{"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-1/papers/8","list_of":"/task/reinforcement-learning-1","task":"Reinforcement Learning (RL)","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":8,"pages_in_order":152,"rows_per_page":100,"rows":[701,800],"of":15113,"counts":{"archive_papers_tagged":15113,"with_a_code_link":4749,"where_syntology_ran_a_sample":1416,"not_listed_spam_title":0,"listed":15113,"listed_where_code_ran":1416,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1186,"every_run_a_failure_of_syntologys_instrument":230,"listed_with_a_run_with_no_instrument_failure":1186,"listed_every_run_a_failure_of_syntologys_instrument":230,"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-1","prev":"/task/reinforcement-learning-1/papers/7","next":"/task/reinforcement-learning-1/papers/9","papers":[{"url":"/paper/revisiting-fundamentals-of-experience-replay","slug":"revisiting-fundamentals-of-experience-replay","title":"Revisiting Fundamentals of Experience Replay","date":"2020-07-13","arxiv_id":"2007.06700","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/revisiting-fundamentals-of-experience-replay#ran","syntology_url":"https://syntology.ai/paper/2007.06700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06700"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/an-equivalence-between-loss-functions-and-non","slug":"an-equivalence-between-loss-functions-and-non","title":"An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay","date":"2020-07-12","arxiv_id":"2007.06049","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/an-equivalence-between-loss-functions-and-non#ran","syntology_url":"https://syntology.ai/paper/2007.06049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06049"}},"official":{"repos":["sfujim/LAP-PAL"],"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/on-the-reliability-and-generalizability-of","slug":"on-the-reliability-and-generalizability-of","title":"On the Reliability and Generalizability of Brain-inspired Reinforcement Learning Algorithms","date":"2020-07-09","arxiv_id":"2007.04578","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/the-loca-regret-a-consistent-metric-to","slug":"the-loca-regret-a-consistent-metric-to","title":"The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning","date":"2020-07-07","arxiv_id":"2007.03158","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"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 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/the-loca-regret-a-consistent-metric-to#ran","syntology_url":"https://syntology.ai/paper/2007.03158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03158"}},"official":{"repos":["chandar-lab/LoCA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/maximum-entropy-gain-exploration-for-long","slug":"maximum-entropy-gain-exploration-for-long","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","date":"2020-07-06","arxiv_id":"2007.02832","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/maximum-entropy-gain-exploration-for-long#ran","syntology_url":"https://syntology.ai/paper/2007.02832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02832"}},"official":{"repos":["spitis/mrl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/reward-machines-for-cooperative-multi-agent","slug":"reward-machines-for-cooperative-multi-agent","title":"Reward Machines for Cooperative Multi-Agent Reinforcement Learning","date":"2020-07-03","arxiv_id":"2007.01962","repositories_listed":2,"syntology":null},{"url":"/paper/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/disk-learning-local-features-with-policy","slug":"disk-learning-local-features-with-policy","title":"DISK: Learning local features with policy gradient","date":"2020-06-24","arxiv_id":"2006.13566","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":4,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 4 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/disk-learning-local-features-with-policy#ran","syntology_url":"https://syntology.ai/paper/2006.13566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13566"}},"official":{"repos":["cvlab-epfl/disk"],"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/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/converting-biomechanical-models-from-opensim","slug":"converting-biomechanical-models-from-opensim","title":"Converting Biomechanical Models from OpenSim to MuJoCo","date":"2020-06-17","arxiv_id":"2006.10618","repositories_listed":2,"syntology":null},{"url":"/paper/analytic-manifold-learning-unifying-and","slug":"analytic-manifold-learning-unifying-and","title":"Analytic Manifold Learning: Unifying and Evaluating Representations for Continuous Control","date":"2020-06-15","arxiv_id":"2006.08718","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/modelling-hierarchical-structure-between","slug":"modelling-hierarchical-structure-between","title":"Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System","date":"2020-06-11","arxiv_id":"2006.06814","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-incentivize-other-learning-agents","slug":"learning-to-incentivize-other-learning-agents","title":"Learning to Incentivize Other Learning Agents","date":"2020-06-10","arxiv_id":"2006.06051","repositories_listed":2,"syntology":{"n":10,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 10 unverified","sample_list":"/paper/learning-to-incentivize-other-learning-agents#ran","syntology_url":"https://syntology.ai/paper/2006.06051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06051"}},"official":{"repos":["011235813/lio"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":10,"ran_from_kinds":[]}}},{"url":"/paper/what-matters-in-on-policy-reinforcement","slug":"what-matters-in-on-policy-reinforcement","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","date":"2020-06-10","arxiv_id":"2006.05990","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/what-matters-in-on-policy-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2006.05990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.05990"}},"official":null}},{"url":"/paper/learning-to-play-no-press-diplomacy-with-best","slug":"learning-to-play-no-press-diplomacy-with-best","title":"Learning to Play No-Press Diplomacy with Best Response Policy Iteration","date":"2020-06-08","arxiv_id":"2006.04635","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/learning-to-play-no-press-diplomacy-with-best#ran","syntology_url":"https://syntology.ai/paper/2006.04635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04635"}},"official":{"repos":["deepmind/diplomacy"],"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/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/context-aware-dynamics-model-for","slug":"context-aware-dynamics-model-for","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","date":"2020-05-14","arxiv_id":"2005.06800","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/context-aware-dynamics-model-for#ran","syntology_url":"https://syntology.ai/paper/2005.06800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.06800"}},"official":{"repos":["younggyoseo/CaDM"],"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/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/implementation-matters-in-deep-rl-a-case","slug":"implementation-matters-in-deep-rl-a-case","title":"Implementation Matters in Deep RL: A Case Study on PPO and TRPO","date":"2020-05-01","arxiv_id":null,"repositories_listed":2,"syntology":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/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/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/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/langevin-dqn","slug":"langevin-dqn","title":"Langevin DQN","date":"2020-02-17","arxiv_id":"2002.07282","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/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/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/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/explain-your-move-understanding-agent-actions-1","slug":"explain-your-move-understanding-agent-actions-1","title":"Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution","date":"2019-12-23","arxiv_id":"1912.12191","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"6 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/explain-your-move-understanding-agent-actions-1#ran","syntology_url":"https://syntology.ai/paper/1912.12191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.12191"}},"official":{"repos":["rl-interpretation/understandingRL"],"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":["listed","official","unlocated"]}}},{"url":"/paper/interestingness-elements-for-explainable","slug":"interestingness-elements-for-explainable","title":"Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations","date":"2019-12-19","arxiv_id":"1912.09007","repositories_listed":2,"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":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","sample_list":"/paper/interestingness-elements-for-explainable#ran","syntology_url":"https://syntology.ai/paper/1912.09007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.09007"}},"official":{"repos":["SRI-AIC/InterestingnessXRL"],"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/eyecar-modeling-the-visual-attention","slug":"eyecar-modeling-the-visual-attention","title":"MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learning","date":"2019-12-17","arxiv_id":"1912.07773","repositories_listed":2,"syntology":null},{"url":"/paper/pseudo-random-number-generation-a","slug":"pseudo-random-number-generation-a","title":"Pseudo Random Number Generation: a Reinforcement Learning approach","date":"2019-12-15","arxiv_id":"1912.11531","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-reach-goals-without-reinforcement-1","slug":"learning-to-reach-goals-without-reinforcement-1","title":"Learning to Reach Goals via Iterated Supervised Learning","date":"2019-12-12","arxiv_id":"1912.06088","repositories_listed":2,"syntology":null},{"url":"/paper/orl-reinforcement-learning-benchmarks-for","slug":"orl-reinforcement-learning-benchmarks-for","title":"ORL: Reinforcement Learning Benchmarks for Online Stochastic Optimization Problems","date":"2019-11-24","arxiv_id":"1911.10641","repositories_listed":2,"syntology":null},{"url":"/paper/combinatorial-optimization-by-graph-pointer","slug":"combinatorial-optimization-by-graph-pointer","title":"Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning","date":"2019-11-12","arxiv_id":"1911.04936","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/combinatorial-optimization-by-graph-pointer#ran","syntology_url":"https://syntology.ai/paper/1911.04936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04936"}},"official":{"repos":["qiang-ma/graph-pointer-network"],"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/frequentist-regret-bounds-for-randomized","slug":"frequentist-regret-bounds-for-randomized","title":"Frequentist Regret Bounds for Randomized Least-Squares Value Iteration","date":"2019-11-01","arxiv_id":"1911.00567","repositories_listed":2,"syntology":null},{"url":"/paper/pic-permutation-invariant-critic-for-multi","slug":"pic-permutation-invariant-critic-for-multi","title":"PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning","date":"2019-10-31","arxiv_id":"1911.00025","repositories_listed":2,"syntology":null},{"url":"/paper/multimodal-model-agnostic-meta-learning-via","slug":"multimodal-model-agnostic-meta-learning-via","title":"Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation","date":"2019-10-30","arxiv_id":"1910.13616","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/multimodal-model-agnostic-meta-learning-via#ran","syntology_url":"https://syntology.ai/paper/1910.13616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13616"}},"official":{"repos":["vuoristo/MMAML"],"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/191013439","slug":"191013439","title":"Learning to Manipulate Deformable Objects without Demonstrations","date":"2019-10-29","arxiv_id":"1910.13439","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/191013439#ran","syntology_url":"https://syntology.ai/paper/1910.13439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13439"}},"official":{"repos":["wilson1yan/rlpyt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-predict-without-looking-ahead","slug":"learning-to-predict-without-looking-ahead","title":"Learning to Predict Without Looking Ahead: World Models Without Forward Prediction","date":"2019-10-29","arxiv_id":"1910.13038","repositories_listed":2,"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/learning-to-predict-without-looking-ahead#ran","syntology_url":"https://syntology.ai/paper/1910.13038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13038"}},"official":null}},{"url":"/paper/learning-data-manipulation-for-augmentation","slug":"learning-data-manipulation-for-augmentation","title":"Learning Data Manipulation for Augmentation and Weighting","date":"2019-10-28","arxiv_id":"1910.12795","repositories_listed":2,"syntology":null},{"url":"/paper/zpd-teaching-strategies-for-deep","slug":"zpd-teaching-strategies-for-deep","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","date":"2019-10-26","arxiv_id":"1910.12154","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zpd-teaching-strategies-for-deep#ran","syntology_url":"https://syntology.ai/paper/1910.12154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12154"}},"official":null}},{"url":"/paper/rationally-inattentive-inverse-reinforcement","slug":"rationally-inattentive-inverse-reinforcement","title":"Rationally Inattentive Inverse Reinforcement Learning Explains YouTube Commenting Behavior","date":"2019-10-24","arxiv_id":"1910.11703","repositories_listed":2,"syntology":null},{"url":"/paper/learning-q-network-for-active-information","slug":"learning-q-network-for-active-information","title":"Learning Q-network for Active Information Acquisition","date":"2019-10-23","arxiv_id":"1910.10754","repositories_listed":2,"syntology":null},{"url":"/paper/robust-domain-randomization-for-reinforcement","slug":"robust-domain-randomization-for-reinforcement","title":"Robust Visual Domain Randomization for Reinforcement Learning","date":"2019-10-23","arxiv_id":"1910.10537","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/robust-domain-randomization-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1910.10537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10537"}},"official":{"repos":["IndustAI/visual-domain-randomization","uncharted-technologies/robust-domain-randomization"],"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/regularization-matters-in-policy-optimization-1","slug":"regularization-matters-in-policy-optimization-1","title":"Regularization Matters in Policy Optimization","date":"2019-10-21","arxiv_id":"1910.09191","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/regularization-matters-in-policy-optimization-1#ran","syntology_url":"https://syntology.ai/paper/1910.09191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09191"}},"official":{"repos":["xuanlinli17/iclr2021_rlreg","xuanlinli17/po-rl-regularization"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/towards-a-reinforcement-learning-environment","slug":"towards-a-reinforcement-learning-environment","title":"Towards a Reinforcement Learning Environment Toolbox for Intelligent Electric Motor Control","date":"2019-10-21","arxiv_id":"1910.09434","repositories_listed":2,"syntology":null},{"url":"/paper/policy-learning-for-malaria-control","slug":"policy-learning-for-malaria-control","title":"Policy Learning for Malaria Control","date":"2019-10-20","arxiv_id":"1910.08926","repositories_listed":2,"syntology":null},{"url":"/paper/on-learning-paradigms-for-the-travelling","slug":"on-learning-paradigms-for-the-travelling","title":"On Learning Paradigms for the Travelling Salesman Problem","date":"2019-10-16","arxiv_id":"1910.07210","repositories_listed":2,"syntology":null},{"url":"/paper/reinforcement-learning-for-robotic","slug":"reinforcement-learning-for-robotic","title":"Reinforcement Learning for Robotic Manipulation using Simulated Locomotion Demonstrations","date":"2019-10-16","arxiv_id":"1910.07294","repositories_listed":2,"syntology":null},{"url":"/paper/multipolar-multi-source-policy-aggregation","slug":"multipolar-multi-source-policy-aggregation","title":"MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics","date":"2019-09-28","arxiv_id":"1909.13111","repositories_listed":2,"syntology":null},{"url":"/paper/deep-coordination-graphs","slug":"deep-coordination-graphs","title":"Deep Coordination Graphs","date":"2019-09-27","arxiv_id":"1910.00091","repositories_listed":2,"syntology":null},{"url":"/paper/improving-sat-solver-heuristics-with-graph","slug":"improving-sat-solver-heuristics-with-graph","title":"Can $Q$-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?","date":"2019-09-26","arxiv_id":"1909.11830","repositories_listed":2,"syntology":null},{"url":"/paper/data-valuation-using-reinforcement-learning","slug":"data-valuation-using-reinforcement-learning","title":"Data Valuation using Reinforcement Learning","date":"2019-09-25","arxiv_id":"1909.11671","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":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/data-valuation-using-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1909.11671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11671"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/modular-deep-reinforcement-learning-with","slug":"modular-deep-reinforcement-learning-with","title":"Modular Deep Reinforcement Learning with Temporal Logic Specifications","date":"2019-09-23","arxiv_id":"1909.11591","repositories_listed":2,"syntology":null},{"url":"/paper/driving-in-dense-traffic-with-model-free","slug":"driving-in-dense-traffic-with-model-free","title":"Driving in Dense Traffic with Model-Free Reinforcement Learning","date":"2019-09-15","arxiv_id":"1909.06710","repositories_listed":2,"syntology":null},{"url":"/paper/flight-controller-synthesis-via-deep","slug":"flight-controller-synthesis-via-deep","title":"Flight Controller Synthesis Via Deep Reinforcement Learning","date":"2019-09-14","arxiv_id":"1909.06493","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reinforcement-learning-algorithm-for","slug":"deep-reinforcement-learning-algorithm-for","title":"Deep Reinforcement Learning Algorithm for Dynamic Pricing of Express Lanes with Multiple Access Locations","date":"2019-09-10","arxiv_id":"1909.04760","repositories_listed":2,"syntology":null},{"url":"/paper/exploratory-combinatorial-optimization-with","slug":"exploratory-combinatorial-optimization-with","title":"Exploratory Combinatorial Optimization with Reinforcement Learning","date":"2019-09-09","arxiv_id":"1909.04063","repositories_listed":2,"syntology":{"n":20,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/exploratory-combinatorial-optimization-with#ran","syntology_url":"https://syntology.ai/paper/1909.04063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04063"}},"official":{"repos":["tomdbar/eco-dqn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-reinforcement-learning-for-control-of","slug":"deep-reinforcement-learning-for-control-of","title":"Deep Reinforcement Learning for Control of Probabilistic Boolean Networks","date":"2019-09-07","arxiv_id":"1909.03331","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-communication-in-multi-agent","slug":"efficient-communication-in-multi-agent","title":"Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control","date":"2019-09-06","arxiv_id":"1909.02682","repositories_listed":2,"syntology":null},{"url":"/paper/classification-with-costly-features-as-a","slug":"classification-with-costly-features-as-a","title":"Classification with Costly Features as a Sequential Decision-Making Problem","date":"2019-09-05","arxiv_id":"1909.02564","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/classification-with-costly-features-as-a#ran","syntology_url":"https://syntology.ai/paper/1909.02564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02564"}},"official":{"repos":["jaromiru/cwcf"],"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/answers-unite-unsupervised-metrics-for","slug":"answers-unite-unsupervised-metrics-for","title":"Answers Unite! Unsupervised Metrics for Reinforced Summarization Models","date":"2019-09-04","arxiv_id":"1909.01610","repositories_listed":2,"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/answers-unite-unsupervised-metrics-for#ran","syntology_url":"https://syntology.ai/paper/1909.01610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01610"}},"official":{"repos":["recitalAI/summa-qa"],"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/learning-dynamic-context-augmentation-for","slug":"learning-dynamic-context-augmentation-for","title":"Learning Dynamic Context Augmentation for Global Entity Linking","date":"2019-09-04","arxiv_id":"1909.02117","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":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/learning-dynamic-context-augmentation-for#ran","syntology_url":"https://syntology.ai/paper/1909.02117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02117"}},"official":{"repos":["YoungXiyuan/DCA"],"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/better-rewards-yield-better-summaries","slug":"better-rewards-yield-better-summaries","title":"Better Rewards Yield Better Summaries: Learning to Summarise Without References","date":"2019-09-03","arxiv_id":"1909.01214","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/better-rewards-yield-better-summaries#ran","syntology_url":"https://syntology.ai/paper/1909.01214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01214"}},"official":{"repos":["yg211/summary-reward-no-reference"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dynamics-aware-embeddings","slug":"dynamics-aware-embeddings","title":"Dynamics-aware Embeddings","date":"2019-08-25","arxiv_id":"1908.09357","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/dynamics-aware-embeddings#ran","syntology_url":"https://syntology.ai/paper/1908.09357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09357"}},"official":{"repos":["dyne-submission/dynamics-aware-embeddings"],"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/vusfavariational-universal-successor-features","slug":"vusfavariational-universal-successor-features","title":"VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation","date":"2019-08-18","arxiv_id":"1908.06376","repositories_listed":2,"syntology":null},{"url":"/paper/performing-deep-recurrent-double-q-learning","slug":"performing-deep-recurrent-double-q-learning","title":"Performing Deep Recurrent Double Q-Learning for Atari Games","date":"2019-08-16","arxiv_id":"1908.06040","repositories_listed":2,"syntology":null},{"url":"/paper/reinforcement-learning-based-interconnection","slug":"reinforcement-learning-based-interconnection","title":"Reinforcement Learning based Interconnection Routing for Adaptive Traffic Optimization","date":"2019-08-13","arxiv_id":"1908.04484","repositories_listed":2,"syntology":null},{"url":"/paper/arena-a-toolkit-for-multi-agent-reinforcement","slug":"arena-a-toolkit-for-multi-agent-reinforcement","title":"Arena: a toolkit for Multi-Agent Reinforcement Learning","date":"2019-07-20","arxiv_id":"1907.09467","repositories_listed":2,"syntology":null},{"url":"/paper/gpu-accelerated-atari-emulation-for","slug":"gpu-accelerated-atari-emulation-for","title":"Accelerating Reinforcement Learning through GPU Atari Emulation","date":"2019-07-19","arxiv_id":"1907.08467","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/gpu-accelerated-atari-emulation-for#ran","syntology_url":"https://syntology.ai/paper/1907.08467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.08467"}},"official":{"repos":["NVLABs/cule"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/provably-efficient-reinforcement-learning","slug":"provably-efficient-reinforcement-learning","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","date":"2019-07-11","arxiv_id":"1907.05388","repositories_listed":2,"syntology":null},{"url":"/paper/ranking-based-reward-extrapolation-without","slug":"ranking-based-reward-extrapolation-without","title":"Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations","date":"2019-07-09","arxiv_id":"1907.03976","repositories_listed":2,"syntology":null}],"record_sha256":"b7409fc3c7798b1bb76ee208adcd99351ddd08e0386f02ff8ce34f47ce5ae87d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}