url":"/task/reinforcement-learning-2/papers/96","json":"/task/reinforcement-learning-2/papers/96.json","rows":100},{"order":"archive","page":97,"of":135,"url":"/task/reinforcement-learning-2/papers/97","json":"/task/reinforcement-learning-2/papers/97.json","rows":100},{"order":"archive","page":98,"of":135,"url":"/task/reinforcement-learning-2/papers/98","json":"/task/reinforcement-learning-2/papers/98.json","rows":100},{"order":"archive","page":99,"of":135,"url":"/task/reinforcement-learning-2/papers/99","json":"/task/reinforcement-learning-2/papers/99.json","rows":100},{"order":"archive","page":100,"of":135,"url":"/task/reinforcement-learning-2/papers/100","json":"/task/reinforcement-learning-2/papers/100.json","rows":100},{"order":"archive","page":101,"of":135,"url":"/task/reinforcement-learning-2/papers/101","json":"/task/reinforcement-learning-2/papers/101.json","rows":100},{"order":"archive","page":102,"of":135,"url":"/task/reinforcement-learning-2/papers/102","json":"/task/reinforcement-learning-2/papers/102.json","rows":100},{"order":"archive","page":103,"of":135,"url":"/task/reinforcement-learning-2/papers/103","json":"/task/reinforcement-learning-2/papers/103.json","rows":100},{"order":"archive","page":104,"of":135,"url":"/task/reinforcement-learning-2/papers/104","json":"/task/reinforcement-learning-2/papers/104.json","rows":100},{"order":"archive","page":105,"of":135,"url":"/task/reinforcement-learning-2/papers/105","json":"/task/reinforcement-learning-2/papers/105.json","rows":100},{"order":"archive","page":106,"of":135,"url":"/task/reinforcement-learning-2/papers/106","json":"/task/reinforcement-learning-2/papers/106.json","rows":100},{"order":"archive","page":107,"of":135,"url":"/task/reinforcement-learning-2/papers/107","json":"/task/reinforcement-learning-2/papers/107.json","rows":100},{"order":"archive","page":108,"of":135,"url":"/task/reinforcement-learning-2/papers/108","json":"/task/reinforcement-learning-2/papers/108.json","rows":100},{"order":"archive","page":109,"of":135,"url":"/task/reinforcement-learning-2/papers/109","json":"/task/reinforcement-learning-2/papers/109.json","rows":100},{"order":"archive","page":110,"of":135,"url":"/task/reinforcement-learning-2/papers/110","json":"/task/reinforcement-learning-2/papers/110.json","rows":100},{"order":"archive","page":111,"of":135,"url":"/task/reinforcement-learning-2/papers/111","json":"/task/reinforcement-learning-2/papers/111.json","rows":100},{"order":"archive","page":112,"of":135,"url":"/task/reinforcement-learning-2/papers/112","json":"/task/reinforcement-learning-2/papers/112.json","rows":100},{"order":"archive","page":113,"of":135,"url":"/task/reinforcement-learning-2/papers/113","json":"/task/reinforcement-learning-2/papers/113.json","rows":100},{"order":"archive","page":114,"of":135,"url":"/task/reinforcement-learning-2/papers/114","json":"/task/reinforcement-learning-2/papers/114.json","rows":100},{"order":"archive","page":115,"of":135,"url":"/task/reinforcement-learning-2/papers/115","json":"/task/reinforcement-learning-2/papers/115.json","rows":100},{"order":"archive","page":116,"of":135,"url":"/task/reinforcement-learning-2/papers/116","json":"/task/reinforcement-learning-2/papers/116.json","rows":100},{"order":"archive","page":117,"of":135,"url":"/task/reinforcement-learning-2/papers/117","json":"/task/reinforcement-learning-2/papers/117.json","rows":100},{"order":"archive","page":118,"of":135,"url":"/task/reinforcement-learning-2/papers/118","json":"/task/reinforcement-learning-2/papers/118.json","rows":100},{"order":"archive","page":119,"of":135,"url":"/task/reinforcement-learning-2/papers/119","json":"/task/reinforcement-learning-2/papers/119.json","rows":100},{"order":"archive","page":120,"of":135,"url":"/task/reinforcement-learning-2/papers/120","json":"/task/reinforcement-learning-2/papers/120.json","rows":100},{"order":"archive","page":121,"of":135,"url":"/task/reinforcement-learning-2/papers/121","json":"/task/reinforcement-learning-2/papers/121.json","rows":100},{"order":"archive","page":122,"of":135,"url":"/task/reinforcement-learning-2/papers/122","json":"/task/reinforcement-learning-2/papers/122.json","rows":100},{"order":"archive","page":123,"of":135,"url":"/task/reinforcement-learning-2/papers/123","json":"/task/reinforcement-learning-2/papers/123.json","rows":100},{"order":"archive","page":124,"of":135,"url":"/task/reinforcement-learning-2/papers/124","json":"/task/reinforcement-learning-2/papers/124.json","rows":100},{"order":"archive","page":125,"of":135,"url":"/task/reinforcement-learning-2/papers/125","json":"/task/reinforcement-learning-2/papers/125.json","rows":100},{"order":"archive","page":126,"of":135,"url":"/task/reinforcement-learning-2/papers/126","json":"/task/reinforcement-learning-2/papers/126.json","rows":100},{"order":"archive","page":127,"of":135,"url":"/task/reinforcement-learning-2/papers/127","json":"/task/reinforcement-learning-2/papers/127.json","rows":100},{"order":"archive","page":128,"of":135,"url":"/task/reinforcement-learning-2/papers/128","json":"/task/reinforcement-learning-2/papers/128.json","rows":100},{"order":"archive","page":129,"of":135,"url":"/task/reinforcement-learning-2/papers/129","json":"/task/reinforcement-learning-2/papers/129.json","rows":100},{"order":"archive","page":130,"of":135,"url":"/task/reinforcement-learning-2/papers/130","json":"/task/reinforcement-learning-2/papers/130.json","rows":100},{"order":"archive","page":131,"of":135,"url":"/task/reinforcement-learning-2/papers/131","json":"/task/reinforcement-learning-2/papers/131.json","rows":100},{"order":"archive","page":132,"of":135,"url":"/task/reinforcement-learning-2/papers/132","json":"/task/reinforcement-learning-2/papers/132.json","rows":100},{"order":"archive","page":133,"of":135,"url":"/task/reinforcement-learning-2/papers/133","json":"/task/reinforcement-learning-2/papers/133.json","rows":100},{"order":"archive","page":134,"of":135,"url":"/task/reinforcement-learning-2/papers/134","json":"/task/reinforcement-learning-2/papers/134.json","rows":100},{"order":"archive","page":135,"of":135,"url":"/task/reinforcement-learning-2/papers/135","json":"/task/reinforcement-learning-2/papers/135.json","rows":27},{"order":"ran","page":1,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/1","json":"/task/reinforcement-learning-2/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/2","json":"/task/reinforcement-learning-2/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/3","json":"/task/reinforcement-learning-2/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/4","json":"/task/reinforcement-learning-2/papers/ran/4.json","rows":100},{"order":"ran","page":5,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/5","json":"/task/reinforcement-learning-2/papers/ran/5.json","rows":100},{"order":"ran","page":6,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/6","json":"/task/reinforcement-learning-2/papers/ran/6.json","rows":100},{"order":"ran","page":7,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/7","json":"/task/reinforcement-learning-2/papers/ran/7.json","rows":100},{"order":"ran","page":8,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/8","json":"/task/reinforcement-learning-2/papers/ran/8.json","rows":100},{"order":"ran","page":9,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/9","json":"/task/reinforcement-learning-2/papers/ran/9.json","rows":100},{"order":"ran","page":10,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/10","json":"/task/reinforcement-learning-2/papers/ran/10.json","rows":100},{"order":"ran","page":11,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/11","json":"/task/reinforcement-learning-2/papers/ran/11.json","rows":100},{"order":"ran","page":12,"of":12,"url":"/task/reinforcement-learning-2/papers/ran/12","json":"/task/reinforcement-learning-2/papers/ran/12.json","rows":65}],"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":"0022ba80266926fb1023ef2e318c8fec728e1f724d96d7b7a6c615cfaad2a7ea","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}