{"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/deep-reinforcement-learning","name":"Deep Reinforcement Learning","slug":"deep-reinforcement-learning","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":5822,"papers_with_code":1739,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/reinforcement-learning","name":"Reinforcement Learning"}],"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":59,"rows_per_page":100,"shown":100,"of":5822,"of_with_code":1739,"tagged_in_all":5822,"counts":{"archive_papers_tagged":5822,"with_a_code_link":1739,"where_syntology_ran_a_sample":398,"not_listed_spam_title":0,"listed":5822,"listed_where_code_ran":398,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":338,"every_run_a_failure_of_syntologys_instrument":60,"listed_with_a_run_with_no_instrument_failure":338,"listed_every_run_a_failure_of_syntologys_instrument":60,"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/dueling-network-architectures-for-deep","slug":"dueling-network-architectures-for-deep","title":"Dueling Network Architectures for Deep Reinforcement Learning","date":"2015-11-20","arxiv_id":"1511.06581","repositories_listed":73,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/dueling-network-architectures-for-deep#ran","syntology_url":"https://syntology.ai/paper/1511.06581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06581"}},"official":null}},{"url":"/paper/asynchronous-methods-for-deep-reinforcement","slug":"asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","arxiv_id":"1602.01783","repositories_listed":70,"syntology":{"n":95,"n_ran":60,"n_constructed":20,"n_ran_checked":50,"n_instrument":10,"n_unverified":35,"n_honours":2,"n_violates":1,"n_no_contract":47,"n_pointer_only":20,"phrase":"60 ran (of which 20 constructed an object rather than computing a result; 50 with no instrument failure: 2 honoured, 1 violated, 47 with no contract checked; 10 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/asynchronous-methods-for-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1602.01783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.01783"}},"official":null}},{"url":"/paper/rainbow-combining-improvements-in-deep","slug":"rainbow-combining-improvements-in-deep","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","date":"2017-10-06","arxiv_id":"1710.02298","repositories_listed":34,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rainbow-combining-improvements-in-deep#ran","syntology_url":"https://syntology.ai/paper/1710.02298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.02298"}},"official":null}},{"url":"/paper/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/dropout-as-a-bayesian-approximation","slug":"dropout-as-a-bayesian-approximation","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","date":"2015-06-06","arxiv_id":"1506.02142","repositories_listed":29,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"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: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dropout-as-a-bayesian-approximation#ran","syntology_url":"https://syntology.ai/paper/1506.02142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.02142"}},"official":null}},{"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/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/gradient-surgery-for-multi-task-learning-1","slug":"gradient-surgery-for-multi-task-learning-1","title":"Gradient Surgery for Multi-Task Learning","date":"2020-01-19","arxiv_id":"2001.06782","repositories_listed":18,"syntology":{"n":10,"n_ran":7,"n_constructed":5,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"7 ran (of which 5 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/gradient-surgery-for-multi-task-learning-1#ran","syntology_url":"https://syntology.ai/paper/2001.06782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06782"}},"official":{"repos":["tianheyu927/PCGrad"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/flow-architecture-and-benchmarking-for","slug":"flow-architecture-and-benchmarking-for","title":"Flow: A Modular Learning Framework for Mixed Autonomy Traffic","date":"2017-10-16","arxiv_id":"1710.05465","repositories_listed":16,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flow-architecture-and-benchmarking-for#ran","syntology_url":"https://syntology.ai/paper/1710.05465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.05465"}},"official":{"repos":["cathywu/flow","flow-project/flow"],"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/distributed-prioritized-experience-replay","slug":"distributed-prioritized-experience-replay","title":"Distributed Prioritized Experience Replay","date":"2018-03-02","arxiv_id":"1803.00933","repositories_listed":15,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/distributed-prioritized-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1803.00933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.00933"}},"official":null}},{"url":"/paper/noisy-networks-for-exploration","slug":"noisy-networks-for-exploration","title":"Noisy Networks for Exploration","date":"2017-06-30","arxiv_id":"1706.10295","repositories_listed":15,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/noisy-networks-for-exploration#ran","syntology_url":"https://syntology.ai/paper/1706.10295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.10295"}},"official":null}},{"url":"/paper/benchmarking-deep-reinforcement-learning-for","slug":"benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","arxiv_id":"1604.06778","repositories_listed":15,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/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/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/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/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/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/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/population-based-training-of-neural-networks","slug":"population-based-training-of-neural-networks","title":"Population Based Training of Neural Networks","date":"2017-11-27","arxiv_id":"1711.09846","repositories_listed":9,"syntology":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/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/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/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/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/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/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/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/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/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/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},{"url":"/paper/deep-reinforcement-learning-in-parameterized","slug":"deep-reinforcement-learning-in-parameterized","title":"Deep Reinforcement Learning in Parameterized Action Space","date":"2015-11-13","arxiv_id":"1511.04143","repositories_listed":7,"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":0,"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/deep-reinforcement-learning-in-parameterized#ran","syntology_url":"https://syntology.ai/paper/1511.04143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.04143"}},"official":{"repos":["mhauskn/dqn-hfo"],"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/habitat-2-0-training-home-assistants-to","slug":"habitat-2-0-training-home-assistants-to","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","date":"2021-06-28","arxiv_id":"2106.14405","repositories_listed":6,"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":2,"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/habitat-2-0-training-home-assistants-to#ran","syntology_url":"https://syntology.ai/paper/2106.14405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14405"}},"official":{"repos":["facebookresearch/habitat-lab"],"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/finrl-a-deep-reinforcement-learning-library","slug":"finrl-a-deep-reinforcement-learning-library","title":"FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance","date":"2020-11-19","arxiv_id":"2011.09607","repositories_listed":6,"syntology":null},{"url":"/paper/stroke-based-artistic-rendering-agent-with","slug":"stroke-based-artistic-rendering-agent-with","title":"Learning to Paint With Model-based Deep Reinforcement Learning","date":"2019-03-11","arxiv_id":"1903.04411","repositories_listed":6,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/stroke-based-artistic-rendering-agent-with#ran","syntology_url":"https://syntology.ai/paper/1903.04411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04411"}},"official":{"repos":["hzwer/ICCV2019-LearningToPaint"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/evolution-guided-policy-gradient-in","slug":"evolution-guided-policy-gradient-in","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","date":"2018-05-21","arxiv_id":"1805.07917","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/evolution-guided-policy-gradient-in#ran","syntology_url":"https://syntology.ai/paper/1805.07917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07917"}},"official":{"repos":["ShawK91/erl_paper_nips18"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/motion-planning-among-dynamic-decision-making","slug":"motion-planning-among-dynamic-decision-making","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","date":"2018-05-04","arxiv_id":"1805.01956","repositories_listed":6,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/motion-planning-among-dynamic-decision-making#ran","syntology_url":"https://syntology.ai/paper/1805.01956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.01956"}},"official":{"repos":["mfe7/cadrl_ros"],"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/deepmimic-example-guided-deep-reinforcement","slug":"deepmimic-example-guided-deep-reinforcement","title":"DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills","date":"2018-04-08","arxiv_id":"1804.02717","repositories_listed":6,"syntology":null},{"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-reinforcement-learning-for-unsupervised","slug":"deep-reinforcement-learning-for-unsupervised","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","date":"2017-12-29","arxiv_id":"1801.00054","repositories_listed":6,"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/deep-reinforcement-learning-for-unsupervised#ran","syntology_url":"https://syntology.ai/paper/1801.00054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.00054"}},"official":{"repos":["KaiyangZhou/vsumm-reinforce"],"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-high-dimensional-partial-differential","slug":"solving-high-dimensional-partial-differential","title":"Solving high-dimensional partial differential equations using deep learning","date":"2017-07-09","arxiv_id":"1707.02568","repositories_listed":6,"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/solving-high-dimensional-partial-differential#ran","syntology_url":"https://syntology.ai/paper/1707.02568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.02568"}},"official":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/learning-to-walk-in-minutes-using-massively","slug":"learning-to-walk-in-minutes-using-massively","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","date":"2021-09-24","arxiv_id":"2109.11978","repositories_listed":5,"syntology":null},{"url":"/paper/gym-m-rts-toward-affordable-full-game-real","slug":"gym-m-rts-toward-affordable-full-game-real","title":"Gym-$μ$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning","date":"2021-05-21","arxiv_id":"2105.13807","repositories_listed":5,"syntology":null},{"url":"/paper/acme-a-research-framework-for-distributed","slug":"acme-a-research-framework-for-distributed","title":"Acme: A Research Framework for Distributed Reinforcement Learning","date":"2020-06-01","arxiv_id":"2006.00979","repositories_listed":5,"syntology":null},{"url":"/paper/a-simple-randomization-technique-for-1","slug":"a-simple-randomization-technique-for-1","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","date":"2019-10-11","arxiv_id":"1910.05396","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-simple-randomization-technique-for-1#ran","syntology_url":"https://syntology.ai/paper/1910.05396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05396"}},"official":{"repos":["pokaxpoka/netrand"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/multi-agent-deep-reinforcement-learning-for-3","slug":"multi-agent-deep-reinforcement-learning-for-3","title":"Multi-Agent Deep Reinforcement Learning for Liquidation Strategy Analysis","date":"2019-06-24","arxiv_id":"1906.11046","repositories_listed":5,"syntology":null},{"url":"/paper/crossnorm-normalization-for-off-policy-td","slug":"crossnorm-normalization-for-off-policy-td","title":"CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity","date":"2019-02-14","arxiv_id":"1902.05605","repositories_listed":5,"syntology":null},{"url":"/paper/learning-to-design-rna","slug":"learning-to-design-rna","title":"Learning to Design RNA","date":"2018-12-31","arxiv_id":"1812.11951","repositories_listed":5,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-design-rna#ran","syntology_url":"https://syntology.ai/paper/1812.11951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.11951"}},"official":{"repos":["automl/learna"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/an-introduction-to-deep-reinforcement","slug":"an-introduction-to-deep-reinforcement","title":"An Introduction to Deep Reinforcement Learning","date":"2018-11-30","arxiv_id":"1811.12560","repositories_listed":5,"syntology":null},{"url":"/paper/deep-reinforcement-learning-based","slug":"deep-reinforcement-learning-based","title":"Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling","date":"2018-10-29","arxiv_id":"1810.12027","repositories_listed":5,"syntology":null},{"url":"/paper/deep-reinforcement-learning","slug":"deep-reinforcement-learning","title":"Deep Reinforcement Learning","date":"2018-10-15","arxiv_id":"1810.06339","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":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1810.06339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.06339"}},"official":{"repos":["deepmind/lab","google/dopamine","mrkulk/hierarchical-deep-RL","rllab/rllab"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/parametrized-deep-q-networks-learning","slug":"parametrized-deep-q-networks-learning","title":"Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space","date":"2018-10-10","arxiv_id":"1810.06394","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/parametrized-deep-q-networks-learning#ran","syntology_url":"https://syntology.ai/paper/1810.06394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.06394"}},"official":null}},{"url":"/paper/adversarial-deep-reinforcement-learning-in","slug":"adversarial-deep-reinforcement-learning-in","title":"Adversarial Deep Reinforcement Learning in Portfolio Management","date":"2018-08-29","arxiv_id":"1808.09940","repositories_listed":5,"syntology":null},{"url":"/paper/action-branching-architectures-for-deep","slug":"action-branching-architectures-for-deep","title":"Action Branching Architectures for Deep Reinforcement Learning","date":"2017-11-24","arxiv_id":"1711.08946","repositories_listed":5,"syntology":null},{"url":"/paper/deep-learning-based-numerical-methods-for","slug":"deep-learning-based-numerical-methods-for","title":"Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations","date":"2017-06-15","arxiv_id":"1706.04702","repositories_listed":5,"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/deep-learning-based-numerical-methods-for#ran","syntology_url":"https://syntology.ai/paper/1706.04702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.04702"}},"official":null}},{"url":"/paper/efficient-parallel-methods-for-deep","slug":"efficient-parallel-methods-for-deep","title":"Efficient Parallel Methods for Deep Reinforcement Learning","date":"2017-05-13","arxiv_id":"1705.04862","repositories_listed":5,"syntology":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/simba-simplicity-bias-for-scaling-up","slug":"simba-simplicity-bias-for-scaling-up","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","date":"2024-10-13","arxiv_id":"2410.09754","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":2,"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 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simba-simplicity-bias-for-scaling-up#ran","syntology_url":"https://syntology.ai/paper/2410.09754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09754"}},"official":{"repos":["sonyresearch/simba"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dynamic-datasets-and-market-environments-for","slug":"dynamic-datasets-and-market-environments-for","title":"Dynamic Datasets and Market Environments for Financial Reinforcement Learning","date":"2023-04-25","arxiv_id":"2304.13174","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamic-datasets-and-market-environments-for#ran","syntology_url":"https://syntology.ai/paper/2304.13174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13174"}},"official":{"repos":["AI4Finance-Foundation/FinRL","ai4finance-foundation/finrl-meta"],"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/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/finrl-meta-market-environments-and-benchmarks","slug":"finrl-meta-market-environments-and-benchmarks","title":"FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning","date":"2022-11-06","arxiv_id":"2211.03107","repositories_listed":4,"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/finrl-meta-market-environments-and-benchmarks#ran","syntology_url":"https://syntology.ai/paper/2211.03107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03107"}},"official":{"repos":["AI4Finance-Foundation/FinRL","ai4finance-foundation/finrl-meta"],"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/replay-guided-adversarial-environment-design","slug":"replay-guided-adversarial-environment-design","title":"Replay-Guided Adversarial Environment Design","date":"2021-10-06","arxiv_id":"2110.02439","repositories_listed":4,"syntology":{"n":4,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/replay-guided-adversarial-environment-design#ran","syntology_url":"https://syntology.ai/paper/2110.02439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02439"}},"official":null}},{"url":"/paper/a-gentle-introduction-to-conformal-prediction","slug":"a-gentle-introduction-to-conformal-prediction","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","date":"2021-07-15","arxiv_id":"2107.07511","repositories_listed":4,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/a-gentle-introduction-to-conformal-prediction#ran","syntology_url":"https://syntology.ai/paper/2107.07511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07511"}},"official":{"repos":["aangelopoulos/conformal-prediction"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/objective-robustness-in-deep-reinforcement","slug":"objective-robustness-in-deep-reinforcement","title":"Goal Misgeneralization in Deep Reinforcement Learning","date":"2021-05-28","arxiv_id":"2105.14111","repositories_listed":4,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/objective-robustness-in-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2105.14111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14111"}},"official":{"repos":["JacobPfau/procgenAISC","jbkjr/train-procgen-pytorch"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-reinforcement-learning-environment-for-job","slug":"a-reinforcement-learning-environment-for-job","title":"A Reinforcement Learning Environment For Job-Shop Scheduling","date":"2021-04-08","arxiv_id":"2104.03760","repositories_listed":4,"syntology":null},{"url":"/paper/recurrent-rational-networks","slug":"recurrent-rational-networks","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09407","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recurrent-rational-networks#ran","syntology_url":"https://syntology.ai/paper/2102.09407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.09407"}},"official":{"repos":["ml-research/rational_activations","ml-research/rational_rl","ml-research/rational_sl","k4ntz/activation-functions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-dispatch-for-job-shop-scheduling","slug":"learning-to-dispatch-for-job-shop-scheduling","title":"Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning","date":"2020-10-23","arxiv_id":"2010.12367","repositories_listed":4,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-to-dispatch-for-job-shop-scheduling#ran","syntology_url":"https://syntology.ai/paper/2010.12367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12367"}},"official":{"repos":["zcajiayin/L2D"],"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/prioritized-level-replay-1","slug":"prioritized-level-replay-1","title":"Prioritized Level Replay","date":"2020-10-08","arxiv_id":"2010.03934","repositories_listed":4,"syntology":null},{"url":"/paper/image-augmentation-is-all-you-need","slug":"image-augmentation-is-all-you-need","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","date":"2020-04-28","arxiv_id":"2004.13649","repositories_listed":4,"syntology":{"n":10,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/image-augmentation-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2004.13649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13649"}},"official":{"repos":["denisyarats/drq"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/robust-deep-reinforcement-learning-against","slug":"robust-deep-reinforcement-learning-against","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","date":"2020-03-19","arxiv_id":"2003.08938","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/interpretable-end-to-end-urban-autonomous","slug":"interpretable-end-to-end-urban-autonomous","title":"Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning","date":"2020-01-23","arxiv_id":"2001.08726","repositories_listed":4,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/interpretable-end-to-end-urban-autonomous#ran","syntology_url":"https://syntology.ai/paper/2001.08726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.08726"}},"official":{"repos":["cjy1992/interp-e2e-driving"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/comparing-observation-and-action","slug":"comparing-observation-and-action","title":"Comparing Observation and Action Representations for Deep Reinforcement Learning in $μ$RTS","date":"2019-10-26","arxiv_id":"1910.12134","repositories_listed":4,"syntology":null},{"url":"/paper/multi-pass-q-networks-for-deep-reinforcement","slug":"multi-pass-q-networks-for-deep-reinforcement","title":"Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces","date":"2019-05-10","arxiv_id":"1905.04388","repositories_listed":4,"syntology":null},{"url":"/paper/deep-neuroevolution-of-recurrent-and-discrete","slug":"deep-neuroevolution-of-recurrent-and-discrete","title":"Deep Neuroevolution of Recurrent and Discrete World Models","date":"2019-04-28","arxiv_id":"1906.08857","repositories_listed":4,"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/deep-neuroevolution-of-recurrent-and-discrete#ran","syntology_url":"https://syntology.ai/paper/1906.08857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08857"}},"official":{"repos":["sebastianrisi/ga-world-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/lift-reinforcement-learning-in-computer","slug":"lift-reinforcement-learning-in-computer","title":"LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations","date":"2018-08-23","arxiv_id":"1808.07903","repositories_listed":4,"syntology":null},{"url":"/paper/bohb-robust-and-efficient-hyperparameter","slug":"bohb-robust-and-efficient-hyperparameter","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","date":"2018-07-04","arxiv_id":"1807.01774","repositories_listed":4,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-playing-25d","slug":"deep-reinforcement-learning-for-playing-25d","title":"Deep Reinforcement Learning for Playing 2.5D Fighting Games","date":"2018-05-05","arxiv_id":"1805.02070","repositories_listed":4,"syntology":null},{"url":"/paper/learning-to-navigate-in-cities-without-a-map","slug":"learning-to-navigate-in-cities-without-a-map","title":"Learning to Navigate in Cities Without a Map","date":"2018-03-31","arxiv_id":"1804.00168","repositories_listed":4,"syntology":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"]}}}],"syntology_records":67,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":398,"papers_where_code_ran_first_page":"/task/deep-reinforcement-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":59,"url":"/task/deep-reinforcement-learning/papers/2","json":"/task/deep-reinforcement-learning/papers/2.json","rows":100},{"order":"archive","page":3,"of":59,"url":"/task/deep-reinforcement-learning/papers/3","json":"/task/deep-reinforcement-learning/papers/3.json","rows":100},{"order":"archive","page":4,"of":59,"url":"/task/deep-reinforcement-learning/papers/4","json":"/task/deep-reinforcement-learning/papers/4.json","rows":100},{"order":"archive","page":5,"of":59,"url":"/task/deep-reinforcement-learning/papers/5","json":"/task/deep-reinforcement-learning/papers/5.json","rows":100},{"order":"archive","page":6,"of":59,"url":"/task/deep-reinforcement-learning/papers/6","json":"/task/deep-reinforcement-learning/papers/6.json","rows":100},{"order":"archive","page":7,"of":59,"url":"/task/deep-reinforcement-learning/papers/7","json":"/task/deep-reinforcement-learning/papers/7.json","rows":100},{"order":"archive","page":8,"of":59,"url":"/task/deep-reinforcement-learning/papers/8","json":"/task/deep-reinforcement-learning/papers/8.json","rows":100},{"order":"archive","page":9,"of":59,"url":"/task/deep-reinforcement-learning/papers/9","json":"/task/deep-reinforcement-learning/papers/9.json","rows":100},{"order":"archive","page":10,"of":59,"url":"/task/deep-reinforcement-learning/papers/10","json":"/task/deep-reinforcement-learning/papers/10.json","rows":100},{"order":"archive","page":11,"of":59,"url":"/task/deep-reinforcement-learning/papers/11","json":"/task/deep-reinforcement-learning/papers/11.json","rows":100},{"order":"archive","page":12,"of":59,"url":"/task/deep-reinforcement-learning/papers/12","json":"/task/deep-reinforcement-learning/papers/12.json","rows":100},{"order":"archive","page":13,"of":59,"url":"/task/deep-reinforcement-learning/papers/13","json":"/task/deep-reinforcement-learning/papers/13.json","rows":100},{"order":"archive","page":14,"of":59,"url":"/task/deep-reinforcement-learning/papers/14","json":"/task/deep-reinforcement-learning/papers/14.json","rows":100},{"order":"archive","page":15,"of":59,"url":"/task/deep-reinforcement-learning/papers/15","json":"/task/deep-reinforcement-learning/papers/15.json","rows":100},{"order":"archive","page":16,"of":59,"url":"/task/deep-reinforcement-learning/papers/16","json":"/task/deep-reinforcement-learning/papers/16.json","rows":100},{"order":"archive","page":17,"of":59,"url":"/task/deep-reinforcement-learning/papers/17","json":"/task/deep-reinforcement-learning/papers/17.json","rows":100},{"order":"archive","page":18,"of":59,"url":"/task/deep-reinforcement-learning/papers/18","json":"/task/deep-reinforcement-learning/papers/18.json","rows":100},{"order":"archive","page":19,"of":59,"url":"/task/deep-reinforcement-learning/papers/19","json":"/task/deep-reinforcement-learning/papers/19.json","rows":100},{"order":"archive","page":20,"of":59,"url":"/task/deep-reinforcement-learning/papers/20","json":"/task/deep-reinforcement-learning/papers/20.json","rows":100},{"order":"archive","page":21,"of":59,"url":"/task/deep-reinforcement-learning/papers/21","json":"/task/deep-reinforcement-learning/papers/21.json","rows":100},{"order":"archive","page":22,"of":59,"url":"/task/deep-reinforcement-learning/papers/22","json":"/task/deep-reinforcement-learning/papers/22.json","rows":100},{"order":"archive","page":23,"of":59,"url":"/task/deep-reinforcement-learning/papers/23","json":"/task/deep-reinforcement-learning/papers/23.json","rows":100},{"order":"archive","page":24,"of":59,"url":"/task/deep-reinforcement-learning/papers/24","json":"/task/deep-reinforcement-learning/papers/24.json","rows":100},{"order":"archive","page":25,"of":59,"url":"/task/deep-reinforcement-learning/papers/25","json":"/task/deep-reinforcement-learning/papers/25.json","rows":100},{"order":"archive","page":26,"of":59,"url":"/task/deep-reinforcement-learning/papers/26","json":"/task/deep-reinforcement-learning/papers/26.json","rows":100},{"order":"archive","page":27,"of":59,"url":"/task/deep-reinforcement-learning/papers/27","json":"/task/deep-reinforcement-learning/papers/27.json","rows":100},{"order":"archive","page":28,"of":59,"url":"/task/deep-reinforcement-learning/papers/28","json":"/task/deep-reinforcement-learning/papers/28.json","rows":100},{"order":"archive","page":29,"of":59,"url":"/task/deep-reinforcement-learning/papers/29","json":"/task/deep-reinforcement-learning/papers/29.json","rows":100},{"order":"archive","page":30,"of":59,"url":"/task/deep-reinforcement-learning/papers/30","json":"/task/deep-reinforcement-learning/papers/30.json","rows":100},{"order":"archive","page":31,"of":59,"url":"/task/deep-reinforcement-learning/papers/31","json":"/task/deep-reinforcement-learning/papers/31.json","rows":100},{"order":"archive","page":32,"of":59,"url":"/task/deep-reinforcement-learning/papers/32","json":"/task/deep-reinforcement-learning/papers/32.json","rows":100},{"order":"archive","page":33,"of":59,"url":"/task/deep-reinforcement-learning/papers/33","json":"/task/deep-reinforcement-learning/papers/33.json","rows":100},{"order":"archive","page":34,"of":59,"url":"/task/deep-reinforcement-learning/papers/34","json":"/task/deep-reinforcement-learning/papers/34.json","rows":100},{"order":"archive","page":35,"of":59,"url":"/task/deep-reinforcement-learning/papers/35","json":"/task/deep-reinforcement-learning/papers/35.json","rows":100},{"order":"archive","page":36,"of":59,"url":"/task/deep-reinforcement-learning/papers/36","json":"/task/deep-reinforcement-learning/papers/36.json","rows":100},{"order":"archive","page":37,"of":59,"url":"/task/deep-reinforcement-learning/papers/37","json":"/task/deep-reinforcement-learning/papers/37.json","rows":100},{"order":"archive","page":38,"of":59,"url":"/task/deep-reinforcement-learning/papers/38","json":"/task/deep-reinforcement-learning/papers/38.json","rows":100},{"order":"archive","page":39,"of":59,"url":"/task/deep-reinforcement-learning/papers/39","json":"/task/deep-reinforcement-learning/papers/39.json","rows":100},{"order":"archive","page":40,"of":59,"url":"/task/deep-reinforcement-learning/papers/40","json":"/task/deep-reinforcement-learning/papers/40.json","rows":100},{"order":"archive","page":41,"of":59,"url":"/task/deep-reinforcement-learning/papers/41","json":"/task/deep-reinforcement-learning/papers/41.json","rows":100},{"order":"archive","page":42,"of":59,"url":"/task/deep-reinforcement-learning/papers/42","json":"/task/deep-reinforcement-learning/papers/42.json","rows":100},{"order":"archive","page":43,"of":59,"url":"/task/deep-reinforcement-learning/papers/43","json":"/task/deep-reinforcement-learning/papers/43.json","rows":100},{"order":"archive","page":44,"of":59,"url":"/task/deep-reinforcement-learning/papers/44","json":"/task/deep-reinforcement-learning/papers/44.json","rows":100},{"order":"archive","page":45,"of":59,"url":"/task/deep-reinforcement-learning/papers/45","json":"/task/deep-reinforcement-learning/papers/45.json","rows":100},{"order":"archive","page":46,"of":59,"url":"/task/deep-reinforcement-learning/papers/46","json":"/task/deep-reinforcement-learning/papers/46.json","rows":100},{"order":"archive","page":47,"of":59,"url":"/task/deep-reinforcement-learning/papers/47","json":"/task/deep-reinforcement-learning/papers/47.json","rows":100},{"order":"archive","page":48,"of":59,"url":"/task/deep-reinforcement-learning/papers/48","json":"/task/deep-reinforcement-learning/papers/48.json","rows":100},{"order":"archive","page":49,"of":59,"url":"/task/deep-reinforcement-learning/papers/49","json":"/task/deep-reinforcement-learning/papers/49.json","rows":100},{"order":"archive","page":50,"of":59,"url":"/task/deep-reinforcement-learning/papers/50","json":"/task/deep-reinforcement-learning/papers/50.json","rows":100},{"order":"archive","page":51,"of":59,"url":"/task/deep-reinforcement-learning/papers/51","json":"/task/deep-reinforcement-learning/papers/51.json","rows":100},{"order":"archive","page":52,"of":59,"url":"/task/deep-reinforcement-learning/papers/52","json":"/task/deep-reinforcement-learning/papers/52.json","rows":100},{"order":"archive","page":53,"of":59,"url":"/task/deep-reinforcement-learning/papers/53","json":"/task/deep-reinforcement-learning/papers/53.json","rows":100},{"order":"archive","page":54,"of":59,"url":"/task/deep-reinforcement-learning/papers/54","json":"/task/deep-reinforcement-learning/papers/54.json","rows":100},{"order":"archive","page":55,"of":59,"url":"/task/deep-reinforcement-learning/papers/55","json":"/task/deep-reinforcement-learning/papers/55.json","rows":100},{"order":"archive","page":56,"of":59,"url":"/task/deep-reinforcement-learning/papers/56","json":"/task/deep-reinforcement-learning/papers/56.json","rows":100},{"order":"archive","page":57,"of":59,"url":"/task/deep-reinforcement-learning/papers/57","json":"/task/deep-reinforcement-learning/papers/57.json","rows":100},{"order":"archive","page":58,"of":59,"url":"/task/deep-reinforcement-learning/papers/58","json":"/task/deep-reinforcement-learning/papers/58.json","rows":100},{"order":"archive","page":59,"of":59,"url":"/task/deep-reinforcement-learning/papers/59","json":"/task/deep-reinforcement-learning/papers/59.json","rows":22},{"order":"ran","page":1,"of":4,"url":"/task/deep-reinforcement-learning/papers/ran/1","json":"/task/deep-reinforcement-learning/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":4,"url":"/task/deep-reinforcement-learning/papers/ran/2","json":"/task/deep-reinforcement-learning/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":4,"url":"/task/deep-reinforcement-learning/papers/ran/3","json":"/task/deep-reinforcement-learning/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":4,"url":"/task/deep-reinforcement-learning/papers/ran/4","json":"/task/deep-reinforcement-learning/papers/ran/4.json","rows":98}],"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":"bba23fb6932fe4b695fd4354f7214e69087f47ab1bae71fde8abe36a6de12c53","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}