{"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":"/method/q-learning/papers/ran/2","list_of":"/method/q-learning","method":"Q-Learning","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,126],"of":126,"counts":{"archive_papers_tagged":1734,"with_a_code_link":464,"where_syntology_ran_a_sample":126,"not_listed_spam_title":0,"listed":1734,"listed_where_code_ran":126,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":105,"every_run_a_failure_of_syntologys_instrument":21,"listed_with_a_run_with_no_instrument_failure":105,"listed_every_run_a_failure_of_syntologys_instrument":21,"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"},"first_page":"/method/q-learning/papers/ran/1","prev":"/method/q-learning/papers/ran/1","next":null,"papers":[{"paper":"/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","n_code_links":10,"syntology":{"ran":14,"of":14,"n_ran_checked":14,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/paper/deep-multi-agent-reinforcement-learning-with","slug":"deep-multi-agent-reinforcement-learning-with","title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs","date":"2018-11-30","arxiv_id":"1811.12557","n_code_links":1,"syntology":{"ran":1,"of":7,"n_ran_checked":1,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["tegg89/magnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/actor-expert-a-framework-for-using-action","slug":"actor-expert-a-framework-for-using-action","title":"Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement","date":"2018-10-22","arxiv_id":"1810.09103","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["samuelfneumann/greedyac"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/successor-uncertainties-exploration-and","slug":"successor-uncertainties-exploration-and","title":"Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning","date":"2018-10-15","arxiv_id":"1810.06530","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":2,"n_instrument":5,"unverified":0,"pointer_only":7,"phrase":"7 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; 5 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/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","n_code_links":5,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"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","official":null}},{"paper":"/paper/towards-better-interpretability-in-deep-q","slug":"towards-better-interpretability-in-deep-q","title":"Towards Better Interpretability in Deep Q-Networks","date":"2018-09-15","arxiv_id":"1809.05630","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":null}},{"paper":"/paper/implicit-quantile-networks-for-distributional","slug":"implicit-quantile-networks-for-distributional","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","date":"2018-06-14","arxiv_id":"1806.06923","n_code_links":19,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/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","n_code_links":4,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"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","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"]}}},{"paper":"/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","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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","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"]}}},{"paper":"/paper/improving-exploration-in-evolution-strategies","slug":"improving-exploration-in-evolution-strategies","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","date":"2017-12-18","arxiv_id":"1712.06560","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["uber-research/deep-neuroevolution"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/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","n_code_links":12,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"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","official":null}},{"paper":"/paper/treeqn-and-atreec-differentiable-tree","slug":"treeqn-and-atreec-differentiable-tree","title":"TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning","date":"2017-10-31","arxiv_id":"1710.11417","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":7,"n_instrument":0,"unverified":5,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["oxwhirl/treeqn"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/distributional-reinforcement-learning-with-1","slug":"distributional-reinforcement-learning-with-1","title":"Distributional Reinforcement Learning with Quantile Regression","date":"2017-10-27","arxiv_id":"1710.10044","n_code_links":17,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/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","n_code_links":34,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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","official":null}},{"paper":"/paper/noisy-networks-for-exploration","slug":"noisy-networks-for-exploration","title":"Noisy Networks for Exploration","date":"2017-06-30","arxiv_id":"1706.10295","n_code_links":15,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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","official":null}},{"paper":"/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","n_code_links":86,"syntology":{"ran":75,"of":143,"n_ran_checked":68,"n_instrument":7,"unverified":68,"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","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"]}}},{"paper":"/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","n_code_links":10,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"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","official":null}},{"paper":"/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","n_code_links":23,"syntology":{"ran":16,"of":29,"n_ran_checked":11,"n_instrument":5,"unverified":13,"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","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"]}}},{"paper":"/paper/count-based-exploration-with-neural-density","slug":"count-based-exploration-with-neural-density","title":"Count-Based Exploration with Neural Density Models","date":"2017-03-03","arxiv_id":"1703.01310","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":null}},{"paper":"/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","n_code_links":10,"syntology":{"ran":2,"of":5,"n_ran_checked":1,"n_instrument":1,"unverified":3,"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","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"]}}},{"paper":"/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","n_code_links":8,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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","official":null}},{"paper":"/paper/deep-exploration-via-bootstrapped-dqn","slug":"deep-exploration-via-bootstrapped-dqn","title":"Deep Exploration via Bootstrapped DQN","date":"2016-02-15","arxiv_id":"1602.04621","n_code_links":6,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/prioritized-experience-replay","slug":"prioritized-experience-replay","title":"Prioritized Experience Replay","date":"2015-11-18","arxiv_id":"1511.05952","n_code_links":77,"syntology":{"ran":80,"of":111,"n_ran_checked":72,"n_instrument":8,"unverified":31,"pointer_only":43,"phrase":"80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified","official":null}},{"paper":"/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","n_code_links":97,"syntology":{"ran":56,"of":106,"n_ran_checked":55,"n_instrument":1,"unverified":50,"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","official":null}},{"paper":"/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","n_code_links":161,"syntology":{"ran":163,"of":306,"n_ran_checked":152,"n_instrument":11,"unverified":143,"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","official":null}},{"paper":"/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","n_code_links":112,"syntology":{"ran":64,"of":117,"n_ran_checked":46,"n_instrument":18,"unverified":53,"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","official":null}}],"record_sha256":"c159661bd04daff515d7a6596235b72cee30086893f0a7f74ee5de5c71aa81a0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}