{"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/q-learning","name":"Q-Learning","slug":"q-learning","description_markdown":"The goal of Q-learning is to learn a policy, which tells an agent what action to take under what circumstances.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Playing Atari with Deep Reinforcement Learning](https://arxiv.org/pdf/1312.5602v1.pdf) )</span>","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1918,"papers_with_code":463,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/vizdoom","name":"VizDoom","full_name":"VizDoom","num_papers_in_archive":156},{"url":"/dataset/yeast","name":"Yeast","full_name":"","num_papers_in_archive":18}],"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":20,"rows_per_page":100,"shown":100,"of":1918,"of_with_code":463,"tagged_in_all":1918,"counts":{"archive_papers_tagged":1918,"with_a_code_link":463,"where_syntology_ran_a_sample":119,"not_listed_spam_title":0,"listed":1918,"listed_where_code_ran":119,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":102,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":102,"listed_every_run_a_failure_of_syntologys_instrument":17,"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/continuous-control-with-deep-reinforcement","slug":"continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","arxiv_id":"1509.02971","repositories_listed":161,"syntology":{"n":306,"n_ran":163,"n_constructed":126,"n_ran_checked":152,"n_instrument":11,"n_unverified":143,"n_honours":3,"n_violates":0,"n_no_contract":149,"n_pointer_only":163,"phrase":"163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified","sample_list":"/paper/continuous-control-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1509.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.02971"}},"official":null}},{"url":"/paper/playing-atari-with-deep-reinforcement","slug":"playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","arxiv_id":"1312.5602","repositories_listed":112,"syntology":{"n":117,"n_ran":64,"n_constructed":24,"n_ran_checked":46,"n_instrument":18,"n_unverified":53,"n_honours":5,"n_violates":0,"n_no_contract":41,"n_pointer_only":56,"phrase":"64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified","sample_list":"/paper/playing-atari-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1312.5602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1312.5602"}},"official":null}},{"url":"/paper/deep-reinforcement-learning-with-double-q","slug":"deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","arxiv_id":"1509.06461","repositories_listed":97,"syntology":{"n":106,"n_ran":56,"n_constructed":38,"n_ran_checked":55,"n_instrument":1,"n_unverified":50,"n_honours":0,"n_violates":0,"n_no_contract":55,"n_pointer_only":57,"phrase":"56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified","sample_list":"/paper/deep-reinforcement-learning-with-double-q#ran","syntology_url":"https://syntology.ai/paper/1509.06461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.06461"}},"official":null}},{"url":"/paper/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/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/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/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/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/a-disembodied-developmental-robotic-agent","slug":"a-disembodied-developmental-robotic-agent","title":"A disembodied developmental robotic agent called Samu Bátfai","date":"2015-11-09","arxiv_id":"1511.02889","repositories_listed":15,"syntology":null},{"url":"/paper/deep-neuroevolution-genetic-algorithms-are-a","slug":"deep-neuroevolution-genetic-algorithms-are-a","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","date":"2017-12-18","arxiv_id":"1712.06567","repositories_listed":12,"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":4,"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/deep-neuroevolution-genetic-algorithms-are-a#ran","syntology_url":"https://syntology.ai/paper/1712.06567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.06567"}},"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/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/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/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/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/randomized-ensembled-double-q-learning-1","slug":"randomized-ensembled-double-q-learning-1","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","date":"2021-01-15","arxiv_id":"2101.05982","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/randomized-ensembled-double-q-learning-1#ran","syntology_url":"https://syntology.ai/paper/2101.05982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.05982"}},"official":{"repos":["watchernyu/REDQ"],"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/qplex-duplex-dueling-multi-agent-q-learning","slug":"qplex-duplex-dueling-multi-agent-q-learning","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","date":"2020-08-03","arxiv_id":"2008.01062","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/qplex-duplex-dueling-multi-agent-q-learning#ran","syntology_url":"https://syntology.ai/paper/2008.01062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01062"}},"official":{"repos":["wjh720/QPLEX"],"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/deeptraffic-crowdsourced-hyperparameter","slug":"deeptraffic-crowdsourced-hyperparameter","title":"DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation","date":"2018-01-09","arxiv_id":"1801.02805","repositories_listed":6,"syntology":null},{"url":"/paper/deep-q-learning-from-demonstrations","slug":"deep-q-learning-from-demonstrations","title":"Deep Q-learning from Demonstrations","date":"2017-04-12","arxiv_id":"1704.03732","repositories_listed":6,"syntology":null},{"url":"/paper/uncertainty-based-offline-reinforcement","slug":"uncertainty-based-offline-reinforcement","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","date":"2021-10-04","arxiv_id":"2110.01548","repositories_listed":5,"syntology":{"n":21,"n_ran":13,"n_constructed":11,"n_ran_checked":12,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"13 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/uncertainty-based-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2110.01548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01548"}},"official":null}},{"url":"/paper/iq-learn-inverse-soft-q-learning-for","slug":"iq-learn-inverse-soft-q-learning-for","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","date":"2021-06-23","arxiv_id":"2106.12142","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/iq-learn-inverse-soft-q-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.12142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12142"}},"official":{"repos":["Div99/IQ-Learn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/benchmarking-batch-deep-reinforcement","slug":"benchmarking-batch-deep-reinforcement","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","date":"2019-10-03","arxiv_id":"1910.01708","repositories_listed":5,"syntology":null},{"url":"/paper/sqil-imitation-learning-via-regularized","slug":"sqil-imitation-learning-via-regularized","title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","date":"2019-05-27","arxiv_id":"1905.11108","repositories_listed":5,"syntology":null},{"url":"/paper/stabilising-experience-replay-for-deep-multi","slug":"stabilising-experience-replay-for-deep-multi","title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","date":"2017-02-28","arxiv_id":"1702.08887","repositories_listed":5,"syntology":null},{"url":"/paper/designing-neural-network-architectures-using","slug":"designing-neural-network-architectures-using","title":"Designing Neural Network Architectures using Reinforcement Learning","date":"2016-11-07","arxiv_id":"1611.02167","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-neural-network-architectures-using#ran","syntology_url":"https://syntology.ai/paper/1611.02167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.02167"}},"official":null}},{"url":"/paper/deep-recurrent-q-learning-for-partially","slug":"deep-recurrent-q-learning-for-partially","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","date":"2015-07-23","arxiv_id":"1507.06527","repositories_listed":5,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/deep-recurrent-q-learning-for-partially#ran","syntology_url":"https://syntology.ai/paper/1507.06527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1507.06527"}},"official":null}},{"url":"/paper/hierarchical-reinforcement-learning-with-the","slug":"hierarchical-reinforcement-learning-with-the","title":"Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition","date":"1999-05-21","arxiv_id":"cs/9905014","repositories_listed":5,"syntology":null},{"url":"/paper/offline-rl-with-no-ood-actions-in-sample","slug":"offline-rl-with-no-ood-actions-in-sample","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","date":"2023-03-28","arxiv_id":"2303.15810","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/offline-rl-with-no-ood-actions-in-sample#ran","syntology_url":"https://syntology.ai/paper/2303.15810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15810"}},"official":{"repos":["ryanxhr/ivr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/extreme-q-learning-maxent-rl-without-entropy","slug":"extreme-q-learning-maxent-rl-without-entropy","title":"Extreme Q-Learning: MaxEnt RL without Entropy","date":"2023-01-05","arxiv_id":"2301.02328","repositories_listed":4,"syntology":{"n":13,"n_ran":8,"n_constructed":5,"n_ran_checked":5,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"8 ran (of which 5 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) · 5 unverified","sample_list":"/paper/extreme-q-learning-maxent-rl-without-entropy#ran","syntology_url":"https://syntology.ai/paper/2301.02328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02328"}},"official":null}},{"url":"/paper/weighted-qmix-expanding-monotonic-value","slug":"weighted-qmix-expanding-monotonic-value","title":"Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","date":"2020-06-18","arxiv_id":"2006.10800","repositories_listed":4,"syntology":null},{"url":"/paper/discor-corrective-feedback-in-reinforcement","slug":"discor-corrective-feedback-in-reinforcement","title":"DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction","date":"2020-03-16","arxiv_id":"2003.07305","repositories_listed":4,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/discor-corrective-feedback-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2003.07305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07305"}},"official":null}},{"url":"/paper/learning-synergies-between-pushing-and","slug":"learning-synergies-between-pushing-and","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","date":"2018-03-27","arxiv_id":"1803.09956","repositories_listed":4,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-synergies-between-pushing-and#ran","syntology_url":"https://syntology.ai/paper/1803.09956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.09956"}},"official":{"repos":["andyzeng/visual-pushing-grasping"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/reinforcement-learning-with-deep-energy-based","slug":"reinforcement-learning-with-deep-energy-based","title":"Reinforcement Learning with Deep Energy-Based Policies","date":"2017-02-27","arxiv_id":"1702.08165","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/reinforcement-learning-with-deep-energy-based#ran","syntology_url":"https://syntology.ai/paper/1702.08165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.08165"}},"official":{"repos":["haarnoja/softqlearning"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/multiagent-cooperation-and-competition-with","slug":"multiagent-cooperation-and-competition-with","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","date":"2015-11-27","arxiv_id":"1511.08779","repositories_listed":4,"syntology":null},{"url":"/paper/cal-ql-calibrated-offline-rl-pre-training-for-1","slug":"cal-ql-calibrated-offline-rl-pre-training-for-1","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","date":"2023-03-09","arxiv_id":"2303.05479","repositories_listed":3,"syntology":null},{"url":"/paper/diffusion-policies-as-an-expressive-policy","slug":"diffusion-policies-as-an-expressive-policy","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","date":"2022-08-12","arxiv_id":"2208.06193","repositories_listed":3,"syntology":{"n":18,"n_ran":11,"n_constructed":5,"n_ran_checked":11,"n_instrument":0,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"11 ran (of which 5 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/diffusion-policies-as-an-expressive-policy#ran","syntology_url":"https://syntology.ai/paper/2208.06193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.06193"}},"official":{"repos":["zhendong-wang/diffusion-policies-for-offline-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mildly-conservative-q-learning-for-offline","slug":"mildly-conservative-q-learning-for-offline","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","date":"2022-06-09","arxiv_id":"2206.04745","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":6,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":10,"n_pointer_only":11,"phrase":"13 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mildly-conservative-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2206.04745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04745"}},"official":{"repos":["dmksjfl/mcq"],"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":["found_in_text","listed"]}}},{"url":"/paper/stabilizing-deep-q-learning-with-convnets-and","slug":"stabilizing-deep-q-learning-with-convnets-and","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","date":"2021-07-01","arxiv_id":"2107.00644","repositories_listed":3,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":12,"n_instrument":5,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stabilizing-deep-q-learning-with-convnets-and#ran","syntology_url":"https://syntology.ai/paper/2107.00644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00644"}},"official":{"repos":["nicklashansen/dmcontrol-generalization-benchmark"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deep-multi-agent-reinforcement-learning-for","slug":"deep-multi-agent-reinforcement-learning-for","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","date":"2020-03-14","arxiv_id":"2003.06709","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-multi-agent-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.06709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06709"}},"official":{"repos":["schroederdewitt/multiagent_mujoco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/approximating-two-value-functions-instead-of","slug":"approximating-two-value-functions-instead-of","title":"Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms","date":"2019-09-01","arxiv_id":"1909.01779","repositories_listed":3,"syntology":null},{"url":"/paper/boosting-soft-actor-critic-emphasizing-recent","slug":"boosting-soft-actor-critic-emphasizing-recent","title":"Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past","date":"2019-06-10","arxiv_id":"1906.04009","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/boosting-soft-actor-critic-emphasizing-recent#ran","syntology_url":"https://syntology.ai/paper/1906.04009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04009"}},"official":null}},{"url":"/paper/190600949","slug":"190600949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","date":"2019-06-03","arxiv_id":"1906.00949","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/190600949#ran","syntology_url":"https://syntology.ai/paper/1906.00949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00949"}},"official":null}},{"url":"/paper/reinforcement-learning-for-slate-based","slug":"reinforcement-learning-for-slate-based","title":"Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology","date":"2019-05-29","arxiv_id":"1905.12767","repositories_listed":3,"syntology":null},{"url":"/paper/improved-robustness-of-reinforcement-learning","slug":"improved-robustness-of-reinforcement-learning","title":"Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to ATARI games","date":"2019-03-26","arxiv_id":"1903.11012","repositories_listed":3,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-imbalanced","slug":"deep-reinforcement-learning-for-imbalanced","title":"Deep Reinforcement Learning for Imbalanced Classification","date":"2019-01-05","arxiv_id":"1901.01379","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-reinforcement-learning-for-imbalanced#ran","syntology_url":"https://syntology.ai/paper/1901.01379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.01379"}},"official":{"repos":["linenus/DRL-For-imbalanced-Classification"],"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/adversarial-learning-of-a-sampler-based-on-an","slug":"adversarial-learning-of-a-sampler-based-on-an","title":"Adversarial Learning of a Sampler Based on an Unnormalized Distribution","date":"2019-01-03","arxiv_id":"1901.00612","repositories_listed":3,"syntology":null},{"url":"/paper/deep-quality-value-dqv-learning","slug":"deep-quality-value-dqv-learning","title":"Deep Quality-Value (DQV) Learning","date":"2018-09-30","arxiv_id":"1810.00368","repositories_listed":3,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-traffic-light","slug":"deep-reinforcement-learning-for-traffic-light","title":"Deep Reinforcement Learning for Traffic Light Control in Vehicular Networks","date":"2018-03-29","arxiv_id":"1803.11115","repositories_listed":3,"syntology":null},{"url":"/paper/mean-field-multi-agent-reinforcement-learning","slug":"mean-field-multi-agent-reinforcement-learning","title":"Mean Field Multi-Agent Reinforcement Learning","date":"2018-02-15","arxiv_id":"1802.05438","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/mean-field-multi-agent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1802.05438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05438"}},"official":{"repos":["mlii/mfrl"],"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/learning-to-communicate-with-deep-multi-agent","slug":"learning-to-communicate-with-deep-multi-agent","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","date":"2016-05-21","arxiv_id":"1605.06676","repositories_listed":3,"syntology":null},{"url":"/paper/taming-the-noise-in-reinforcement-learning","slug":"taming-the-noise-in-reinforcement-learning","title":"Taming the Noise in Reinforcement Learning via Soft Updates","date":"2015-12-28","arxiv_id":"1512.08562","repositories_listed":3,"syntology":null},{"url":"/paper/deep-reinforcement-learning-with-a-natural","slug":"deep-reinforcement-learning-with-a-natural","title":"Deep Reinforcement Learning with a Natural Language Action Space","date":"2015-11-14","arxiv_id":"1511.04636","repositories_listed":3,"syntology":null},{"url":"/paper/flow-q-learning","slug":"flow-q-learning","title":"Flow Q-Learning","date":"2025-02-04","arxiv_id":"2502.02538","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flow-q-learning#ran","syntology_url":"https://syntology.ai/paper/2502.02538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02538"}},"official":{"repos":["seohongpark/fql"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rethinking-data-augmentation-for-robust-lidar","slug":"rethinking-data-augmentation-for-robust-lidar","title":"Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather","date":"2024-07-02","arxiv_id":"2407.02286","repositories_listed":2,"syntology":null},{"url":"/paper/towards-optimal-adversarial-robust-q-learning","slug":"towards-optimal-adversarial-robust-q-learning","title":"Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error","date":"2024-02-03","arxiv_id":"2402.02165","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-optimal-adversarial-robust-q-learning#ran","syntology_url":"https://syntology.ai/paper/2402.02165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02165"}},"official":{"repos":["leoranlmia/CAR-DQN"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-robust-offline-reinforcement-learning","slug":"towards-robust-offline-reinforcement-learning","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","date":"2023-10-19","arxiv_id":"2310.12955","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 2 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) · 4 unverified","sample_list":"/paper/towards-robust-offline-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2310.12955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12955"}},"official":{"repos":["yangrui2015/riql"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/dynamic-control-of-self-assembly-of","slug":"dynamic-control-of-self-assembly-of","title":"Dynamic control of self-assembly of quasicrystalline structures through reinforcement learning","date":"2023-09-13","arxiv_id":"2309.06869","repositories_listed":2,"syntology":null},{"url":"/paper/variations-on-the-reinforcement-learning","slug":"variations-on-the-reinforcement-learning","title":"Variations on the Reinforcement Learning performance of Blackjack","date":"2023-08-09","arxiv_id":"2308.07329","repositories_listed":2,"syntology":null},{"url":"/paper/location-routing-planning-for-last-mile","slug":"location-routing-planning-for-last-mile","title":"Route Planning for Last-Mile Deliveries Using Mobile Parcel Lockers: A Hybrid Q-Learning Network Approach","date":"2022-09-09","arxiv_id":"2209.04265","repositories_listed":2,"syntology":null},{"url":"/paper/a-deep-reinforcement-learning-approach-for-13","slug":"a-deep-reinforcement-learning-approach-for-13","title":"A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games","date":"2022-07-18","arxiv_id":"2207.08894","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-deep-reinforcement-learning-approach-for-13#ran","syntology_url":"https://syntology.ai/paper/2207.08894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08894"}},"official":{"repos":["quantumiracle/mars","quantumiracle/nash-dqn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-learning-and-learnablity-of","slug":"on-the-learning-and-learnablity-of","title":"On the Learning and Learnability of Quasimetrics","date":"2022-06-30","arxiv_id":"2206.15478","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/on-the-learning-and-learnablity-of#ran","syntology_url":"https://syntology.ai/paper/2206.15478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.15478"}},"official":{"repos":["ssnl/poisson_quasimetric_embedding"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-rl-for-natural-language-generation","slug":"offline-rl-for-natural-language-generation","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","date":"2022-06-05","arxiv_id":"2206.11871","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/offline-rl-for-natural-language-generation#ran","syntology_url":"https://syntology.ai/paper/2206.11871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11871"}},"official":null}},{"url":"/paper/shinrl-a-library-for-evaluating-rl-algorithms","slug":"shinrl-a-library-for-evaluating-rl-algorithms","title":"ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives","date":"2021-12-08","arxiv_id":"2112.04123","repositories_listed":2,"syntology":null},{"url":"/paper/dropout-q-functions-for-doubly-efficient","slug":"dropout-q-functions-for-doubly-efficient","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","date":"2021-10-05","arxiv_id":"2110.02034","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dropout-q-functions-for-doubly-efficient#ran","syntology_url":"https://syntology.ai/paper/2110.02034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02034"}},"official":{"repos":["TakuyaHiraoka/Dropout-Q-Functions-for-Doubly-Efficient-Reinforcement-Learning"],"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":["found_in_text","official"]}}},{"url":"/paper/temporl-learning-when-to-act","slug":"temporl-learning-when-to-act","title":"TempoRL: Learning When to Act","date":"2021-06-09","arxiv_id":"2106.05262","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/temporl-learning-when-to-act#ran","syntology_url":"https://syntology.ai/paper/2106.05262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05262"}},"official":{"repos":["automl/TempoRL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-weighted-actor-critic-for-offline","slug":"uncertainty-weighted-actor-critic-for-offline","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","date":"2021-05-17","arxiv_id":"2105.08140","repositories_listed":2,"syntology":null},{"url":"/paper/revisiting-prioritized-experience-replay-a-1","slug":"revisiting-prioritized-experience-replay-a-1","title":"Revisiting Prioritized Experience Replay: A Value Perspective","date":"2021-02-05","arxiv_id":"2102.03261","repositories_listed":2,"syntology":null},{"url":"/paper/acting-in-delayed-environments-with-non-1","slug":"acting-in-delayed-environments-with-non-1","title":"Acting in Delayed Environments with Non-Stationary Markov Policies","date":"2021-01-28","arxiv_id":"2101.11992","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/acting-in-delayed-environments-with-non-1#ran","syntology_url":"https://syntology.ai/paper/2101.11992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11992"}},"official":{"repos":["galdl/rl_delay_atari","galdl/rl_delay_basic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-the-lunar-lander-problem-under","slug":"solving-the-lunar-lander-problem-under","title":"Solving The Lunar Lander Problem under Uncertainty using Reinforcement Learning","date":"2020-11-24","arxiv_id":"2011.11850","repositories_listed":2,"syntology":null},{"url":"/paper/learning-guidance-rewards-with-trajectory","slug":"learning-guidance-rewards-with-trajectory","title":"Learning Guidance Rewards with Trajectory-space Smoothing","date":"2020-10-23","arxiv_id":"2010.12718","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-guidance-rewards-with-trajectory#ran","syntology_url":"https://syntology.ai/paper/2010.12718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12718"}},"official":{"repos":["tgangwani/GuidanceRewards"],"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-collaboration-via-reward-1","slug":"multi-agent-collaboration-via-reward-1","title":"Multi-Agent Collaboration via Reward Attribution Decomposition","date":"2020-10-16","arxiv_id":"2010.08531","repositories_listed":2,"syntology":null},{"url":"/paper/epidemioptim-a-toolbox-for-the-optimization-1","slug":"epidemioptim-a-toolbox-for-the-optimization-1","title":"EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models","date":"2020-10-09","arxiv_id":"2010.04452","repositories_listed":2,"syntology":null},{"url":"/paper/robust-deep-reinforcement-learning-through","slug":"robust-deep-reinforcement-learning-through","title":"Robust Deep Reinforcement Learning through Adversarial Loss","date":"2020-08-05","arxiv_id":"2008.01976","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-through#ran","syntology_url":"https://syntology.ai/paper/2008.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01976"}},"official":{"repos":["tuomaso/radial_rl","tuomaso/radial_rl_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-inverse-q-learning-with-constraints","slug":"deep-inverse-q-learning-with-constraints","title":"Deep Inverse Q-learning with Constraints","date":"2020-08-04","arxiv_id":"2008.01712","repositories_listed":2,"syntology":null},{"url":"/paper/revisiting-fundamentals-of-experience-replay","slug":"revisiting-fundamentals-of-experience-replay","title":"Revisiting Fundamentals of Experience Replay","date":"2020-07-13","arxiv_id":"2007.06700","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/revisiting-fundamentals-of-experience-replay#ran","syntology_url":"https://syntology.ai/paper/2007.06700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06700"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/reward-machines-for-cooperative-multi-agent","slug":"reward-machines-for-cooperative-multi-agent","title":"Reward Machines for Cooperative Multi-Agent Reinforcement Learning","date":"2020-07-03","arxiv_id":"2007.01962","repositories_listed":2,"syntology":null},{"url":"/paper/flapai-bird-training-an-agent-to-play-flappy","slug":"flapai-bird-training-an-agent-to-play-flappy","title":"FlapAI Bird: Training an Agent to Play Flappy Bird Using Reinforcement Learning Techniques","date":"2020-03-21","arxiv_id":"2003.09579","repositories_listed":2,"syntology":null},{"url":"/paper/learning-state-abstractions-for-transfer-in","slug":"learning-state-abstractions-for-transfer-in","title":"Learning State Abstractions for Transfer in Continuous Control","date":"2020-02-08","arxiv_id":"2002.05518","repositories_listed":2,"syntology":null},{"url":"/paper/zpd-teaching-strategies-for-deep","slug":"zpd-teaching-strategies-for-deep","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","date":"2019-10-26","arxiv_id":"1910.12154","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zpd-teaching-strategies-for-deep#ran","syntology_url":"https://syntology.ai/paper/1910.12154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12154"}},"official":null}},{"url":"/paper/policy-learning-for-malaria-control","slug":"policy-learning-for-malaria-control","title":"Policy Learning for Malaria Control","date":"2019-10-20","arxiv_id":"1910.08926","repositories_listed":2,"syntology":null},{"url":"/paper/seed-rl-scalable-and-efficient-deep-rl-with-1","slug":"seed-rl-scalable-and-efficient-deep-rl-with-1","title":"SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference","date":"2019-10-15","arxiv_id":"1910.06591","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seed-rl-scalable-and-efficient-deep-rl-with-1#ran","syntology_url":"https://syntology.ai/paper/1910.06591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06591"}},"official":{"repos":["google-research/seed_rl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-q-learning","slug":"meta-q-learning","title":"Meta-Q-Learning","date":"2019-09-30","arxiv_id":"1910.00125","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-q-learning#ran","syntology_url":"https://syntology.ai/paper/1910.00125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00125"}},"official":{"repos":["amazon-research/meta-q-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/deep-coordination-graphs","slug":"deep-coordination-graphs","title":"Deep Coordination Graphs","date":"2019-09-27","arxiv_id":"1910.00091","repositories_listed":2,"syntology":null},{"url":"/paper/improving-sat-solver-heuristics-with-graph","slug":"improving-sat-solver-heuristics-with-graph","title":"Can $Q$-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?","date":"2019-09-26","arxiv_id":"1909.11830","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-control-of","slug":"deep-reinforcement-learning-for-control-of","title":"Deep Reinforcement Learning for Control of Probabilistic Boolean Networks","date":"2019-09-07","arxiv_id":"1909.03331","repositories_listed":2,"syntology":null},{"url":"/paper/performing-deep-recurrent-double-q-learning","slug":"performing-deep-recurrent-double-q-learning","title":"Performing Deep Recurrent Double Q-Learning for Atari Games","date":"2019-08-16","arxiv_id":"1908.06040","repositories_listed":2,"syntology":null},{"url":"/paper/playing-adaptively-against-stealthy-opponents","slug":"playing-adaptively-against-stealthy-opponents","title":"QFlip: An Adaptive Reinforcement Learning Strategy for the FlipIt Security Game","date":"2019-06-27","arxiv_id":"1906.11938","repositories_listed":2,"syntology":null},{"url":"/paper/solving-np-hard-problems-on-graphs-by","slug":"solving-np-hard-problems-on-graphs-by","title":"Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero","date":"2019-05-28","arxiv_id":"1905.11623","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/solving-np-hard-problems-on-graphs-by#ran","syntology_url":"https://syntology.ai/paper/1905.11623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11623"}},"official":null}},{"url":"/paper/comprehensible-context-driven-text-game","slug":"comprehensible-context-driven-text-game","title":"Comprehensible Context-driven Text Game Playing","date":"2019-05-06","arxiv_id":"1905.02265","repositories_listed":2,"syntology":null},{"url":"/paper/deep-recurrent-q-learning-vs-deep-q-learning","slug":"deep-recurrent-q-learning-vs-deep-q-learning","title":"Deep Recurrent Q-Learning vs Deep Q-Learning on a simple Partially Observable Markov Decision Process with Minecraft","date":"2019-03-11","arxiv_id":"1903.04311","repositories_listed":2,"syntology":null},{"url":"/paper/learning-heuristics-over-large-graphs-via","slug":"learning-heuristics-over-large-graphs-via","title":"Learning Heuristics over Large Graphs via Deep Reinforcement Learning","date":"2019-03-08","arxiv_id":"1903.03332","repositories_listed":2,"syntology":null},{"url":"/paper/revisiting-the-softmax-bellman-operator","slug":"revisiting-the-softmax-bellman-operator","title":"Revisiting the Softmax Bellman Operator: New Benefits and New Perspective","date":"2018-12-02","arxiv_id":"1812.00456","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/revisiting-the-softmax-bellman-operator#ran","syntology_url":"https://syntology.ai/paper/1812.00456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00456"}},"official":{"repos":["zhao-song/Softmax-DQN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/reinforcement-learning-with-a-and-a-deep","slug":"reinforcement-learning-with-a-and-a-deep","title":"Reinforcement Learning with A* and a Deep Heuristic","date":"2018-11-19","arxiv_id":"1811.07745","repositories_listed":2,"syntology":null},{"url":"/paper/q-map-a-convolutional-approach-for-goal","slug":"q-map-a-convolutional-approach-for-goal","title":"Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks","date":"2018-10-06","arxiv_id":"1810.02927","repositories_listed":2,"syntology":null},{"url":"/paper/sampled-policy-gradient-for-learning-to-play","slug":"sampled-policy-gradient-for-learning-to-play","title":"Sampled Policy Gradient for Learning to Play the Game Agar.io","date":"2018-09-15","arxiv_id":"1809.05763","repositories_listed":2,"syntology":null},{"url":"/paper/blockqnn-efficient-block-wise-neural-network","slug":"blockqnn-efficient-block-wise-neural-network","title":"BlockQNN: Efficient Block-wise Neural Network Architecture Generation","date":"2018-08-16","arxiv_id":"1808.05584","repositories_listed":2,"syntology":null},{"url":"/paper/a-framework-for-automated-cellular-network","slug":"a-framework-for-automated-cellular-network","title":"A Framework for Automated Cellular Network Tuning with Reinforcement Learning","date":"2018-08-13","arxiv_id":"1808.05140","repositories_listed":2,"syntology":null},{"url":"/paper/remember-and-forget-for-experience-replay","slug":"remember-and-forget-for-experience-replay","title":"Remember and Forget for Experience Replay","date":"2018-07-16","arxiv_id":"1807.05827","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/remember-and-forget-for-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1807.05827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.05827"}},"official":{"repos":["cselab/smarties"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-reinforcement-learning-for-time-series","slug":"deep-reinforcement-learning-for-time-series","title":"Deep reinforcement learning for time series: playing idealized trading games","date":"2018-03-11","arxiv_id":"1803.03916","repositories_listed":2,"syntology":null}],"syntology_records":50,"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":119,"papers_where_code_ran_first_page":"/task/q-learning/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":20,"url":"/task/q-learning/papers/2","json":"/task/q-learning/papers/2.json","rows":100},{"order":"archive","page":3,"of":20,"url":"/task/q-learning/papers/3","json":"/task/q-learning/papers/3.json","rows":100},{"order":"archive","page":4,"of":20,"url":"/task/q-learning/papers/4","json":"/task/q-learning/papers/4.json","rows":100},{"order":"archive","page":5,"of":20,"url":"/task/q-learning/papers/5","json":"/task/q-learning/papers/5.json","rows":100},{"order":"archive","page":6,"of":20,"url":"/task/q-learning/papers/6","json":"/task/q-learning/papers/6.json","rows":100},{"order":"archive","page":7,"of":20,"url":"/task/q-learning/papers/7","json":"/task/q-learning/papers/7.json","rows":100},{"order":"archive","page":8,"of":20,"url":"/task/q-learning/papers/8","json":"/task/q-learning/papers/8.json","rows":100},{"order":"archive","page":9,"of":20,"url":"/task/q-learning/papers/9","json":"/task/q-learning/papers/9.json","rows":100},{"order":"archive","page":10,"of":20,"url":"/task/q-learning/papers/10","json":"/task/q-learning/papers/10.json","rows":100},{"order":"archive","page":11,"of":20,"url":"/task/q-learning/papers/11","json":"/task/q-learning/papers/11.json","rows":100},{"order":"archive","page":12,"of":20,"url":"/task/q-learning/papers/12","json":"/task/q-learning/papers/12.json","rows":100},{"order":"archive","page":13,"of":20,"url":"/task/q-learning/papers/13","json":"/task/q-learning/papers/13.json","rows":100},{"order":"archive","page":14,"of":20,"url":"/task/q-learning/papers/14","json":"/task/q-learning/papers/14.json","rows":100},{"order":"archive","page":15,"of":20,"url":"/task/q-learning/papers/15","json":"/task/q-learning/papers/15.json","rows":100},{"order":"archive","page":16,"of":20,"url":"/task/q-learning/papers/16","json":"/task/q-learning/papers/16.json","rows":100},{"order":"archive","page":17,"of":20,"url":"/task/q-learning/papers/17","json":"/task/q-learning/papers/17.json","rows":100},{"order":"archive","page":18,"of":20,"url":"/task/q-learning/papers/18","json":"/task/q-learning/papers/18.json","rows":100},{"order":"archive","page":19,"of":20,"url":"/task/q-learning/papers/19","json":"/task/q-learning/papers/19.json","rows":100},{"order":"archive","page":20,"of":20,"url":"/task/q-learning/papers/20","json":"/task/q-learning/papers/20.json","rows":18},{"order":"ran","page":1,"of":2,"url":"/task/q-learning/papers/ran/1","json":"/task/q-learning/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/q-learning/papers/ran/2","json":"/task/q-learning/papers/ran/2.json","rows":19}],"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":"c9ff5cefe9f8853adb633bed459e2df073019c84e790af4c4a6dc074485a5dd8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}