{"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/8","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":8,"pages_in_order":132,"rows_per_page":100,"rows":[701,800],"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/7","next":"/task/reinforcement-learning/papers/9","papers":[{"url":"/paper/audio-visual-embodied-navigation","slug":"audio-visual-embodied-navigation","title":"SoundSpaces: Audio-Visual Navigation in 3D Environments","date":"2019-12-24","arxiv_id":"1912.11474","repositories_listed":2,"syntology":null},{"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/reinforced-feature-points-optimizing-feature","slug":"reinforced-feature-points-optimizing-feature","title":"Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task","date":"2019-12-02","arxiv_id":"1912.00623","repositories_listed":2,"syntology":null},{"url":"/paper/affect-based-intrinsic-rewards-for-learning","slug":"affect-based-intrinsic-rewards-for-learning","title":"Modeling Affect-based Intrinsic Rewards for Exploration and Learning","date":"2019-12-01","arxiv_id":"1912.00403","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/learning-fairness-in-multi-agent-systems","slug":"learning-fairness-in-multi-agent-systems","title":"Learning Fairness in Multi-Agent Systems","date":"2019-10-31","arxiv_id":"1910.14472","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/teacher-algorithms-for-curriculum-learning-of","slug":"teacher-algorithms-for-curriculum-learning-of","title":"Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments","date":"2019-10-16","arxiv_id":"1910.07224","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/teacher-algorithms-for-curriculum-learning-of#ran","syntology_url":"https://syntology.ai/paper/1910.07224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07224"}},"official":{"repos":["flowersteam/teachDeepRL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/seed-rl-scalable-and-efficient-deep-rl-with-1","slug":"seed-rl-scalable-and-efficient-deep-rl-with-1","title":"SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference","date":"2019-10-15","arxiv_id":"1910.06591","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seed-rl-scalable-and-efficient-deep-rl-with-1#ran","syntology_url":"https://syntology.ai/paper/1910.06591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06591"}},"official":{"repos":["google-research/seed_rl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-q-learning","slug":"meta-q-learning","title":"Meta-Q-Learning","date":"2019-09-30","arxiv_id":"1910.00125","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-q-learning#ran","syntology_url":"https://syntology.ai/paper/1910.00125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00125"}},"official":{"repos":["amazon-research/meta-q-learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/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/rlbench-the-robot-learning-benchmark-learning","slug":"rlbench-the-robot-learning-benchmark-learning","title":"RLBench: The Robot Learning Benchmark & Learning Environment","date":"2019-09-26","arxiv_id":"1909.12271","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/rlbench-the-robot-learning-benchmark-learning#ran","syntology_url":"https://syntology.ai/paper/1909.12271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.12271"}},"official":{"repos":["stepjam/RLBench"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"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/learning-controls-using-cross-modal","slug":"learning-controls-using-cross-modal","title":"Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations","date":"2019-09-16","arxiv_id":"1909.06993","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/collaborative-policy-learning-for-open","slug":"collaborative-policy-learning-for-open","title":"Collaborative Policy Learning for Open Knowledge Graph Reasoning","date":"2019-08-31","arxiv_id":"1909.00230","repositories_listed":2,"syntology":null},{"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/genesis-generative-scene-inference-and","slug":"genesis-generative-scene-inference-and","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","date":"2019-07-30","arxiv_id":"1907.13052","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/rethink-global-reward-game-and-credit","slug":"rethink-global-reward-game-and-credit","title":"Shapley Q-value: A Local Reward Approach to Solve Global Reward Games","date":"2019-07-11","arxiv_id":"1907.05707","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/rethink-global-reward-game-and-credit#ran","syntology_url":"https://syntology.ai/paper/1907.05707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05707"}},"official":{"repos":["hsvgbkhgbv/SQDDPG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-policy-improvement-with-soft-baseline","slug":"safe-policy-improvement-with-soft-baseline","title":"Safe Policy Improvement with Soft Baseline Bootstrapping","date":"2019-07-11","arxiv_id":"1907.05079","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-policy-improvement-with-soft-baseline#ran","syntology_url":"https://syntology.ai/paper/1907.05079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05079"}},"official":{"repos":["RomainLaroche/SPIBB","rems75/SPIBB-DQN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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},{"url":"/paper/deep-active-inference-as-variational-policy","slug":"deep-active-inference-as-variational-policy","title":"Deep Active Inference as Variational Policy Gradients","date":"2019-07-08","arxiv_id":"1907.03876","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-model-based-reinforcement","slug":"benchmarking-model-based-reinforcement","title":"Benchmarking Model-Based Reinforcement Learning","date":"2019-07-03","arxiv_id":"1907.02057","repositories_listed":2,"syntology":null},{"url":"/paper/playing-adaptively-against-stealthy-opponents","slug":"playing-adaptively-against-stealthy-opponents","title":"QFlip: An Adaptive Reinforcement Learning Strategy for the FlipIt Security Game","date":"2019-06-27","arxiv_id":"1906.11938","repositories_listed":2,"syntology":null},{"url":"/paper/monte-carlo-gradient-estimation-in-machine","slug":"monte-carlo-gradient-estimation-in-machine","title":"Monte Carlo Gradient Estimation in Machine Learning","date":"2019-06-25","arxiv_id":"1906.10652","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/monte-carlo-gradient-estimation-in-machine#ran","syntology_url":"https://syntology.ai/paper/1906.10652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10652"}},"official":{"repos":["deepmind/mc_gradients"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/modern-deep-reinforcement-learning-algorithms","slug":"modern-deep-reinforcement-learning-algorithms","title":"Modern Deep Reinforcement Learning Algorithms","date":"2019-06-24","arxiv_id":"1906.10025","repositories_listed":2,"syntology":null},{"url":"/paper/explainable-knowledge-graph-based","slug":"explainable-knowledge-graph-based","title":"Ekar: An Explainable Method for Knowledge Aware Recommendation","date":"2019-06-22","arxiv_id":"1906.09506","repositories_listed":2,"syntology":null},{"url":"/paper/language-as-an-abstraction-for-hierarchical","slug":"language-as-an-abstraction-for-hierarchical","title":"Language as an Abstraction for Hierarchical Deep Reinforcement Learning","date":"2019-06-18","arxiv_id":"1906.07343","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/language-as-an-abstraction-for-hierarchical#ran","syntology_url":"https://syntology.ai/paper/1906.07343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.07343"}},"official":{"repos":["google-research/clevr_robot_env"],"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/moet-interpretable-and-verifiable","slug":"moet-interpretable-and-verifiable","title":"MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning","date":"2019-06-16","arxiv_id":"1906.06717","repositories_listed":2,"syntology":null},{"url":"/paper/cross-view-policy-learning-for-street","slug":"cross-view-policy-learning-for-street","title":"Cross-View Policy Learning for Street Navigation","date":"2019-06-13","arxiv_id":"1906.05930","repositories_listed":2,"syntology":null},{"url":"/paper/when-to-use-parametric-models-in","slug":"when-to-use-parametric-models-in","title":"When to use parametric models in reinforcement learning?","date":"2019-06-12","arxiv_id":"1906.05243","repositories_listed":2,"syntology":null},{"url":"/paper/importance-resampling-for-off-policy","slug":"importance-resampling-for-off-policy","title":"Importance Resampling for Off-policy Prediction","date":"2019-06-11","arxiv_id":"1906.04328","repositories_listed":2,"syntology":null},{"url":"/paper/dualdice-behavior-agnostic-estimation-of","slug":"dualdice-behavior-agnostic-estimation-of","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","date":"2019-06-10","arxiv_id":"1906.04733","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-exploration-via-disagreement","slug":"self-supervised-exploration-via-disagreement","title":"Self-Supervised Exploration via Disagreement","date":"2019-06-10","arxiv_id":"1906.04161","repositories_listed":2,"syntology":null},{"url":"/paper/intrinsically-efficient-stable-and-bounded","slug":"intrinsically-efficient-stable-and-bounded","title":"Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning","date":"2019-06-09","arxiv_id":"1906.03735","repositories_listed":2,"syntology":null},{"url":"/paper/190600572","slug":"190600572","title":"Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning","date":"2019-06-03","arxiv_id":"1906.00572","repositories_listed":2,"syntology":null},{"url":"/paper/molecularrnn-generating-realistic-molecular","slug":"molecularrnn-generating-realistic-molecular","title":"MolecularRNN: Generating realistic molecular graphs with optimized properties","date":"2019-05-31","arxiv_id":"1905.13372","repositories_listed":2,"syntology":null},{"url":"/paper/solving-np-hard-problems-on-graphs-by","slug":"solving-np-hard-problems-on-graphs-by","title":"Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero","date":"2019-05-28","arxiv_id":"1905.11623","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/solving-np-hard-problems-on-graphs-by#ran","syntology_url":"https://syntology.ai/paper/1905.11623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11623"}},"official":null}},{"url":"/paper/uncertainty-based-continual-learning-with","slug":"uncertainty-based-continual-learning-with","title":"Uncertainty-based Continual Learning with Adaptive Regularization","date":"2019-05-28","arxiv_id":"1905.11614","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/uncertainty-based-continual-learning-with#ran","syntology_url":"https://syntology.ai/paper/1905.11614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11614"}},"official":{"repos":["csm9493/UCL"],"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/explainable-reinforcement-learning-through-a","slug":"explainable-reinforcement-learning-through-a","title":"Explainable Reinforcement Learning Through a Causal Lens","date":"2019-05-27","arxiv_id":"1905.10958","repositories_listed":2,"syntology":null},{"url":"/paper/interactive-differentiable-simulation","slug":"interactive-differentiable-simulation","title":"Interactive Differentiable Simulation","date":"2019-05-26","arxiv_id":"1905.10706","repositories_listed":2,"syntology":null},{"url":"/paper/adversarial-policies-attacking-deep","slug":"adversarial-policies-attacking-deep","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","date":"2019-05-25","arxiv_id":"1905.10615","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":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) · 3 unverified","sample_list":"/paper/adversarial-policies-attacking-deep#ran","syntology_url":"https://syntology.ai/paper/1905.10615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.10615"}},"official":{"repos":["HumanCompatibleAI/adversarial-policies"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-dual-reinforcement-learning-framework-for","slug":"a-dual-reinforcement-learning-framework-for","title":"A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer","date":"2019-05-24","arxiv_id":"1905.10060","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/a-dual-reinforcement-learning-framework-for#ran","syntology_url":"https://syntology.ai/paper/1905.10060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.10060"}},"official":{"repos":["luofuli/DualLanST"],"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/continual-reinforcement-learning-in-3d-non","slug":"continual-reinforcement-learning-in-3d-non","title":"Continual Reinforcement Learning in 3D Non-stationary Environments","date":"2019-05-24","arxiv_id":"1905.10112","repositories_listed":2,"syntology":null},{"url":"/paper/estimating-risk-and-uncertainty-in-deep","slug":"estimating-risk-and-uncertainty-in-deep","title":"Estimating Risk and Uncertainty in Deep Reinforcement Learning","date":"2019-05-23","arxiv_id":"1905.09638","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/estimating-risk-and-uncertainty-in-deep#ran","syntology_url":"https://syntology.ai/paper/1905.09638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09638"}},"official":{"repos":["IndustAI/risk-and-uncertainty"],"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/inverse-reinforcement-learning-in-contextual","slug":"inverse-reinforcement-learning-in-contextual","title":"Inverse Reinforcement Learning in Contextual MDPs","date":"2019-05-23","arxiv_id":"1905.09710","repositories_listed":2,"syntology":null},{"url":"/paper/cobra-data-efficient-model-based-rl-through","slug":"cobra-data-efficient-model-based-rl-through","title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","date":"2019-05-22","arxiv_id":"1905.09275","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cobra-data-efficient-model-based-rl-through#ran","syntology_url":"https://syntology.ai/paper/1905.09275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09275"}},"official":{"repos":["deepmind/spriteworld"],"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/arena-a-general-evaluation-platform-and","slug":"arena-a-general-evaluation-platform-and","title":"Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence","date":"2019-05-17","arxiv_id":"1905.08085","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/arena-a-general-evaluation-platform-and#ran","syntology_url":"https://syntology.ai/paper/1905.08085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08085"}},"official":{"repos":["YuhangSong/Arena-Baselines","YuhangSong/Arena-BuildingToolkit"],"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/meta-reinforcement-learning-with-task","slug":"meta-reinforcement-learning-with-task","title":"Meta Reinforcement Learning with Task Embedding and Shared Policy","date":"2019-05-16","arxiv_id":"1905.06527","repositories_listed":2,"syntology":null},{"url":"/paper/random-expert-distillation-imitation-learning","slug":"random-expert-distillation-imitation-learning","title":"Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation","date":"2019-05-16","arxiv_id":"1905.06750","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/random-expert-distillation-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1905.06750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.06750"}},"official":{"repos":["RuohanW/RED"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/trajectory-based-off-policy-deep","slug":"trajectory-based-off-policy-deep","title":"Trajectory-Based Off-Policy Deep Reinforcement Learning","date":"2019-05-14","arxiv_id":"1905.05710","repositories_listed":2,"syntology":null},{"url":"/paper/second-order-value-iteration-in-reinforcement","slug":"second-order-value-iteration-in-reinforcement","title":"Generalized Second Order Value Iteration in Markov Decision Processes","date":"2019-05-10","arxiv_id":"1905.03927","repositories_listed":2,"syntology":null},{"url":"/paper/toybox-a-suite-of-environments-for","slug":"toybox-a-suite-of-environments-for","title":"Toybox: A Suite of Environments for Experimental Evaluation of Deep Reinforcement Learning","date":"2019-05-07","arxiv_id":"1905.02825","repositories_listed":2,"syntology":null},{"url":"/paper/scaling-and-benchmarking-self-supervised","slug":"scaling-and-benchmarking-self-supervised","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","date":"2019-05-03","arxiv_id":"1905.01235","repositories_listed":2,"syntology":null},{"url":"/paper/synthesis-of-biologically-realistic-human","slug":"synthesis-of-biologically-realistic-human","title":"Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation","date":"2019-04-30","arxiv_id":"1904.13041","repositories_listed":2,"syntology":null},{"url":"/paper/rl-gan-net-a-reinforcement-learning-agent","slug":"rl-gan-net-a-reinforcement-learning-agent","title":"RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion","date":"2019-04-28","arxiv_id":"1904.12304","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rl-gan-net-a-reinforcement-learning-agent#ran","syntology_url":"https://syntology.ai/paper/1904.12304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12304"}},"official":null}},{"url":"/paper/faster-and-more-accurate-learning-with-meta","slug":"faster-and-more-accurate-learning-with-meta","title":"META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation","date":"2019-04-25","arxiv_id":"1904.11439","repositories_listed":2,"syntology":{"n":14,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":11,"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) · 11 unverified","sample_list":"/paper/faster-and-more-accurate-learning-with-meta#ran","syntology_url":"https://syntology.ai/paper/1904.11439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11439"}},"official":{"repos":["PwnerHarry/META","PwnerHarry/MTA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-with-scene","slug":"safe-reinforcement-learning-with-scene","title":"Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments","date":"2019-04-25","arxiv_id":"1904.11483","repositories_listed":2,"syntology":null},{"url":"/paper/machine-learning-for-long-distance-quantum","slug":"machine-learning-for-long-distance-quantum","title":"Machine learning for long-distance quantum communication","date":"2019-04-24","arxiv_id":"1904.10797","repositories_listed":2,"syntology":null},{"url":"/paper/baconian-a-unified-opensource-framework-for","slug":"baconian-a-unified-opensource-framework-for","title":"Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning","date":"2019-04-23","arxiv_id":"1904.10762","repositories_listed":2,"syntology":null},{"url":"/paper/model-free-deep-reinforcement-learning-for","slug":"model-free-deep-reinforcement-learning-for","title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","date":"2019-04-20","arxiv_id":"1904.09503","repositories_listed":2,"syntology":null},{"url":"/paper/rogue-gym-a-new-challenge-for-generalization","slug":"rogue-gym-a-new-challenge-for-generalization","title":"Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning","date":"2019-04-17","arxiv_id":"1904.08129","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/rogue-gym-a-new-challenge-for-generalization#ran","syntology_url":"https://syntology.ai/paper/1904.08129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08129"}},"official":{"repos":["kngwyu/rogue-gym","kngwyu/rogue-gym-agents-cog19"],"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/a-solution-for-dynamic-spectrum-management-in","slug":"a-solution-for-dynamic-spectrum-management-in","title":"A Solution for Dynamic Spectrum Management in Mission-Critical UAV Networks","date":"2019-04-16","arxiv_id":"1904.07380","repositories_listed":2,"syntology":null}],"record_sha256":"71659f8c5260454195341a2dcd0bf611df2eb89dca25cbfdd16bdc7b873aaac8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}