{"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/44","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":44,"pages_in_order":152,"rows_per_page":100,"rows":[4301,4400],"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/43","next":"/task/reinforcement-learning-1/papers/45","papers":[{"url":"/paper/reinforcement-learning-with-dynamic-boltzmann","slug":"reinforcement-learning-with-dynamic-boltzmann","title":"Reinforcement Learning with Dynamic Boltzmann Softmax Updates","date":"2019-03-14","arxiv_id":"1903.05926","repositories_listed":1,"syntology":null},{"url":"/paper/coacor-code-annotation-for-code-retrieval","slug":"coacor-code-annotation-for-code-retrieval","title":"CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning","date":"2019-03-13","arxiv_id":"1904.00720","repositories_listed":1,"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/coacor-code-annotation-for-code-retrieval#ran","syntology_url":"https://syntology.ai/paper/1904.00720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00720"}},"official":{"repos":["LittleYUYU/CoaCor"],"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/vrkitchen-an-interactive-3d-virtual","slug":"vrkitchen-an-interactive-3d-virtual","title":"VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning","date":"2019-03-13","arxiv_id":"1903.05757","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-reinforcement-learning-with-expert","slug":"hybrid-reinforcement-learning-with-expert","title":"Hybrid Reinforcement Learning with Expert State Sequences","date":"2019-03-11","arxiv_id":"1903.04110","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hybrid-reinforcement-learning-with-expert#ran","syntology_url":"https://syntology.ai/paper/1903.04110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04110"}},"official":{"repos":["XiaoxiaoGuo/tensor4rl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-agent-deep-reinforcement-learning-for-2","slug":"multi-agent-deep-reinforcement-learning-for-2","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","date":"2019-03-11","arxiv_id":"1903.04527","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-agent-deep-reinforcement-learning-for-2#ran","syntology_url":"https://syntology.ai/paper/1903.04527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04527"}},"official":{"repos":["cts198859/deeprl_signal_control"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-model-free-reinforcement","slug":"sample-efficient-model-free-reinforcement","title":"Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics","date":"2019-03-11","arxiv_id":"1903.04193","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-power-system-emergency-control-using","slug":"adaptive-power-system-emergency-control-using","title":"Adaptive Power System Emergency Control using Deep Reinforcement Learning","date":"2019-03-09","arxiv_id":"1903.03712","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-power-system-emergency-control-using#ran","syntology_url":"https://syntology.ai/paper/1903.03712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03712"}},"official":{"repos":["RLGC-Project/RLGC"],"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":["official"]}}},{"url":"/paper/concurrent-meta-reinforcement-learning","slug":"concurrent-meta-reinforcement-learning","title":"Concurrent Meta Reinforcement Learning","date":"2019-03-07","arxiv_id":"1903.02710","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-research-trends-from-arxiv","slug":"predicting-research-trends-from-arxiv","title":"Predicting Research Trends From Arxiv","date":"2019-03-07","arxiv_id":"1903.02831","repositories_listed":1,"syntology":null},{"url":"/paper/a-hitchhiker-s-guide-to-statistical","slug":"a-hitchhiker-s-guide-to-statistical","title":"A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms","date":"2019-03-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/simple-rl-reproducible-reinforcement-learning","slug":"simple-rl-reproducible-reinforcement-learning","title":"simple_rl: Reproducible Reinforcement Learning in Python","date":"2019-03-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/using-natural-language-for-reward-shaping-in","slug":"using-natural-language-for-reward-shaping-in","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","date":"2019-03-05","arxiv_id":"1903.02020","repositories_listed":1,"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/using-natural-language-for-reward-shaping-in#ran","syntology_url":"https://syntology.ai/paper/1903.02020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.02020"}},"official":null}},{"url":"/paper/viewpoint-optimization-for-autonomous","slug":"viewpoint-optimization-for-autonomous","title":"Viewpoint Optimization for Autonomous Strawberry Harvesting with Deep Reinforcement Learning","date":"2019-03-05","arxiv_id":"1903.02074","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-actor-critic-reinforcement-learning-in","slug":"hybrid-actor-critic-reinforcement-learning-in","title":"Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space","date":"2019-03-04","arxiv_id":"1903.01344","repositories_listed":1,"syntology":null},{"url":"/paper/model-primitive-hierarchical-lifelong","slug":"model-primitive-hierarchical-lifelong","title":"Model Primitive Hierarchical Lifelong Reinforcement Learning","date":"2019-03-04","arxiv_id":"1903.01567","repositories_listed":1,"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/model-primitive-hierarchical-lifelong#ran","syntology_url":"https://syntology.ai/paper/1903.01567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.01567"}},"official":{"repos":["sisl/MPHRL"],"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/norml-no-reward-meta-learning","slug":"norml-no-reward-meta-learning","title":"NoRML: No-Reward Meta Learning","date":"2019-03-04","arxiv_id":"1903.01063","repositories_listed":1,"syntology":null},{"url":"/paper/asynchronous-episodic-deep-deterministic","slug":"asynchronous-episodic-deep-deterministic","title":"Asynchronous Episodic Deep Deterministic Policy Gradient: Towards Continuous Control in Computationally Complex Environments","date":"2019-03-03","arxiv_id":"1903.00827","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-up-budgeted-reinforcement-learning","slug":"scaling-up-budgeted-reinforcement-learning","title":"Budgeted Reinforcement Learning in Continuous State Space","date":"2019-03-03","arxiv_id":"1903.01004","repositories_listed":1,"syntology":null},{"url":"/paper/a-cooperative-multi-agent-reinforcement","slug":"a-cooperative-multi-agent-reinforcement","title":"A Cooperative Multi-Agent Reinforcement Learning Framework for Resource Balancing in Complex Logistics Network","date":"2019-03-02","arxiv_id":"1903.00714","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-reinforcement-learning-with-a-mind","slug":"efficient-reinforcement-learning-with-a-mind","title":"Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning","date":"2019-03-02","arxiv_id":"1903.00715","repositories_listed":1,"syntology":null},{"url":"/paper/regularity-normalization-constraining","slug":"regularity-normalization-constraining","title":"Unsupervised Attention Mechanism across Neural Network Layers","date":"2019-02-27","arxiv_id":"1902.10658","repositories_listed":1,"syntology":null},{"url":"/paper/diagnosing-bottlenecks-in-deep-q-learning","slug":"diagnosing-bottlenecks-in-deep-q-learning","title":"Diagnosing Bottlenecks in Deep Q-learning Algorithms","date":"2019-02-26","arxiv_id":"1902.10250","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diagnosing-bottlenecks-in-deep-q-learning#ran","syntology_url":"https://syntology.ai/paper/1902.10250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.10250"}},"official":null}},{"url":"/paper/flappy-hummingbird-an-open-source-dynamic","slug":"flappy-hummingbird-an-open-source-dynamic","title":"Flappy Hummingbird: An Open Source Dynamic Simulation of Flapping Wing Robots and Animals","date":"2019-02-25","arxiv_id":"1902.09628","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-framework-for-structured-learning","slug":"a-general-framework-for-structured-learning","title":"A General Framework for Structured Learning of Mechanical Systems","date":"2019-02-22","arxiv_id":"1902.08705","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-general-framework-for-structured-learning#ran","syntology_url":"https://syntology.ai/paper/1902.08705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.08705"}},"official":{"repos":["sisl/mechamodlearn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-confidence-regions-tight-bayesian","slug":"beyond-confidence-regions-tight-bayesian","title":"Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs","date":"2019-02-20","arxiv_id":"1902.07605","repositories_listed":1,"syntology":null},{"url":"/paper/dom-q-net-grounded-rl-on-structured-language","slug":"dom-q-net-grounded-rl-on-structured-language","title":"DOM-Q-NET: Grounded RL on Structured Language","date":"2019-02-19","arxiv_id":"1902.07257","repositories_listed":1,"syntology":null},{"url":"/paper/hyperbolic-discounting-and-learning-over","slug":"hyperbolic-discounting-and-learning-over","title":"Hyperbolic Discounting and Learning over Multiple Horizons","date":"2019-02-19","arxiv_id":"1902.06865","repositories_listed":1,"syntology":null},{"url":"/paper/heuristics-answer-set-programming-and-markov","slug":"heuristics-answer-set-programming-and-markov","title":"Heuristics, Answer Set Programming and Markov Decision Process for Solving a Set of Spatial Puzzles","date":"2019-02-16","arxiv_id":"1903.03411","repositories_listed":1,"syntology":null},{"url":"/paper/prolonets-neural-encoding-human-experts","slug":"prolonets-neural-encoding-human-experts","title":"Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning","date":"2019-02-15","arxiv_id":"1902.06007","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-visuomotor-control-through","slug":"unsupervised-visuomotor-control-through","title":"Unsupervised Visuomotor Control through Distributional Planning Networks","date":"2019-02-14","arxiv_id":"1902.05542","repositories_listed":1,"syntology":null},{"url":"/paper/verifiably-safe-off-model-reinforcement","slug":"verifiably-safe-off-model-reinforcement","title":"Verifiably Safe Off-Model Reinforcement Learning","date":"2019-02-14","arxiv_id":"1902.05632","repositories_listed":1,"syntology":null},{"url":"/paper/preferences-implicit-in-the-state-of-the","slug":"preferences-implicit-in-the-state-of-the","title":"Preferences Implicit in the State of the World","date":"2019-02-12","arxiv_id":"1902.04198","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/preferences-implicit-in-the-state-of-the#ran","syntology_url":"https://syntology.ai/paper/1902.04198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04198"}},"official":{"repos":["HumanCompatibleAI/rlsp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/generalization-through-simulation-integrating","slug":"generalization-through-simulation-integrating","title":"Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight","date":"2019-02-11","arxiv_id":"1902.03701","repositories_listed":1,"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/generalization-through-simulation-integrating#ran","syntology_url":"https://syntology.ai/paper/1902.03701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.03701"}},"official":{"repos":["gkahn13/GtS"],"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/novelty-search-for-deep-reinforcement","slug":"novelty-search-for-deep-reinforcement","title":"Novelty Search for Deep Reinforcement Learning Policy Network Weights by Action Sequence Edit Metric Distance","date":"2019-02-08","arxiv_id":"1902.03142","repositories_listed":1,"syntology":null},{"url":"/paper/artificial-intelligence-for-prosthetics","slug":"artificial-intelligence-for-prosthetics","title":"Artificial Intelligence for Prosthetics - challenge solutions","date":"2019-02-07","arxiv_id":"1902.02441","repositories_listed":1,"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/artificial-intelligence-for-prosthetics#ran","syntology_url":"https://syntology.ai/paper/1902.02441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.02441"}},"official":{"repos":["iasawseen/MultiServerRL"],"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/deeper-sparser-exploration","slug":"deeper-sparser-exploration","title":"Bayesian Reinforcement Learning via Deep, Sparse Sampling","date":"2019-02-07","arxiv_id":"1902.02661","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-schedule-communication-in-multi","slug":"learning-to-schedule-communication-in-multi","title":"Learning to Schedule Communication in Multi-agent Reinforcement Learning","date":"2019-02-05","arxiv_id":"1902.01554","repositories_listed":1,"syntology":null},{"url":"/paper/separating-value-functions-across-time-scales","slug":"separating-value-functions-across-time-scales","title":"Separating value functions across time-scales","date":"2019-02-05","arxiv_id":"1902.01883","repositories_listed":1,"syntology":null},{"url":"/paper/the-natural-language-of-actions","slug":"the-natural-language-of-actions","title":"The Natural Language of Actions","date":"2019-02-04","arxiv_id":"1902.01119","repositories_listed":1,"syntology":null},{"url":"/paper/a-meta-mdp-approach-to-exploration-for","slug":"a-meta-mdp-approach-to-exploration-for","title":"A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning","date":"2019-02-03","arxiv_id":"1902.00843","repositories_listed":1,"syntology":null},{"url":"/paper/certified-reinforcement-learning-with-logic","slug":"certified-reinforcement-learning-with-logic","title":"Certified Reinforcement Learning with Logic Guidance","date":"2019-02-02","arxiv_id":"1902.00778","repositories_listed":1,"syntology":null},{"url":"/paper/policy-consolidation-for-continual","slug":"policy-consolidation-for-continual","title":"Policy Consolidation for Continual Reinforcement Learning","date":"2019-02-01","arxiv_id":"1902.00255","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/policy-consolidation-for-continual#ran","syntology_url":"https://syntology.ai/paper/1902.00255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00255"}},"official":null}},{"url":"/paper/contrasting-exploration-in-parameter-and","slug":"contrasting-exploration-in-parameter-and","title":"Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective","date":"2019-01-31","arxiv_id":"1901.11503","repositories_listed":1,"syntology":null},{"url":"/paper/private-q-learning-with-functional-noise-in","slug":"private-q-learning-with-functional-noise-in","title":"Privacy-preserving Q-Learning with Functional Noise in Continuous State Spaces","date":"2019-01-30","arxiv_id":"1901.10634","repositories_listed":1,"syntology":null},{"url":"/paper/emergence-of-hierarchy-via-reinforcement","slug":"emergence-of-hierarchy-via-reinforcement","title":"Self-organization of action hierarchy and compositionality by reinforcement learning with recurrent neural networks","date":"2019-01-29","arxiv_id":"1901.10113","repositories_listed":1,"syntology":null},{"url":"/paper/safe-efficient-and-comfortable-velocity","slug":"safe-efficient-and-comfortable-velocity","title":"Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving","date":"2019-01-29","arxiv_id":"1902.00089","repositories_listed":1,"syntology":null},{"url":"/paper/emergent-linguistic-phenomena-in-multi-agent","slug":"emergent-linguistic-phenomena-in-multi-agent","title":"Emergent Linguistic Phenomena in Multi-Agent Communication Games","date":"2019-01-25","arxiv_id":"1901.08706","repositories_listed":1,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/emergent-linguistic-phenomena-in-multi-agent#ran","syntology_url":"https://syntology.ai/paper/1901.08706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08706"}},"official":{"repos":["lgraesser/MultimodalGame"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-measurement-scheduling-for-event","slug":"dynamic-measurement-scheduling-for-event","title":"Dynamic Measurement Scheduling for Event Forecasting using Deep RL","date":"2019-01-24","arxiv_id":"1901.09699","repositories_listed":1,"syntology":null},{"url":"/paper/causal-reasoning-from-meta-reinforcement","slug":"causal-reasoning-from-meta-reinforcement","title":"Causal Reasoning from Meta-reinforcement Learning","date":"2019-01-23","arxiv_id":"1901.08162","repositories_listed":1,"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/causal-reasoning-from-meta-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1901.08162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08162"}},"official":null}},{"url":"/paper/understanding-multi-step-deep-reinforcement","slug":"understanding-multi-step-deep-reinforcement","title":"Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target","date":"2019-01-22","arxiv_id":"1901.07510","repositories_listed":1,"syntology":null},{"url":"/paper/read-watch-and-move-reinforcement-learning","slug":"read-watch-and-move-reinforcement-learning","title":"Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos","date":"2019-01-21","arxiv_id":"1901.06829","repositories_listed":1,"syntology":null},{"url":"/paper/wall-e-an-efficient-reinforcement-learning","slug":"wall-e-an-efficient-reinforcement-learning","title":"WALL-E: An Efficient Reinforcement Learning Research Framework","date":"2019-01-18","arxiv_id":"1901.06086","repositories_listed":1,"syntology":null},{"url":"/paper/amplifying-the-imitation-effect-for","slug":"amplifying-the-imitation-effect-for","title":"Amplifying the Imitation Effect for Reinforcement Learning of UCAV's Mission Execution","date":"2019-01-17","arxiv_id":"1901.05856","repositories_listed":1,"syntology":null},{"url":"/paper/autophase-compiler-phase-ordering-for-high","slug":"autophase-compiler-phase-ordering-for-high","title":"AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement Learning","date":"2019-01-15","arxiv_id":"1901.04615","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-for-prosthetics-using","slug":"transfer-learning-for-prosthetics-using","title":"Transfer Learning for Prosthetics Using Imitation Learning","date":"2019-01-15","arxiv_id":"1901.04772","repositories_listed":1,"syntology":null},{"url":"/paper/improving-coordination-in-multi-agent-deep","slug":"improving-coordination-in-multi-agent-deep","title":"Improving Coordination in Small-Scale Multi-Agent Deep Reinforcement Learning through Memory-driven Communication","date":"2019-01-12","arxiv_id":"1901.03887","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-coordination-in-multi-agent-deep#ran","syntology_url":"https://syntology.ai/paper/1901.03887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.03887"}},"official":null}},{"url":"/paper/an-investigation-of-model-free-planning","slug":"an-investigation-of-model-free-planning","title":"An investigation of model-free planning","date":"2019-01-11","arxiv_id":"1901.03559","repositories_listed":1,"syntology":null},{"url":"/paper/self-learning-exploration-and-mapping-for","slug":"self-learning-exploration-and-mapping-for","title":"Self-Learning Exploration and Mapping for Mobile Robots via Deep Reinforcement Learning","date":"2019-01-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-reinforcement-learning-via","slug":"hierarchical-reinforcement-learning-via","title":"Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization","date":"2019-01-05","arxiv_id":"1901.01365","repositories_listed":1,"syntology":null},{"url":"/paper/generative-adversarial-user-model-for","slug":"generative-adversarial-user-model-for","title":"Generative Adversarial User Model for Reinforcement Learning Based Recommendation System","date":"2018-12-27","arxiv_id":"1812.10613","repositories_listed":1,"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/generative-adversarial-user-model-for#ran","syntology_url":"https://syntology.ai/paper/1812.10613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.10613"}},"official":{"repos":["xinshi-chen/GenerativeAdversarialUserModel"],"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/deconfounding-reinforcement-learning-in","slug":"deconfounding-reinforcement-learning-in","title":"Deconfounding Reinforcement Learning in Observational Settings","date":"2018-12-26","arxiv_id":"1812.10576","repositories_listed":1,"syntology":null},{"url":"/paper/iroko-a-framework-to-prototype-reinforcement","slug":"iroko-a-framework-to-prototype-reinforcement","title":"Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Control","date":"2018-12-24","arxiv_id":"1812.09975","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-with-non-expert-human","slug":"pre-training-with-non-expert-human","title":"Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning","date":"2018-12-21","arxiv_id":"1812.08904","repositories_listed":1,"syntology":null},{"url":"/paper/td-regularized-actor-critic-methods","slug":"td-regularized-actor-critic-methods","title":"TD-Regularized Actor-Critic Methods","date":"2018-12-19","arxiv_id":"1812.08288","repositories_listed":1,"syntology":null},{"url":"/paper/information-directed-exploration-for-deep","slug":"information-directed-exploration-for-deep","title":"Information-Directed Exploration for Deep Reinforcement Learning","date":"2018-12-18","arxiv_id":"1812.07544","repositories_listed":1,"syntology":null},{"url":"/paper/an-atari-model-zoo-for-analyzing-visualizing","slug":"an-atari-model-zoo-for-analyzing-visualizing","title":"An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents","date":"2018-12-17","arxiv_id":"1812.07069","repositories_listed":1,"syntology":null},{"url":"/paper/residual-policy-learning","slug":"residual-policy-learning","title":"Residual Policy Learning","date":"2018-12-15","arxiv_id":"1812.06298","repositories_listed":1,"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/residual-policy-learning#ran","syntology_url":"https://syntology.ai/paper/1812.06298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.06298"}},"official":null}},{"url":"/paper/simulation-to-scaled-city-zero-shot-policy","slug":"simulation-to-scaled-city-zero-shot-policy","title":"Simulation to Scaled City: Zero-Shot Policy Transfer for Traffic Control via Autonomous Vehicles","date":"2018-12-14","arxiv_id":"1812.06120","repositories_listed":1,"syntology":null},{"url":"/paper/exploration-conscious-reinforcement-learning","slug":"exploration-conscious-reinforcement-learning","title":"Exploration Conscious Reinforcement Learning Revisited","date":"2018-12-13","arxiv_id":"1812.05551","repositories_listed":1,"syntology":null},{"url":"/paper/irlas-inverse-reinforcement-learning-for","slug":"irlas-inverse-reinforcement-learning-for","title":"IRLAS: Inverse Reinforcement Learning for Architecture Search","date":"2018-12-13","arxiv_id":"1812.05285","repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-generation-from-imitation-learning","slug":"dialogue-generation-from-imitation-learning","title":"Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning","date":"2018-12-09","arxiv_id":"1812.03509","repositories_listed":1,"syntology":null},{"url":"/paper/pseudo-rehearsal-achieving-deep-reinforcement","slug":"pseudo-rehearsal-achieving-deep-reinforcement","title":"Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting","date":"2018-12-06","arxiv_id":"1812.02464","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-generalization-in-reinforcement","slug":"quantifying-generalization-in-reinforcement","title":"Quantifying Generalization in Reinforcement Learning","date":"2018-12-06","arxiv_id":"1812.02341","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/quantifying-generalization-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1812.02341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.02341"}},"official":{"repos":["openai/coinrun"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adapting-auxiliary-losses-using-gradient","slug":"adapting-auxiliary-losses-using-gradient","title":"Adapting Auxiliary Losses Using Gradient Similarity","date":"2018-12-05","arxiv_id":"1812.02224","repositories_listed":1,"syntology":null},{"url":"/paper/relative-entropy-regularized-policy-iteration","slug":"relative-entropy-regularized-policy-iteration","title":"Relative Entropy Regularized Policy Iteration","date":"2018-12-05","arxiv_id":"1812.02256","repositories_listed":1,"syntology":null},{"url":"/paper/playing-text-adventure-games-with-graph-based","slug":"playing-text-adventure-games-with-graph-based","title":"Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning","date":"2018-12-04","arxiv_id":"1812.01628","repositories_listed":1,"syntology":null},{"url":"/paper/towards-solving-text-based-games-by-producing","slug":"towards-solving-text-based-games-by-producing","title":"Towards Solving Text-based Games by Producing Adaptive Action Spaces","date":"2018-12-03","arxiv_id":"1812.00855","repositories_listed":1,"syntology":null},{"url":"/paper/visual-foresight-model-based-deep","slug":"visual-foresight-model-based-deep","title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","date":"2018-12-03","arxiv_id":"1812.00568","repositories_listed":1,"syntology":null},{"url":"/paper/macro-action-selection-with-deep","slug":"macro-action-selection-with-deep","title":"Macro action selection with deep reinforcement learning in StarCraft","date":"2018-12-02","arxiv_id":"1812.00336","repositories_listed":1,"syntology":null},{"url":"/paper/data-center-cooling-using-model-predictive","slug":"data-center-cooling-using-model-predictive","title":"Data center cooling using model-predictive control","date":"2018-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exponentially-weighted-imitation-learning-for","slug":"exponentially-weighted-imitation-learning-for","title":"Exponentially Weighted Imitation Learning for Batched Historical Data","date":"2018-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-curriculum-policies-for","slug":"learning-curriculum-policies-for","title":"Learning Curriculum Policies for Reinforcement Learning","date":"2018-12-01","arxiv_id":"1812.00285","repositories_listed":1,"syntology":null},{"url":"/paper/simple-random-search-of-static-linear","slug":"simple-random-search-of-static-linear","title":"Simple random search of static linear policies is competitive for reinforcement learning","date":"2018-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/temporal-regularization-for-markov-decision","slug":"temporal-regularization-for-markov-decision","title":"Temporal Regularization for Markov Decision Process","date":"2018-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-multi-agent-reinforcement-learning-with","slug":"deep-multi-agent-reinforcement-learning-with","title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs","date":"2018-11-30","arxiv_id":"1811.12557","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/deep-multi-agent-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/1811.12557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12557"}},"official":{"repos":["tegg89/magnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/modeling-natural-language-emergence-with","slug":"modeling-natural-language-emergence-with","title":"Modeling natural language emergence with integral transform theory and reinforcement learning","date":"2018-11-30","arxiv_id":"1812.01431","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-autonomous","slug":"deep-reinforcement-learning-for-autonomous","title":"Deep Reinforcement Learning for Autonomous Driving","date":"2018-11-28","arxiv_id":"1811.11329","repositories_listed":1,"syntology":null},{"url":"/paper/grammars-and-reinforcement-learning-for","slug":"grammars-and-reinforcement-learning-for","title":"Grammars and reinforcement learning for molecule optimization","date":"2018-11-27","arxiv_id":"1811.11222","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-impact-of-entropy-on-policy","slug":"understanding-the-impact-of-entropy-on-policy","title":"Understanding the impact of entropy on policy optimization","date":"2018-11-27","arxiv_id":"1811.11214","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/understanding-the-impact-of-entropy-on-policy#ran","syntology_url":"https://syntology.ai/paper/1811.11214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11214"}},"official":{"repos":["zafarali/emdp"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-for-uplift-modeling","slug":"reinforcement-learning-for-uplift-modeling","title":"Reinforcement Learning for Uplift Modeling","date":"2018-11-26","arxiv_id":"1811.10158","repositories_listed":1,"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/reinforcement-learning-for-uplift-modeling#ran","syntology_url":"https://syntology.ai/paper/1811.10158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.10158"}},"official":null}},{"url":"/paper/torchproteinlibrary-a-computationally","slug":"torchproteinlibrary-a-computationally","title":"TorchProteinLibrary: A computationally efficient, differentiable representation of protein structure","date":"2018-11-23","arxiv_id":"1812.01108","repositories_listed":1,"syntology":null},{"url":"/paper/urban-driving-with-multi-objective-deep","slug":"urban-driving-with-multi-objective-deep","title":"Urban Driving with Multi-Objective Deep Reinforcement Learning","date":"2018-11-21","arxiv_id":"1811.08586","repositories_listed":1,"syntology":null},{"url":"/paper/model-learning-for-look-ahead-exploration-in","slug":"model-learning-for-look-ahead-exploration-in","title":"Model Learning for Look-ahead Exploration in Continuous Control","date":"2018-11-20","arxiv_id":"1811.08086","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-of-active-vision-for","slug":"reinforcement-learning-of-active-vision-for","title":"Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions","date":"2018-11-20","arxiv_id":"1811.08067","repositories_listed":1,"syntology":null},{"url":"/paper/learning-actionable-representations-with-goal","slug":"learning-actionable-representations-with-goal","title":"Learning Actionable Representations with Goal-Conditioned Policies","date":"2018-11-19","arxiv_id":"1811.07819","repositories_listed":1,"syntology":null},{"url":"/paper/deep-q-learning-for-fooling-neural-networks","slug":"deep-q-learning-for-fooling-neural-networks","title":"Deep Q learning for fooling neural networks","date":"2018-11-13","arxiv_id":"1811.05521","repositories_listed":1,"syntology":null},{"url":"/paper/diversity-driven-extensible-hierarchical","slug":"diversity-driven-extensible-hierarchical","title":"Diversity-Driven Extensible Hierarchical Reinforcement Learning","date":"2018-11-10","arxiv_id":"1811.04324","repositories_listed":1,"syntology":null},{"url":"/paper/fully-convolutional-network-with-multi-step","slug":"fully-convolutional-network-with-multi-step","title":"Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing","date":"2018-11-10","arxiv_id":"1811.04323","repositories_listed":1,"syntology":null},{"url":"/paper/ace-an-actor-ensemble-algorithm-for","slug":"ace-an-actor-ensemble-algorithm-for","title":"ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search","date":"2018-11-06","arxiv_id":"1811.02696","repositories_listed":1,"syntology":null},{"url":"/paper/a-biologically-plausible-learning-rule-for","slug":"a-biologically-plausible-learning-rule-for","title":"A Biologically Plausible Learning Rule for Deep Learning in the Brain","date":"2018-11-05","arxiv_id":"1811.01768","repositories_listed":1,"syntology":null}],"record_sha256":"fd6c03fe46ddb7847a6d8d79829d306e7206b8375976e08c605320708f242fde","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}