{"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/25","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":25,"pages_in_order":132,"rows_per_page":100,"rows":[2401,2500],"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/24","next":"/task/reinforcement-learning/papers/26","papers":[{"url":"/paper/stochastic-actor-executor-critic-for-image-to","slug":"stochastic-actor-executor-critic-for-image-to","title":"Stochastic Actor-Executor-Critic for Image-to-Image Translation","date":"2021-12-14","arxiv_id":"2112.07403","repositories_listed":1,"syntology":null},{"url":"/paper/stochastic-planner-actor-critic-for","slug":"stochastic-planner-actor-critic-for","title":"Stochastic Planner-Actor-Critic for Unsupervised Deformable Image Registration","date":"2021-12-14","arxiv_id":"2112.07415","repositories_listed":1,"syntology":null},{"url":"/paper/finrl-meta-a-universe-of-near-real-market","slug":"finrl-meta-a-universe-of-near-real-market","title":"FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative Finance","date":"2021-12-13","arxiv_id":"2112.06753","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/finrl-meta-a-universe-of-near-real-market#ran","syntology_url":"https://syntology.ai/paper/2112.06753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.06753"}},"official":{"repos":["ai4finance-foundation/finrl-meta"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/human-level-control-through-directly-trained","slug":"human-level-control-through-directly-trained","title":"Human-Level Control through Directly-Trained Deep Spiking Q-Networks","date":"2021-12-13","arxiv_id":"2201.07211","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/human-level-control-through-directly-trained#ran","syntology_url":"https://syntology.ai/paper/2201.07211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.07211"}},"official":{"repos":["aptx395/deep-spiking-q-networks"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/tree-based-focused-web-crawling-with","slug":"tree-based-focused-web-crawling-with","title":"Tree-based Focused Web Crawling with Reinforcement Learning","date":"2021-12-12","arxiv_id":"2112.07620","repositories_listed":1,"syntology":null},{"url":"/paper/elegantrl-podracer-scalable-and-elastic","slug":"elegantrl-podracer-scalable-and-elastic","title":"ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning","date":"2021-12-11","arxiv_id":"2112.05923","repositories_listed":1,"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/elegantrl-podracer-scalable-and-elastic#ran","syntology_url":"https://syntology.ai/paper/2112.05923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05923"}},"official":{"repos":["ai4finance-foundation/elegantrl"],"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/blockwise-sequential-model-learning-for","slug":"blockwise-sequential-model-learning-for","title":"Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning","date":"2021-12-10","arxiv_id":"2112.05343","repositories_listed":1,"syntology":null},{"url":"/paper/deep-q-network-with-proximal-iteration-1","slug":"deep-q-network-with-proximal-iteration-1","title":"Faster Deep Reinforcement Learning with Slower Online Network","date":"2021-12-10","arxiv_id":"2112.05848","repositories_listed":1,"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/deep-q-network-with-proximal-iteration-1#ran","syntology_url":"https://syntology.ai/paper/2112.05848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05848"}},"official":{"repos":["amazon-research/fast-rl-with-slow-updates"],"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":["official"]}}},{"url":"/paper/learning-multiple-gaits-of-quadruped-robot","slug":"learning-multiple-gaits-of-quadruped-robot","title":"Learning multiple gaits of quadruped robot using hierarchical reinforcement learning","date":"2021-12-09","arxiv_id":"2112.04741","repositories_listed":1,"syntology":null},{"url":"/paper/value-function-factorisation-with-hypergraph","slug":"value-function-factorisation-with-hypergraph","title":"Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution","date":"2021-12-09","arxiv_id":"2112.06771","repositories_listed":1,"syntology":null},{"url":"/paper/godot-reinforcement-learning-agents","slug":"godot-reinforcement-learning-agents","title":"Godot Reinforcement Learning Agents","date":"2021-12-07","arxiv_id":"2112.03636","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/godot-reinforcement-learning-agents#ran","syntology_url":"https://syntology.ai/paper/2112.03636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03636"}},"official":{"repos":["edbeeching/godot_rl_agents"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/flexible-option-learning-1","slug":"flexible-option-learning-1","title":"Flexible Option Learning","date":"2021-12-06","arxiv_id":"2112.03097","repositories_listed":1,"syntology":null},{"url":"/paper/functional-regularization-for-reinforcement-1","slug":"functional-regularization-for-reinforcement-1","title":"Functional Regularization for Reinforcement Learning via Learned Fourier Features","date":"2021-12-06","arxiv_id":"2112.03257","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/functional-regularization-for-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2112.03257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03257"}},"official":{"repos":["alexlioralexli/learned-fourier-features"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-reinforcement-learning-with-5","slug":"hierarchical-reinforcement-learning-with-5","title":"Hierarchical Reinforcement Learning with Timed Subgoals","date":"2021-12-06","arxiv_id":"2112.03100","repositories_listed":1,"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/hierarchical-reinforcement-learning-with-5#ran","syntology_url":"https://syntology.ai/paper/2112.03100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03100"}},"official":{"repos":["martius-lab/hits"],"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/mdpgt-momentum-based-decentralized-policy","slug":"mdpgt-momentum-based-decentralized-policy","title":"MDPGT: Momentum-based Decentralized Policy Gradient Tracking","date":"2021-12-06","arxiv_id":"2112.02813","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-based-automatic-1","slug":"reinforcement-learning-based-automatic-1","title":"Reinforcement Learning-Based Automatic Berthing System","date":"2021-12-03","arxiv_id":"2112.01879","repositories_listed":1,"syntology":null},{"url":"/paper/sample-complexity-of-robust-reinforcement","slug":"sample-complexity-of-robust-reinforcement","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","date":"2021-12-02","arxiv_id":"2112.01506","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":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/sample-complexity-of-robust-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2112.01506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01506"}},"official":{"repos":["kishanpb/RobustRL"],"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/sparrl-graph-sparsification-via-deep-1","slug":"sparrl-graph-sparsification-via-deep-1","title":"A Generic Graph Sparsification Framework using Deep Reinforcement Learning","date":"2021-12-02","arxiv_id":"2112.01565","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-data-augmentation-for-1","slug":"automatic-data-augmentation-for-1","title":"Automatic Data Augmentation for Generalization in Reinforcement Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-domain-adaptation-for-cost","slug":"cross-modal-domain-adaptation-for-cost","title":"Cross-modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/edge-explaining-deep-reinforcement-learning","slug":"edge-explaining-deep-reinforcement-learning","title":"EDGE: Explaining Deep Reinforcement Learning Policies","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/explicable-reward-design-for-reinforcement","slug":"explicable-reward-design-for-reinforcement","title":"Explicable Reward Design for Reinforcement Learning Agents","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neorl-neuroevolution-optimization-with","slug":"neorl-neuroevolution-optimization-with","title":"NEORL: NeuroEvolution Optimization with Reinforcement Learning","date":"2021-12-01","arxiv_id":"2112.07057","repositories_listed":1,"syntology":null},{"url":"/paper/offline-model-based-adaptable-policy-learning","slug":"offline-model-based-adaptable-policy-learning","title":"Offline Model-based Adaptable Policy Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/regularized-softmax-deep-multi-agent-q","slug":"regularized-softmax-deep-multi-agent-q","title":"Regularized Softmax Deep Multi-Agent Q-Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/safe-exploration-for-constrained","slug":"safe-exploration-for-constrained","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","date":"2021-12-01","arxiv_id":"2112.00885","repositories_listed":1,"syntology":null},{"url":"/paper/symbolic-regression-via-deep-reinforcement","slug":"symbolic-regression-via-deep-reinforcement","title":"Symbolic Regression via Deep Reinforcement Learning Enhanced Genetic Programming Seeding","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/model-based-end-to-end-learning-for-wdm","slug":"model-based-end-to-end-learning-for-wdm","title":"Model-Based End-to-End Learning for WDM Systems With Transceiver Hardware Impairments","date":"2021-11-29","arxiv_id":"2111.14515","repositories_listed":1,"syntology":null},{"url":"/paper/deep-q-learning-based-reinforcement-learning","slug":"deep-q-learning-based-reinforcement-learning","title":"Deep Q-Learning based Reinforcement Learning Approach for Network Intrusion Detection","date":"2021-11-27","arxiv_id":"2111.13978","repositories_listed":1,"syntology":null},{"url":"/paper/learning-long-term-reward-redistribution-via-1","slug":"learning-long-term-reward-redistribution-via-1","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","date":"2021-11-26","arxiv_id":"2111.13485","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/learning-long-term-reward-redistribution-via-1#ran","syntology_url":"https://syntology.ai/paper/2111.13485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13485"}},"official":{"repos":["stilwell-git/randomized-return-decomposition"],"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/adaptively-calibrated-critic-estimates-for","slug":"adaptively-calibrated-critic-estimates-for","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","date":"2021-11-24","arxiv_id":"2111.12673","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/adaptively-calibrated-critic-estimates-for#ran","syntology_url":"https://syntology.ai/paper/2111.12673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12673"}},"official":{"repos":["nicolinho/acc"],"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/learning-state-representations-via-retracing-1","slug":"learning-state-representations-via-retracing-1","title":"Learning State Representations via Retracing in Reinforcement Learning","date":"2021-11-24","arxiv_id":"2111.12600","repositories_listed":1,"syntology":null},{"url":"/paper/off-policy-correction-for-multi-agent","slug":"off-policy-correction-for-multi-agent","title":"Off-Policy Correction For Multi-Agent Reinforcement Learning","date":"2021-11-22","arxiv_id":"2111.11229","repositories_listed":1,"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/off-policy-correction-for-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2111.11229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.11229"}},"official":{"repos":["awarelab/seed_rl"],"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/real-world-dexterous-object-manipulation","slug":"real-world-dexterous-object-manipulation","title":"Real-World Dexterous Object Manipulation based Deep Reinforcement Learning","date":"2021-11-22","arxiv_id":"2112.04893","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-few-shot-text","slug":"reinforcement-learning-for-few-shot-text","title":"Reinforcement Learning for Few-Shot Text Generation Adaptation","date":"2021-11-22","arxiv_id":"2111.11030","repositories_listed":1,"syntology":null},{"url":"/paper/successor-feature-landmarks-for-long-horizon","slug":"successor-feature-landmarks-for-long-horizon","title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","date":"2021-11-18","arxiv_id":"2111.09858","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/successor-feature-landmarks-for-long-horizon#ran","syntology_url":"https://syntology.ai/paper/2111.09858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09858"}},"official":null}},{"url":"/paper/on-effective-scheduling-of-model-based","slug":"on-effective-scheduling-of-model-based","title":"On Effective Scheduling of Model-based Reinforcement Learning","date":"2021-11-16","arxiv_id":"2111.08550","repositories_listed":1,"syntology":null},{"url":"/paper/modular-networks-prevent-catastrophic","slug":"modular-networks-prevent-catastrophic","title":"Modular Networks Prevent Catastrophic Interference in Model-Based Multi-Task Reinforcement Learning","date":"2021-11-15","arxiv_id":"2111.08010","repositories_listed":1,"syntology":null},{"url":"/paper/recursive-self-improvement-for-camera-image","slug":"recursive-self-improvement-for-camera-image","title":"Reinforcement Learning of Self Enhancing Camera Image and Signal Processing","date":"2021-11-15","arxiv_id":"2111.07499","repositories_listed":1,"syntology":null},{"url":"/paper/intelligent-trading-systems-a-sentiment-aware","slug":"intelligent-trading-systems-a-sentiment-aware","title":"Intelligent Trading Systems: A Sentiment-Aware Reinforcement Learning Approach","date":"2021-11-14","arxiv_id":"2112.02095","repositories_listed":1,"syntology":null},{"url":"/paper/cooperative-multi-agent-reinforcement-4","slug":"cooperative-multi-agent-reinforcement-4","title":"Cooperative multi-agent reinforcement learning for high-dimensional nonequilibrium control","date":"2021-11-12","arxiv_id":"2111.06875","repositories_listed":1,"syntology":null},{"url":"/paper/improving-experience-replay-through-modeling","slug":"improving-experience-replay-through-modeling","title":"Improving Experience Replay through Modeling of Similar Transitions' Sets","date":"2021-11-12","arxiv_id":"2111.06907","repositories_listed":1,"syntology":null},{"url":"/paper/resilient-consensus-based-multi-agent","slug":"resilient-consensus-based-multi-agent","title":"Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation","date":"2021-11-12","arxiv_id":"2111.06776","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-motion-planner-augmented-policies","slug":"distilling-motion-planner-augmented-policies","title":"Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation","date":"2021-11-11","arxiv_id":"2111.06383","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/distilling-motion-planner-augmented-policies#ran","syntology_url":"https://syntology.ai/paper/2111.06383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06383"}},"official":{"repos":["clvrai/mopa-pd"],"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/reinforcement-learning-for-mixed-autonomy","slug":"reinforcement-learning-for-mixed-autonomy","title":"Reinforcement Learning for Mixed Autonomy Intersections","date":"2021-11-08","arxiv_id":"2111.04686","repositories_listed":1,"syntology":null},{"url":"/paper/robust-deep-reinforcement-learning-for-1","slug":"robust-deep-reinforcement-learning-for-1","title":"Robust Deep Reinforcement Learning for Quadcopter Control","date":"2021-11-06","arxiv_id":"2111.03915","repositories_listed":1,"syntology":null},{"url":"/paper/b-pref-benchmarking-preference-based","slug":"b-pref-benchmarking-preference-based","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","date":"2021-11-04","arxiv_id":"2111.03026","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/b-pref-benchmarking-preference-based#ran","syntology_url":"https://syntology.ai/paper/2111.03026","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03026"}},"official":{"repos":["rll-research/b-pref"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/infinite-time-horizon-safety-of-bayesian","slug":"infinite-time-horizon-safety-of-bayesian","title":"Infinite Time Horizon Safety of Bayesian Neural Networks","date":"2021-11-04","arxiv_id":"2111.03165","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/infinite-time-horizon-safety-of-bayesian#ran","syntology_url":"https://syntology.ai/paper/2111.03165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03165"}},"official":{"repos":["mlech26l/bayesian_nn_safety"],"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/rlds-an-ecosystem-to-generate-share-and-use","slug":"rlds-an-ecosystem-to-generate-share-and-use","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","date":"2021-11-04","arxiv_id":"2111.02767","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/rlds-an-ecosystem-to-generate-share-and-use#ran","syntology_url":"https://syntology.ai/paper/2111.02767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02767"}},"official":{"repos":["google-research/rlds"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/human-level-control-without-server-grade-1","slug":"human-level-control-without-server-grade-1","title":"Human-Level Control without Server-Grade Hardware","date":"2021-11-01","arxiv_id":"2111.01264","repositories_listed":1,"syntology":null},{"url":"/paper/proximal-reinforcement-learning-efficient-off","slug":"proximal-reinforcement-learning-efficient-off","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","date":"2021-10-28","arxiv_id":"2110.15332","repositories_listed":1,"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/proximal-reinforcement-learning-efficient-off#ran","syntology_url":"https://syntology.ai/paper/2110.15332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15332"}},"official":{"repos":["causalml/proximalrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/urlb-unsupervised-reinforcement-learning","slug":"urlb-unsupervised-reinforcement-learning","title":"URLB: Unsupervised Reinforcement Learning Benchmark","date":"2021-10-28","arxiv_id":"2110.15191","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/urlb-unsupervised-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2110.15191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15191"}},"official":{"repos":["rll-research/url_benchmark"],"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/dreamerpro-reconstruction-free-model-based-1","slug":"dreamerpro-reconstruction-free-model-based-1","title":"DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations","date":"2021-10-27","arxiv_id":"2110.14565","repositories_listed":1,"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/dreamerpro-reconstruction-free-model-based-1#ran","syntology_url":"https://syntology.ai/paper/2110.14565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14565"}},"official":{"repos":["fdeng18/dreamer-pro"],"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":["official"]}}},{"url":"/paper/stabilising-viscous-extensional-flows-using","slug":"stabilising-viscous-extensional-flows-using","title":"Stabilising viscous extensional flows using Reinforcement Learning","date":"2021-10-27","arxiv_id":"2110.14677","repositories_listed":1,"syntology":null},{"url":"/paper/landmark-guided-subgoal-generation-in","slug":"landmark-guided-subgoal-generation-in","title":"Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning","date":"2021-10-26","arxiv_id":"2110.13625","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/landmark-guided-subgoal-generation-in#ran","syntology_url":"https://syntology.ai/paper/2110.13625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13625"}},"official":{"repos":["junsu-kim97/higl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-simulate-self-driven-particles","slug":"learning-to-simulate-self-driven-particles","title":"Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization","date":"2021-10-26","arxiv_id":"2110.13827","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/learning-to-simulate-self-driven-particles#ran","syntology_url":"https://syntology.ai/paper/2110.13827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13827"}},"official":{"repos":["decisionforce/CoPO"],"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/the-difficulty-of-passive-learning-in-deep","slug":"the-difficulty-of-passive-learning-in-deep","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","date":"2021-10-26","arxiv_id":"2110.14020","repositories_listed":1,"syntology":null},{"url":"/paper/towards-hyperparameter-free-policy-selection","slug":"towards-hyperparameter-free-policy-selection","title":"Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning","date":"2021-10-26","arxiv_id":"2110.14000","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/towards-hyperparameter-free-policy-selection#ran","syntology_url":"https://syntology.ai/paper/2110.14000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14000"}},"official":{"repos":["jasonzhang929/BVFT_empirical_experiments"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/goal-aware-cross-entropy-for-multi-target","slug":"goal-aware-cross-entropy-for-multi-target","title":"Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning","date":"2021-10-25","arxiv_id":"2110.12985","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 2 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) · 1 unverified","sample_list":"/paper/goal-aware-cross-entropy-for-multi-target#ran","syntology_url":"https://syntology.ai/paper/2110.12985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.12985"}},"official":{"repos":["kibeomkim/gace-gdan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mixture-of-variational-experts-for-continual","slug":"mixture-of-variational-experts-for-continual","title":"Mixture-of-Variational-Experts for Continual Learning","date":"2021-10-25","arxiv_id":"2110.12667","repositories_listed":1,"syntology":null},{"url":"/paper/safely-bridging-offline-and-online","slug":"safely-bridging-offline-and-online","title":"Uniformly Conservative Exploration in Reinforcement Learning","date":"2021-10-25","arxiv_id":"2110.13060","repositories_listed":1,"syntology":null},{"url":"/paper/score-spurious-correlation-reduction-for","slug":"score-spurious-correlation-reduction-for","title":"False Correlation Reduction for Offline Reinforcement Learning","date":"2021-10-24","arxiv_id":"2110.12468","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-world-through-action","slug":"understanding-the-world-through-action","title":"Understanding the World Through Action","date":"2021-10-24","arxiv_id":"2110.12543","repositories_listed":1,"syntology":null},{"url":"/paper/relace-reinforcement-learning-agent-for","slug":"relace-reinforcement-learning-agent-for","title":"ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models","date":"2021-10-22","arxiv_id":"2110.11960","repositories_listed":1,"syntology":null},{"url":"/paper/loa-logical-optimal-actions-for-text-based-1","slug":"loa-logical-optimal-actions-for-text-based-1","title":"LOA: Logical Optimal Actions for Text-based Interaction Games","date":"2021-10-21","arxiv_id":"2110.10973","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-skills-for-efficient-exploration","slug":"hierarchical-skills-for-efficient-exploration","title":"Hierarchical Skills for Efficient Exploration","date":"2021-10-20","arxiv_id":"2110.10809","repositories_listed":1,"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":7,"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/hierarchical-skills-for-efficient-exploration#ran","syntology_url":"https://syntology.ai/paper/2110.10809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10809"}},"official":{"repos":["facebookresearch/hsd3"],"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/playing-2048-with-reinforcement-learning","slug":"playing-2048-with-reinforcement-learning","title":"Playing 2048 With Reinforcement Learning","date":"2021-10-20","arxiv_id":"2110.10374","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-active-inference","slug":"contrastive-active-inference","title":"Contrastive Active Inference","date":"2021-10-19","arxiv_id":"2110.10083","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":2,"n_ran_checked":2,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contrastive-active-inference#ran","syntology_url":"https://syntology.ai/paper/2110.10083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10083"}},"official":{"repos":["mazpie/contrastive-aif"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-reinforcement-learning-with-value-1","slug":"offline-reinforcement-learning-with-value-1","title":"Offline Reinforcement Learning with Value-based Episodic Memory","date":"2021-10-19","arxiv_id":"2110.09796","repositories_listed":1,"syntology":null},{"url":"/paper/rl4rs-a-real-world-benchmark-for","slug":"rl4rs-a-real-world-benchmark-for","title":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","date":"2021-10-18","arxiv_id":"2110.11073","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-lifelong-reinforcement-learning","slug":"accelerating-lifelong-reinforcement-learning","title":"Accelerating lifelong reinforcement learning via reshaping rewards","date":"2021-10-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/extending-environments-to-measure-self","slug":"extending-environments-to-measure-self","title":"Extending Environments To Measure Self-Reflection In Reinforcement Learning","date":"2021-10-13","arxiv_id":"2110.06890","repositories_listed":1,"syntology":null},{"url":"/paper/safe-driving-via-expert-guided-policy","slug":"safe-driving-via-expert-guided-policy","title":"Safe Driving via Expert Guided Policy Optimization","date":"2021-10-13","arxiv_id":"2110.06831","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/safe-driving-via-expert-guided-policy#ran","syntology_url":"https://syntology.ai/paper/2110.06831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06831"}},"official":{"repos":["decisionforce/EGPO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/autonomous-racing-using-a-hybrid-imitation","slug":"autonomous-racing-using-a-hybrid-imitation","title":"Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture","date":"2021-10-11","arxiv_id":"2110.05437","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-ambiguous-demonstrations-with","slug":"learning-from-ambiguous-demonstrations-with","title":"Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning","date":"2021-10-11","arxiv_id":"2110.05286","repositories_listed":1,"syntology":null},{"url":"/paper/safe-model-based-reinforcement-learning-using","slug":"safe-model-based-reinforcement-learning-using","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","date":"2021-10-11","arxiv_id":"2110.05415","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-safety-requirements-for","slug":"understanding-the-safety-requirements-for","title":"Understanding the Safety Requirements for Learning-based Power Systems Operations","date":"2021-10-11","arxiv_id":"2110.04983","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-in-two-player-zero-sum","slug":"reinforcement-learning-in-two-player-zero-sum","title":"Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games","date":"2021-10-10","arxiv_id":"2110.04835","repositories_listed":1,"syntology":null},{"url":"/paper/vectorization-of-raster-manga-by-deep","slug":"vectorization-of-raster-manga-by-deep","title":"MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning","date":"2021-10-10","arxiv_id":"2110.04830","repositories_listed":1,"syntology":null},{"url":"/paper/augmenting-reinforcement-learning-with","slug":"augmenting-reinforcement-learning-with","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","date":"2021-10-07","arxiv_id":"2110.03655","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/augmenting-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2110.03655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03655"}},"official":{"repos":["UT-Austin-RPL/maple"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-sense-the-world-leveraging-hierarchy","slug":"how-to-sense-the-world-leveraging-hierarchy","title":"How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents","date":"2021-10-07","arxiv_id":"2110.03608","repositories_listed":1,"syntology":null},{"url":"/paper/optimized-recommender-systems-with-deep","slug":"optimized-recommender-systems-with-deep","title":"Optimized Recommender Systems with Deep Reinforcement Learning","date":"2021-10-06","arxiv_id":"2110.03039","repositories_listed":1,"syntology":null},{"url":"/paper/the-information-geometry-of-unsupervised","slug":"the-information-geometry-of-unsupervised","title":"The Information Geometry of Unsupervised Reinforcement Learning","date":"2021-10-06","arxiv_id":"2110.02719","repositories_listed":1,"syntology":null},{"url":"/paper/carl-a-benchmark-for-contextual-and-adaptive","slug":"carl-a-benchmark-for-contextual-and-adaptive","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","date":"2021-10-05","arxiv_id":"2110.02102","repositories_listed":1,"syntology":null},{"url":"/paper/brac-improved-behavior-regularized-actor","slug":"brac-improved-behavior-regularized-actor","title":"BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning","date":"2021-10-02","arxiv_id":"2110.00894","repositories_listed":1,"syntology":null},{"url":"/paper/mapping-language-to-programs-using-multiple","slug":"mapping-language-to-programs-using-multiple","title":"Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning","date":"2021-10-02","arxiv_id":"2110.00842","repositories_listed":1,"syntology":null},{"url":"/paper/offline-reinforcement-learning-with-reverse","slug":"offline-reinforcement-learning-with-reverse","title":"Offline Reinforcement Learning with Reverse Model-based Imagination","date":"2021-10-01","arxiv_id":"2110.00188","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-online-planning-via-reinforcement","slug":"scalable-online-planning-via-reinforcement","title":"Scalable Online Planning via Reinforcement Learning Fine-Tuning","date":"2021-09-30","arxiv_id":"2109.15316","repositories_listed":1,"syntology":null},{"url":"/paper/surveillance-evasion-through-bayesian","slug":"surveillance-evasion-through-bayesian","title":"Surveillance Evasion Through Bayesian Reinforcement Learning","date":"2021-09-30","arxiv_id":"2109.14811","repositories_listed":1,"syntology":null},{"url":"/paper/width-based-planning-and-active-learning-for","slug":"width-based-planning-and-active-learning-for","title":"Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari","date":"2021-09-30","arxiv_id":"2109.15310","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/width-based-planning-and-active-learning-for#ran","syntology_url":"https://syntology.ai/paper/2109.15310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.15310"}},"official":{"repos":["ibm/atari-active-learning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fourier-features-in-reinforcement-learning","slug":"fourier-features-in-reinforcement-learning","title":"Fourier Features in Reinforcement Learning with Neural Networks","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hyperdqn-a-randomized-exploration-method-for","slug":"hyperdqn-a-randomized-exploration-method-for","title":"HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/know-your-action-set-learning-action","slug":"know-your-action-set-learning-action","title":"Know Your Action Set: Learning Action Relations for Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/offline-reinforcement-learning-with-in-sample","slug":"offline-reinforcement-learning-with-in-sample","title":"Offline Reinforcement Learning with In-sample Q-Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/prioritized-experience-based-reinforcement","slug":"prioritized-experience-based-reinforcement","title":"Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving","date":"2021-09-26","arxiv_id":"2109.12516","repositories_listed":1,"syntology":null},{"url":"/paper/stackelberg-actor-critic-game-theoretic","slug":"stackelberg-actor-critic-game-theoretic","title":"Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms","date":"2021-09-25","arxiv_id":"2109.12286","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stackelberg-actor-critic-game-theoretic#ran","syntology_url":"https://syntology.ai/paper/2109.12286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12286"}},"official":{"repos":["leozhengzly/stackelberg-actor-critic-algos"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/nice-robust-scheduling-through-reinforcement","slug":"nice-robust-scheduling-through-reinforcement","title":"NICE: Robust Scheduling through Reinforcement Learning-Guided Integer Programming","date":"2021-09-24","arxiv_id":"2109.12171","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-navigational-safety-in-crowded","slug":"enhancing-navigational-safety-in-crowded","title":"Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation","date":"2021-09-23","arxiv_id":"2109.11288","repositories_listed":1,"syntology":null},{"url":"/paper/a-reinforcement-learning-benchmark-for","slug":"a-reinforcement-learning-benchmark-for","title":"A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios","date":"2021-09-22","arxiv_id":"2109.10557","repositories_listed":1,"syntology":null},{"url":"/paper/a-workflow-for-offline-model-free-robotic","slug":"a-workflow-for-offline-model-free-robotic","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10813","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/a-workflow-for-offline-model-free-robotic#ran","syntology_url":"https://syntology.ai/paper/2109.10813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10813"}},"official":null}}],"record_sha256":"af563877d06997220ca9a24a551035cce906ca8d15665cfe558ecab37858ab70","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}