{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/reinforcement-learning/papers/7","list_of":"/task/reinforcement-learning","task":"Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":132,"rows_per_page":100,"rows":[601,700],"of":13178,"counts":{"archive_papers_tagged":13178,"with_a_code_link":4183,"where_syntology_ran_a_sample":1175,"not_listed_spam_title":0,"listed":13178,"listed_where_code_ran":1175,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":988,"every_run_a_failure_of_syntologys_instrument":187,"listed_with_a_run_with_no_instrument_failure":988,"listed_every_run_a_failure_of_syntologys_instrument":187,"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":"/task/reinforcement-learning","prev":"/task/reinforcement-learning/papers/6","next":"/task/reinforcement-learning/papers/8","papers":[{"url":"/paper/action-advising-with-advice-imitation-in-deep","slug":"action-advising-with-advice-imitation-in-deep","title":"Action Advising with Advice Imitation in Deep Reinforcement Learning","date":"2021-04-17","arxiv_id":"2104.08441","repositories_listed":2,"syntology":null},{"url":"/paper/online-and-offline-reinforcement-learning-by","slug":"online-and-offline-reinforcement-learning-by","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","date":"2021-04-13","arxiv_id":"2104.06294","repositories_listed":2,"syntology":null},{"url":"/paper/cropgym-a-reinforcement-learning-environment","slug":"cropgym-a-reinforcement-learning-environment","title":"CropGym: a Reinforcement Learning Environment for Crop Management","date":"2021-04-09","arxiv_id":"2104.04326","repositories_listed":2,"syntology":null},{"url":"/paper/improving-robustness-of-deep-reinforcement","slug":"improving-robustness-of-deep-reinforcement","title":"Improving Robustness of Deep Reinforcement Learning Agents: Environment Attack based on the Critic Network","date":"2021-04-07","arxiv_id":"2104.03154","repositories_listed":2,"syntology":null},{"url":"/paper/reagent-point-cloud-registration-using","slug":"reagent-point-cloud-registration-using","title":"ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning","date":"2021-03-28","arxiv_id":"2103.15231","repositories_listed":2,"syntology":null},{"url":"/paper/bellman-a-toolbox-for-model-based","slug":"bellman-a-toolbox-for-model-based","title":"Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow","date":"2021-03-26","arxiv_id":"2103.14407","repositories_listed":2,"syntology":null},{"url":"/paper/online-baum-welch-algorithm-for-hierarchical","slug":"online-baum-welch-algorithm-for-hierarchical","title":"Online Baum-Welch algorithm for Hierarchical Imitation Learning","date":"2021-03-22","arxiv_id":"2103.12197","repositories_listed":2,"syntology":null},{"url":"/paper/offline-reinforcement-learning-with-fisher","slug":"offline-reinforcement-learning-with-fisher","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","date":"2021-03-14","arxiv_id":"2103.08050","repositories_listed":2,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-in-2","slug":"multi-agent-reinforcement-learning-in-2","title":"Multi-agent Reinforcement Learning in OpenSpiel: A Reproduction Report","date":"2021-02-27","arxiv_id":"2103.00187","repositories_listed":2,"syntology":null},{"url":"/paper/decoupling-value-and-policy-for","slug":"decoupling-value-and-policy-for","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","date":"2021-02-20","arxiv_id":"2102.10330","repositories_listed":2,"syntology":null},{"url":"/paper/scalable-bayesian-inverse-reinforcement-1","slug":"scalable-bayesian-inverse-reinforcement-1","title":"Scalable Bayesian Inverse Reinforcement Learning","date":"2021-02-12","arxiv_id":"2102.06483","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/scalable-bayesian-inverse-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2102.06483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.06483"}},"official":{"repos":["XanderJC/scalable-birl","vanderschaarlab/mlforhealthlabpub"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/multi-task-reinforcement-learning-with","slug":"multi-task-reinforcement-learning-with","title":"Multi-Task Reinforcement Learning with Context-based Representations","date":"2021-02-11","arxiv_id":"2102.06177","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/multi-task-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2102.06177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.06177"}},"official":{"repos":["facebookresearch/mtenv","facebookresearch/mtrl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/neurogenetic-programming-framework-for","slug":"neurogenetic-programming-framework-for","title":"Neurogenetic Programming Framework for Explainable Reinforcement Learning","date":"2021-02-08","arxiv_id":"2102.04231","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reinforcement-learning-with-dynamic","slug":"deep-reinforcement-learning-with-dynamic","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","date":"2021-02-07","arxiv_id":"2102.03765","repositories_listed":2,"syntology":null},{"url":"/paper/hyperparameter-tricks-in-multi-agent","slug":"hyperparameter-tricks-in-multi-agent","title":"Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement Learning","date":"2021-02-06","arxiv_id":"2102.03479","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hyperparameter-tricks-in-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2102.03479","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03479"}},"official":{"repos":["hijkzzz/pymarl2"],"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/metrics-and-continuity-in-reinforcement","slug":"metrics-and-continuity-in-reinforcement","title":"Metrics and continuity in reinforcement learning","date":"2021-02-02","arxiv_id":"2102.01514","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/metrics-and-continuity-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2102.01514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.01514"}},"official":{"repos":["google-research/google-research"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/robust-reinforcement-learning-on-state-1","slug":"robust-reinforcement-learning-on-state-1","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","date":"2021-01-21","arxiv_id":"2101.08452","repositories_listed":2,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/robust-reinforcement-learning-on-state-1#ran","syntology_url":"https://syntology.ai/paper/2101.08452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08452"}},"official":{"repos":["huanzhang12/ATLA_robust_RL"],"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-common-payoff-games-with-approximate","slug":"solving-common-payoff-games-with-approximate","title":"Solving Common-Payoff Games with Approximate Policy Iteration","date":"2021-01-11","arxiv_id":"2101.04237","repositories_listed":2,"syntology":{"n":9,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 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) · 7 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/solving-common-payoff-games-with-approximate#ran","syntology_url":"https://syntology.ai/paper/2101.04237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.04237"}},"official":{"repos":["ssokota/capi","ssokota/tiny-hanabi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-with-latent-flow-1","slug":"reinforcement-learning-with-latent-flow-1","title":"Reinforcement Learning with Latent Flow","date":"2021-01-06","arxiv_id":"2101.01857","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-with-latent-flow-1#ran","syntology_url":"https://syntology.ai/paper/2101.01857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.01857"}},"official":{"repos":["WendyShang/flare","WendyShang/dqn_zoo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-for-control-of-valves","slug":"reinforcement-learning-for-control-of-valves","title":"Reinforcement Learning for Control of Valves","date":"2020-12-29","arxiv_id":"2012.14668","repositories_listed":2,"syntology":null},{"url":"/paper/augmenting-policy-learning-with-routines","slug":"augmenting-policy-learning-with-routines","title":"Augmenting Policy Learning with Routines Discovered from a Single Demonstration","date":"2020-12-23","arxiv_id":"2012.12469","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/augmenting-policy-learning-with-routines#ran","syntology_url":"https://syntology.ai/paper/2012.12469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.12469"}},"official":{"repos":["sjtuytc/-AAAI21-RoutineAugmentedPolicyLearning-RAPL-","sjtuytc/AAAI21-RoutineAugmentedPolicyLearning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-the-lunar-lander-problem-under","slug":"solving-the-lunar-lander-problem-under","title":"Solving The Lunar Lander Problem under Uncertainty using Reinforcement Learning","date":"2020-11-24","arxiv_id":"2011.11850","repositories_listed":2,"syntology":null},{"url":"/paper/revisiting-rainbow-promoting-more-insightful","slug":"revisiting-rainbow-promoting-more-insightful","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","date":"2020-11-20","arxiv_id":"2011.14826","repositories_listed":2,"syntology":null},{"url":"/paper/plas-latent-action-space-for-offline","slug":"plas-latent-action-space-for-offline","title":"PLAS: Latent Action Space for Offline Reinforcement Learning","date":"2020-11-14","arxiv_id":"2011.07213","repositories_listed":2,"syntology":null},{"url":"/paper/softgym-benchmarking-deep-reinforcement","slug":"softgym-benchmarking-deep-reinforcement","title":"SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation","date":"2020-11-14","arxiv_id":"2011.07215","repositories_listed":2,"syntology":null},{"url":"/paper/what-did-you-think-would-happen-explaining","slug":"what-did-you-think-would-happen-explaining","title":"What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes","date":"2020-11-10","arxiv_id":"2011.05064","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/what-did-you-think-would-happen-explaining#ran","syntology_url":"https://syntology.ai/paper/2011.05064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.05064"}},"official":{"repos":["hmhyau/rl-intention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/generalization-to-new-actions-in-1","slug":"generalization-to-new-actions-in-1","title":"Generalization to New Actions in Reinforcement Learning","date":"2020-11-03","arxiv_id":"2011.01928","repositories_listed":2,"syntology":{"n":21,"n_ran":18,"n_constructed":14,"n_ran_checked":16,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":14,"n_pointer_only":20,"phrase":"18 ran (of which 14 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generalization-to-new-actions-in-1#ran","syntology_url":"https://syntology.ai/paper/2011.01928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01928"}},"official":{"repos":["clvrai/new-actions-rl","clvrai/create"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":14,"n_ran_no_instrument_failure":16,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/exact-asymptotics-for-linear-quadratic","slug":"exact-asymptotics-for-linear-quadratic","title":"Exact Asymptotics for Linear Quadratic Adaptive Control","date":"2020-11-02","arxiv_id":"2011.01364","repositories_listed":2,"syntology":null},{"url":"/paper/recovery-rl-safe-reinforcement-learning-with","slug":"recovery-rl-safe-reinforcement-learning-with","title":"Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones","date":"2020-10-29","arxiv_id":"2010.15920","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recovery-rl-safe-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2010.15920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15920"}},"official":null}},{"url":"/paper/accelerating-reinforcement-learning-with-1","slug":"accelerating-reinforcement-learning-with-1","title":"Accelerating Reinforcement Learning with Learned Skill Priors","date":"2020-10-22","arxiv_id":"2010.11944","repositories_listed":2,"syntology":null},{"url":"/paper/improving-generalization-in-reinforcement","slug":"improving-generalization-in-reinforcement","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","date":"2020-10-21","arxiv_id":"2010.10814","repositories_listed":2,"syntology":null},{"url":"/paper/deepaveragers-offline-reinforcement-learning-1","slug":"deepaveragers-offline-reinforcement-learning-1","title":"DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs","date":"2020-10-18","arxiv_id":"2010.08891","repositories_listed":2,"syntology":null},{"url":"/paper/hyperparameter-auto-tuning-in-self-supervised","slug":"hyperparameter-auto-tuning-in-self-supervised","title":"Hyperparameter Auto-tuning in Self-Supervised Robotic Learning","date":"2020-10-16","arxiv_id":"2010.08252","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperparameter-auto-tuning-in-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2010.08252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08252"}},"official":{"repos":["birlrobotics/rlkit_autotune"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/robot-navigation-in-constrained-pedestrian","slug":"robot-navigation-in-constrained-pedestrian","title":"Robot Navigation in Constrained Pedestrian Environments using Reinforcement Learning","date":"2020-10-16","arxiv_id":"2010.08600","repositories_listed":2,"syntology":null},{"url":"/paper/epidemioptim-a-toolbox-for-the-optimization-1","slug":"epidemioptim-a-toolbox-for-the-optimization-1","title":"EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models","date":"2020-10-09","arxiv_id":"2010.04452","repositories_listed":2,"syntology":null},{"url":"/paper/fork-a-forward-looking-actor-for-model-free-1","slug":"fork-a-forward-looking-actor-for-model-free-1","title":"FORK: A Forward-Looking Actor For Model-Free Reinforcement Learning","date":"2020-10-04","arxiv_id":"2010.01652","repositories_listed":2,"syntology":null},{"url":"/paper/pettingzoo-gym-for-multi-agent-reinforcement","slug":"pettingzoo-gym-for-multi-agent-reinforcement","title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","date":"2020-09-30","arxiv_id":"2009.14471","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pettingzoo-gym-for-multi-agent-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2009.14471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14471"}},"official":{"repos":["Farama-Foundation/PettingZoo"],"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/deep-reinforcement-learning-for-process","slug":"deep-reinforcement-learning-for-process","title":"Deep Reinforcement Learning for Process Synthesis","date":"2020-09-23","arxiv_id":"2009.13265","repositories_listed":2,"syntology":null},{"url":"/paper/solving-challenging-dexterous-manipulation","slug":"solving-challenging-dexterous-manipulation","title":"Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning","date":"2020-09-09","arxiv_id":"2009.05104","repositories_listed":2,"syntology":null},{"url":"/paper/market-making-with-reinforcement-learning-sac","slug":"market-making-with-reinforcement-learning-sac","title":"Market-making with reinforcement-learning (SAC)","date":"2020-08-27","arxiv_id":"2008.12275","repositories_listed":2,"syntology":null},{"url":"/paper/reinforcement-learning-with-quantum","slug":"reinforcement-learning-with-quantum","title":"Reinforcement Learning with Quantum Variational Circuits","date":"2020-08-15","arxiv_id":"2008.07524","repositories_listed":2,"syntology":null},{"url":"/paper/offline-meta-reinforcement-learning-with","slug":"offline-meta-reinforcement-learning-with","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","date":"2020-08-13","arxiv_id":"2008.06043","repositories_listed":2,"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/offline-meta-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2008.06043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.06043"}},"official":{"repos":["eric-mitchell/macaw"],"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/trifinger-an-open-source-robot-for-learning","slug":"trifinger-an-open-source-robot-for-learning","title":"TriFinger: An Open-Source Robot for Learning Dexterity","date":"2020-08-08","arxiv_id":"2008.03596","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trifinger-an-open-source-robot-for-learning#ran","syntology_url":"https://syntology.ai/paper/2008.03596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.03596"}},"official":null}},{"url":"/paper/explore-then-execute-adapting-without-rewards","slug":"explore-then-execute-adapting-without-rewards","title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices","date":"2020-08-06","arxiv_id":"2008.02790","repositories_listed":2,"syntology":null},{"url":"/paper/robust-deep-reinforcement-learning-through","slug":"robust-deep-reinforcement-learning-through","title":"Robust Deep Reinforcement Learning through Adversarial Loss","date":"2020-08-05","arxiv_id":"2008.01976","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-through#ran","syntology_url":"https://syntology.ai/paper/2008.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01976"}},"official":{"repos":["tuomaso/radial_rl","tuomaso/radial_rl_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evolve-to-control-evolution-based-soft-actor","slug":"evolve-to-control-evolution-based-soft-actor","title":"Maximum Mutation Reinforcement Learning for Scalable Control","date":"2020-07-24","arxiv_id":"2007.13690","repositories_listed":2,"syntology":null},{"url":"/paper/active-mr-k-space-sampling-with-reinforcement","slug":"active-mr-k-space-sampling-with-reinforcement","title":"Active MR k-space Sampling with Reinforcement Learning","date":"2020-07-20","arxiv_id":"2007.10469","repositories_listed":2,"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":1,"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/active-mr-k-space-sampling-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2007.10469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10469"}},"official":{"repos":["facebookresearch/active-mri-acquisition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/discovering-reinforcement-learning-algorithms","slug":"discovering-reinforcement-learning-algorithms","title":"Discovering Reinforcement Learning Algorithms","date":"2020-07-17","arxiv_id":"2007.08794","repositories_listed":2,"syntology":null},{"url":"/paper/multi-task-reinforcement-learning-as-a-hidden","slug":"multi-task-reinforcement-learning-as-a-hidden","title":"Learning Robust State Abstractions for Hidden-Parameter Block MDPs","date":"2020-07-14","arxiv_id":"2007.07206","repositories_listed":2,"syntology":null},{"url":"/paper/one-policy-to-control-them-all-shared-modular-1","slug":"one-policy-to-control-them-all-shared-modular-1","title":"One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control","date":"2020-07-09","arxiv_id":"2007.04976","repositories_listed":2,"syntology":null},{"url":"/paper/reward-machines-for-cooperative-multi-agent","slug":"reward-machines-for-cooperative-multi-agent","title":"Reward Machines for Cooperative Multi-Agent Reinforcement Learning","date":"2020-07-03","arxiv_id":"2007.01962","repositories_listed":2,"syntology":null},{"url":"/paper/mdp-homomorphic-networks-group-symmetries-in","slug":"mdp-homomorphic-networks-group-symmetries-in","title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning","date":"2020-06-30","arxiv_id":"2006.16908","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mdp-homomorphic-networks-group-symmetries-in#ran","syntology_url":"https://syntology.ai/paper/2006.16908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16908"}},"official":{"repos":["ElisevanderPol/mdp-homomorphic-networks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/off-dynamics-reinforcement-learning-training","slug":"off-dynamics-reinforcement-learning-training","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","date":"2020-06-24","arxiv_id":"2006.13916","repositories_listed":2,"syntology":{"n":23,"n_ran":21,"n_constructed":4,"n_ran_checked":15,"n_instrument":6,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":12,"n_pointer_only":7,"phrase":"21 ran (of which 4 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/off-dynamics-reinforcement-learning-training#ran","syntology_url":"https://syntology.ai/paper/2006.13916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13916"}},"official":null}},{"url":"/paper/rl-unplugged-benchmarks-for-offline","slug":"rl-unplugged-benchmarks-for-offline","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","date":"2020-06-24","arxiv_id":"2006.13888","repositories_listed":2,"syntology":null},{"url":"/paper/expert-supervised-reinforcement-learning-for","slug":"expert-supervised-reinforcement-learning-for","title":"Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation","date":"2020-06-23","arxiv_id":"2006.13189","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":2,"n_ran_checked":2,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":11,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/expert-supervised-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2006.13189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13189"}},"official":{"repos":["asonabend/ESRL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/graph-neural-networks-and-reinforcement","slug":"graph-neural-networks-and-reinforcement","title":"Graph Neural Networks and Reinforcement Learning for Behavior Generation in Semantic Environments","date":"2020-06-22","arxiv_id":"2006.12576","repositories_listed":2,"syntology":null},{"url":"/paper/learning-invariant-representations-for-1","slug":"learning-invariant-representations-for-1","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","date":"2020-06-18","arxiv_id":"2006.10742","repositories_listed":2,"syntology":null},{"url":"/paper/pipeline-psro-a-scalable-approach-for-finding","slug":"pipeline-psro-a-scalable-approach-for-finding","title":"Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games","date":"2020-06-15","arxiv_id":"2006.08555","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pipeline-psro-a-scalable-approach-for-finding#ran","syntology_url":"https://syntology.ai/paper/2006.08555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08555"}},"official":{"repos":["JBLanier/pipeline-psro"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/torsionnet-a-reinforcement-learning-approach","slug":"torsionnet-a-reinforcement-learning-approach","title":"TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search","date":"2020-06-12","arxiv_id":"2006.07078","repositories_listed":2,"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":0,"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/torsionnet-a-reinforcement-learning-approach#ran","syntology_url":"https://syntology.ai/paper/2006.07078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07078"}},"official":{"repos":["tarungog/torsionnet_paper_version"],"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/ai-qmix-attention-and-imagination-for-dynamic","slug":"ai-qmix-attention-and-imagination-for-dynamic","title":"Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04222","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/ai-qmix-attention-and-imagination-for-dynamic#ran","syntology_url":"https://syntology.ai/paper/2006.04222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04222"}},"official":{"repos":["shariqiqbal2810/REFIL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/predicting-goal-directed-human-attention","slug":"predicting-goal-directed-human-attention","title":"Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning","date":"2020-05-28","arxiv_id":"2005.14310","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"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","sample_list":"/paper/predicting-goal-directed-human-attention#ran","syntology_url":"https://syntology.ai/paper/2005.14310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14310"}},"official":{"repos":["cvlab-stonybrook/Scanpath_Prediction"],"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"]}}},{"url":"/paper/morel-model-based-offline-reinforcement","slug":"morel-model-based-offline-reinforcement","title":"MOReL : Model-Based Offline Reinforcement Learning","date":"2020-05-12","arxiv_id":"2005.05951","repositories_listed":2,"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":6,"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/morel-model-based-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2005.05951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05951"}},"official":null}},{"url":"/paper/reinforcement-learning-with-augmented-data","slug":"reinforcement-learning-with-augmented-data","title":"Reinforcement Learning with Augmented Data","date":"2020-04-30","arxiv_id":"2004.14990","repositories_listed":2,"syntology":{"n":24,"n_ran":21,"n_constructed":8,"n_ran_checked":9,"n_instrument":12,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":21,"phrase":"21 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reinforcement-learning-with-augmented-data#ran","syntology_url":"https://syntology.ai/paper/2004.14990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14990"}},"official":null}},{"url":"/paper/emergent-real-world-robotic-skills-via","slug":"emergent-real-world-robotic-skills-via","title":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning","date":"2020-04-27","arxiv_id":"2004.12974","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/emergent-real-world-robotic-skills-via#ran","syntology_url":"https://syntology.ai/paper/2004.12974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12974"}},"official":null}},{"url":"/paper/first-return-then-explore","slug":"first-return-then-explore","title":"First return, then explore","date":"2020-04-27","arxiv_id":"2004.12919","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/first-return-then-explore#ran","syntology_url":"https://syntology.ai/paper/2004.12919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12919"}},"official":{"repos":["uber-research/go-explore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-meta-reinforcement-learning-for","slug":"model-based-meta-reinforcement-learning-for","title":"Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads","date":"2020-04-23","arxiv_id":"2004.11345","repositories_listed":2,"syntology":null},{"url":"/paper/chip-placement-with-deep-reinforcement","slug":"chip-placement-with-deep-reinforcement","title":"Chip Placement with Deep Reinforcement Learning","date":"2020-04-22","arxiv_id":"2004.10746","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/chip-placement-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2004.10746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.10746"}},"official":null}},{"url":"/paper/patchattack-a-black-box-texture-based-attack","slug":"patchattack-a-black-box-texture-based-attack","title":"PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning","date":"2020-04-12","arxiv_id":"2004.05682","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/patchattack-a-black-box-texture-based-attack#ran","syntology_url":"https://syntology.ai/paper/2004.05682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05682"}},"official":{"repos":["Chenglin-Yang/PatchAttack"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/adaptive-partial-scanning-transmission","slug":"adaptive-partial-scanning-transmission","title":"Adaptive Partial Scanning Transmission Electron Microscopy with Reinforcement Learning","date":"2020-04-06","arxiv_id":"2004.02786","repositories_listed":2,"syntology":null},{"url":"/paper/dhp-differentiable-meta-pruning-via","slug":"dhp-differentiable-meta-pruning-via","title":"DHP: Differentiable Meta Pruning via HyperNetworks","date":"2020-03-30","arxiv_id":"2003.13683","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dhp-differentiable-meta-pruning-via#ran","syntology_url":"https://syntology.ai/paper/2003.13683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13683"}},"official":{"repos":["ofsoundof/dhp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-ensemble-learning-with","slug":"sample-efficient-ensemble-learning-with","title":"Sample Efficient Ensemble Learning with Catalyst.RL","date":"2020-03-29","arxiv_id":"2003.14210","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sample-efficient-ensemble-learning-with#ran","syntology_url":"https://syntology.ai/paper/2003.14210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.14210"}},"official":{"repos":["Scitator/run-skeleton-run-in-3d"],"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/modeling-3d-shapes-by-reinforcement-learning","slug":"modeling-3d-shapes-by-reinforcement-learning","title":"Modeling 3D Shapes by Reinforcement Learning","date":"2020-03-27","arxiv_id":"2003.12397","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modeling-3d-shapes-by-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2003.12397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.12397"}},"official":null}},{"url":"/paper/flapai-bird-training-an-agent-to-play-flappy","slug":"flapai-bird-training-an-agent-to-play-flappy","title":"FlapAI Bird: Training an Agent to Play Flappy Bird Using Reinforcement Learning Techniques","date":"2020-03-21","arxiv_id":"2003.09579","repositories_listed":2,"syntology":null},{"url":"/paper/using-counterfactual-reasoning-and","slug":"using-counterfactual-reasoning-and","title":"Counterfactual Policy Evaluation for Decision-Making in Autonomous Driving","date":"2020-03-20","arxiv_id":"2003.11919","repositories_listed":2,"syntology":null},{"url":"/paper/a-deep-multi-agent-reinforcement-learning","slug":"a-deep-multi-agent-reinforcement-learning","title":"A Deep Multi-Agent Reinforcement Learning Approach to Autonomous Separation Assurance","date":"2020-03-17","arxiv_id":"2003.08353","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-unknown-states-with-action-balance","slug":"exploring-unknown-states-with-action-balance","title":"Exploring Unknown States with Action Balance","date":"2020-03-10","arxiv_id":"2003.04518","repositories_listed":2,"syntology":null},{"url":"/paper/other-play-for-zero-shot-coordination","slug":"other-play-for-zero-shot-coordination","title":"\"Other-Play\" for Zero-Shot Coordination","date":"2020-03-06","arxiv_id":"2003.02979","repositories_listed":2,"syntology":null},{"url":"/paper/learning-when-and-where-to-zoom-with-deep","slug":"learning-when-and-where-to-zoom-with-deep","title":"Learning When and Where to Zoom with Deep Reinforcement Learning","date":"2020-03-01","arxiv_id":"2003.00425","repositories_listed":2,"syntology":null},{"url":"/paper/analysis-of-diversity-accuracy-tradeoff-in","slug":"analysis-of-diversity-accuracy-tradeoff-in","title":"Analysis of diversity-accuracy tradeoff in image captioning","date":"2020-02-27","arxiv_id":"2002.11848","repositories_listed":2,"syntology":null},{"url":"/paper/language-as-a-cognitive-tool-to-imagine-goals","slug":"language-as-a-cognitive-tool-to-imagine-goals","title":"Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration","date":"2020-02-21","arxiv_id":"2002.09253","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/language-as-a-cognitive-tool-to-imagine-goals#ran","syntology_url":"https://syntology.ai/paper/2002.09253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09253"}},"official":{"repos":["flowersteam/Imagine","flowersteam/playground_env"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/langevin-dqn","slug":"langevin-dqn","title":"Langevin DQN","date":"2020-02-17","arxiv_id":"2002.07282","repositories_listed":2,"syntology":null},{"url":"/paper/first-order-optimization-in-policy-space-for","slug":"first-order-optimization-in-policy-space-for","title":"First Order Constrained Optimization in Policy Space","date":"2020-02-16","arxiv_id":"2002.06506","repositories_listed":2,"syntology":null},{"url":"/paper/pddlgym-gym-environments-from-pddl-problems","slug":"pddlgym-gym-environments-from-pddl-problems","title":"PDDLGym: Gym Environments from PDDL Problems","date":"2020-02-15","arxiv_id":"2002.06432","repositories_listed":2,"syntology":{"n":11,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/pddlgym-gym-environments-from-pddl-problems#ran","syntology_url":"https://syntology.ai/paper/2002.06432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06432"}},"official":{"repos":["tomsilver/pddlgym"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/an-inductive-bias-for-distances-neural-nets-1","slug":"an-inductive-bias-for-distances-neural-nets-1","title":"An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality","date":"2020-02-14","arxiv_id":"2002.05825","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-inductive-bias-for-distances-neural-nets-1#ran","syntology_url":"https://syntology.ai/paper/2002.05825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05825"}},"official":{"repos":["spitis/deepnorms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/laprop-a-better-way-to-combine-momentum-with","slug":"laprop-a-better-way-to-combine-momentum-with","title":"LaProp: Separating Momentum and Adaptivity in Adam","date":"2020-02-12","arxiv_id":"2002.04839","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/laprop-a-better-way-to-combine-momentum-with#ran","syntology_url":"https://syntology.ai/paper/2002.04839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.04839"}},"official":{"repos":["Z-T-WANG/LaProp-Optimizer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/objective-mismatch-in-model-based-1","slug":"objective-mismatch-in-model-based-1","title":"Objective Mismatch in Model-based Reinforcement Learning","date":"2020-02-11","arxiv_id":"2002.04523","repositories_listed":2,"syntology":null},{"url":"/paper/learning-state-abstractions-for-transfer-in","slug":"learning-state-abstractions-for-transfer-in","title":"Learning State Abstractions for Transfer in Continuous Control","date":"2020-02-08","arxiv_id":"2002.05518","repositories_listed":2,"syntology":null},{"url":"/paper/one-shot-bayes-opt-with-probabilistic","slug":"one-shot-bayes-opt-with-probabilistic","title":"Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits","date":"2020-02-06","arxiv_id":"2002.02518","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/one-shot-bayes-opt-with-probabilistic#ran","syntology_url":"https://syntology.ai/paper/2002.02518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.02518"}},"official":{"repos":["jparkerholder/PB2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/soft-hindsight-experience-replay","slug":"soft-hindsight-experience-replay","title":"Soft Hindsight Experience Replay","date":"2020-02-06","arxiv_id":"2002.02089","repositories_listed":2,"syntology":null},{"url":"/paper/effective-diversity-in-population-based","slug":"effective-diversity-in-population-based","title":"Effective Diversity in Population Based Reinforcement Learning","date":"2020-02-03","arxiv_id":"2002.00632","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":6,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":9,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/effective-diversity-in-population-based#ran","syntology_url":"https://syntology.ai/paper/2002.00632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00632"}},"official":{"repos":["jparkerholder/DvD_ES"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-the-systematic-reporting-of-the","slug":"towards-the-systematic-reporting-of-the","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","date":"2020-01-31","arxiv_id":"2002.05651","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/towards-the-systematic-reporting-of-the#ran","syntology_url":"https://syntology.ai/paper/2002.05651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05651"}},"official":{"repos":["Breakend/ClimateChangeFromMachineLearningResearch","Breakend/experiment-impact-tracker"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/multitask-radiological-modality-invariant","slug":"multitask-radiological-modality-invariant","title":"Multitask radiological modality invariant landmark localization using deep reinforcement learning","date":"2020-01-25","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/silly-rules-improve-the-capacity-of-agents-to","slug":"silly-rules-improve-the-capacity-of-agents-to","title":"Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors","date":"2020-01-25","arxiv_id":"2001.09318","repositories_listed":2,"syntology":null},{"url":"/paper/mushroomrl-simplifying-reinforcement-learning","slug":"mushroomrl-simplifying-reinforcement-learning","title":"MushroomRL: Simplifying Reinforcement Learning Research","date":"2020-01-04","arxiv_id":"2001.01102","repositories_listed":2,"syntology":null},{"url":"/paper/represented-value-function-approach-for-large","slug":"represented-value-function-approach-for-large","title":"Represented Value Function Approach for Large Scale Multi Agent Reinforcement Learning","date":"2020-01-04","arxiv_id":"2001.01096","repositories_listed":2,"syntology":null},{"url":"/paper/operationally-meaningful-representations-of","slug":"operationally-meaningful-representations-of","title":"Operationally meaningful representations of physical systems in neural networks","date":"2020-01-02","arxiv_id":"2001.00593","repositories_listed":2,"syntology":null},{"url":"/paper/reasoning-on-knowledge-graphs-with-debate","slug":"reasoning-on-knowledge-graphs-with-debate","title":"Reasoning on Knowledge Graphs with Debate Dynamics","date":"2020-01-02","arxiv_id":"2001.00461","repositories_listed":2,"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/reasoning-on-knowledge-graphs-with-debate#ran","syntology_url":"https://syntology.ai/paper/2001.00461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00461"}},"official":{"repos":["m-hildebrandt/R2D2"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/prediction-guided-multi-objective","slug":"prediction-guided-multi-objective","title":"Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control","date":"2020-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/pac-confidence-sets-for-deep-neural-networks-1","slug":"pac-confidence-sets-for-deep-neural-networks-1","title":"PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction","date":"2019-12-31","arxiv_id":"2001.00106","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/pac-confidence-sets-for-deep-neural-networks-1#ran","syntology_url":"https://syntology.ai/paper/2001.00106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00106"}},"official":{"repos":["sangdon/PAC-confidence-set"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/side-tuning-network-adaptation-via-additive-1","slug":"side-tuning-network-adaptation-via-additive-1","title":"Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks","date":"2019-12-31","arxiv_id":"1912.13503","repositories_listed":2,"syntology":null}],"record_sha256":"98f34dbb15cdeaffcbde31c8a793ba148ce81dfb627a00c677f4db098a364c84","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}