{"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-2/papers/14","list_of":"/task/reinforcement-learning-2","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":14,"pages_in_order":135,"rows_per_page":100,"rows":[1301,1400],"of":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"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-2","prev":"/task/reinforcement-learning-2/papers/13","next":"/task/reinforcement-learning-2/papers/15","papers":[{"url":"/paper/diffusion-for-world-modeling-visual-details","slug":"diffusion-for-world-modeling-visual-details","title":"Diffusion for World Modeling: Visual Details Matter in Atari","date":"2024-05-20","arxiv_id":"2405.12399","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/diffusion-for-world-modeling-visual-details#ran","syntology_url":"https://syntology.ai/paper/2405.12399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12399"}},"official":{"repos":["eloialonso/diamond"],"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/efficient-multi-agent-reinforcement-learning","slug":"efficient-multi-agent-reinforcement-learning","title":"Efficient Multi-agent Reinforcement Learning by Planning","date":"2024-05-20","arxiv_id":"2405.11778","repositories_listed":1,"syntology":null},{"url":"/paper/feasibility-consistent-representation","slug":"feasibility-consistent-representation","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","date":"2024-05-20","arxiv_id":"2405.11718","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/feasibility-consistent-representation#ran","syntology_url":"https://syntology.ai/paper/2405.11718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11718"}},"official":{"repos":["czp16/fcsrl"],"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/is-mamba-compatible-with-trajectory","slug":"is-mamba-compatible-with-trajectory","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","date":"2024-05-20","arxiv_id":"2405.12094","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/is-mamba-compatible-with-trajectory#ran","syntology_url":"https://syntology.ai/paper/2405.12094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12094"}},"official":{"repos":["AndssY/DeMa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/scrutinize-what-we-ignore-reining-task","slug":"scrutinize-what-we-ignore-reining-task","title":"Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning","date":"2024-05-20","arxiv_id":"2405.12001","repositories_listed":1,"syntology":null},{"url":"/paper/pde-control-gym-a-benchmark-for-data-driven","slug":"pde-control-gym-a-benchmark-for-data-driven","title":"PDE Control Gym: A Benchmark for Data-Driven Boundary Control of Partial Differential Equations","date":"2024-05-18","arxiv_id":"2405.11401","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-1","slug":"reinforcement-learning-1","title":"Reinforcement learning","date":"2024-05-16","arxiv_id":"2405.10369","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2405.10369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10369"}},"official":{"repos":["sarodyatawatta/hintrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hype-or-heuristic-quantum-reinforcement","slug":"hype-or-heuristic-quantum-reinforcement","title":"Hype or Heuristic? Quantum Reinforcement Learning for Join Order Optimisation","date":"2024-05-13","arxiv_id":"2405.07770","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-anomaly-detection-via","slug":"semi-supervised-anomaly-detection-via","title":"Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor Signals","date":"2024-05-11","arxiv_id":"2405.06925","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-representation-for-data-filtering","slug":"contrastive-representation-for-data-filtering","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","date":"2024-05-10","arxiv_id":"2405.06192","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contrastive-representation-for-data-filtering#ran","syntology_url":"https://syntology.ai/paper/2405.06192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06192"}},"official":{"repos":["battlewen/igdf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fault-identification-enhancement-with","slug":"fault-identification-enhancement-with","title":"Fault Identification Enhancement with Reinforcement Learning (FIERL)","date":"2024-05-08","arxiv_id":"2405.04938","repositories_listed":1,"syntology":null},{"url":"/paper/proximal-policy-optimization-with-adaptive-1","slug":"proximal-policy-optimization-with-adaptive-1","title":"Proximal Policy Optimization with Adaptive Exploration","date":"2024-05-07","arxiv_id":"2405.04664","repositories_listed":1,"syntology":null},{"url":"/paper/swiftrl-towards-efficient-reinforcement","slug":"swiftrl-towards-efficient-reinforcement","title":"SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems","date":"2024-05-07","arxiv_id":"2405.03967","repositories_listed":1,"syntology":null},{"url":"/paper/reinwifi-a-reinforcement-learning-based","slug":"reinwifi-a-reinforcement-learning-based","title":"ReinWiFi: Application-Layer QoS Optimization of WiFi Networks with Reinforcement Learning","date":"2024-05-06","arxiv_id":"2405.03526","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-compression-speeds-up-credit","slug":"sequence-compression-speeds-up-credit","title":"Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning","date":"2024-05-06","arxiv_id":"2405.03878","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sequence-compression-speeds-up-credit#ran","syntology_url":"https://syntology.ai/paper/2405.03878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03878"}},"official":{"repos":["aditya-ramesh-10/chunktd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rice-breaking-through-the-training","slug":"rice-breaking-through-the-training","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","date":"2024-05-05","arxiv_id":"2405.03064","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rice-breaking-through-the-training#ran","syntology_url":"https://syntology.ai/paper/2405.03064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03064"}},"official":{"repos":["chengzelei/rice"],"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":["found_in_text","official"]}}},{"url":"/paper/ctd4-a-deep-continuous-distributional-actor","slug":"ctd4-a-deep-continuous-distributional-actor","title":"CTD4 -- A Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics","date":"2024-05-04","arxiv_id":"2405.02576","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cooperation-through-selective","slug":"enhancing-cooperation-through-selective","title":"Enhancing Cooperation through Selective Interaction and Long-term Experiences in Multi-Agent Reinforcement Learning","date":"2024-05-04","arxiv_id":"2405.02654","repositories_listed":1,"syntology":null},{"url":"/paper/hand-object-interaction-controller-hoic-deep","slug":"hand-object-interaction-controller-hoic-deep","title":"Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with Physics","date":"2024-05-04","arxiv_id":"2405.02676","repositories_listed":1,"syntology":null},{"url":"/paper/proximal-curriculum-with-task-correlations","slug":"proximal-curriculum-with-task-correlations","title":"Proximal Curriculum with Task Correlations for Deep Reinforcement Learning","date":"2024-05-03","arxiv_id":"2405.02481","repositories_listed":1,"syntology":null},{"url":"/paper/rlstop-a-reinforcement-learning-stopping","slug":"rlstop-a-reinforcement-learning-stopping","title":"RLStop: A Reinforcement Learning Stopping Method for TAR","date":"2024-05-03","arxiv_id":"2405.02525","repositories_listed":1,"syntology":null},{"url":"/paper/hard-thresholding-meets-evolution-strategies","slug":"hard-thresholding-meets-evolution-strategies","title":"Hard-Thresholding Meets Evolution Strategies in Reinforcement Learning","date":"2024-05-02","arxiv_id":"2405.01615","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hard-thresholding-meets-evolution-strategies#ran","syntology_url":"https://syntology.ai/paper/2405.01615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01615"}},"official":{"repos":["cangcn/nes-ht"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-procedural-generation-for-learning","slug":"leveraging-procedural-generation-for-learning","title":"Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space","date":"2024-05-02","arxiv_id":"2405.01134","repositories_listed":1,"syntology":null},{"url":"/paper/ucb-driven-utility-function-search-for-multi","slug":"ucb-driven-utility-function-search-for-multi","title":"UCB-driven Utility Function Search for Multi-objective Reinforcement Learning","date":"2024-05-01","arxiv_id":"2405.00410","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-reinforcement-learning-for-robot","slug":"adaptive-reinforcement-learning-for-robot","title":"Task and Domain Adaptive Reinforcement Learning for Robot Control","date":"2024-04-29","arxiv_id":"2404.18713","repositories_listed":1,"syntology":null},{"url":"/paper/dpo-meets-ppo-reinforced-token-optimization","slug":"dpo-meets-ppo-reinforced-token-optimization","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","date":"2024-04-29","arxiv_id":"2404.18922","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":1,"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/dpo-meets-ppo-reinforced-token-optimization#ran","syntology_url":"https://syntology.ai/paper/2404.18922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18922"}},"official":{"repos":["zkshan2002/rto"],"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/a-dual-perspective-of-reinforcement-learning","slug":"a-dual-perspective-of-reinforcement-learning","title":"A Dual Perspective of Reinforcement Learning for Imposing Policy Constraints","date":"2024-04-25","arxiv_id":"2404.16468","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-generative-models","slug":"reinforcement-learning-with-generative-models","title":"Reinforcement Learning with Generative Models for Compact Support Sets","date":"2024-04-25","arxiv_id":"2404.16300","repositories_listed":1,"syntology":null},{"url":"/paper/supercompiler-code-optimization-with-zero","slug":"supercompiler-code-optimization-with-zero","title":"CompilerDream: Learning a Compiler World Model for General Code Optimization","date":"2024-04-24","arxiv_id":"2404.16077","repositories_listed":1,"syntology":null},{"url":"/paper/multi-view-disentanglement-for-reinforcement","slug":"multi-view-disentanglement-for-reinforcement","title":"Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras","date":"2024-04-22","arxiv_id":"2404.14064","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-view-disentanglement-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2404.14064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14064"}},"official":{"repos":["uoe-agents/mvd"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/research-on-robot-path-planning-based-on","slug":"research-on-robot-path-planning-based-on","title":"Research on Robot Path Planning Based on Reinforcement Learning","date":"2024-04-22","arxiv_id":"2404.14077","repositories_listed":1,"syntology":null},{"url":"/paper/piper-primitive-informed-preference-based","slug":"piper-primitive-informed-preference-based","title":"PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling","date":"2024-04-20","arxiv_id":"2404.13423","repositories_listed":1,"syntology":null},{"url":"/paper/trajdeleter-enabling-trajectory-forgetting-in","slug":"trajdeleter-enabling-trajectory-forgetting-in","title":"TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents","date":"2024-04-18","arxiv_id":"2404.12530","repositories_listed":1,"syntology":null},{"url":"/paper/group-aware-coordination-graph-for-multi","slug":"group-aware-coordination-graph-for-multi","title":"Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning","date":"2024-04-17","arxiv_id":"2404.10976","repositories_listed":1,"syntology":null},{"url":"/paper/continual-offline-reinforcement-learning-via","slug":"continual-offline-reinforcement-learning-via","title":"Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay","date":"2024-04-16","arxiv_id":"2404.10662","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continual-offline-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2404.10662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10662"}},"official":{"repos":["nju-rl/cugro"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/n-agent-ad-hoc-teamwork","slug":"n-agent-ad-hoc-teamwork","title":"N-Agent Ad Hoc Teamwork","date":"2024-04-16","arxiv_id":"2404.10740","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":5,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/n-agent-ad-hoc-teamwork#ran","syntology_url":"https://syntology.ai/paper/2404.10740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10740"}},"official":{"repos":["carolinewang01/naht"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/sustainability-of-data-center-digital-twins","slug":"sustainability-of-data-center-digital-twins","title":"Sustainability of Data Center Digital Twins with Reinforcement Learning","date":"2024-04-16","arxiv_id":"2404.10786","repositories_listed":1,"syntology":null},{"url":"/paper/warm-start-variational-quantum-policy","slug":"warm-start-variational-quantum-policy","title":"Warm-Start Variational Quantum Policy Iteration","date":"2024-04-16","arxiv_id":"2404.10546","repositories_listed":1,"syntology":null},{"url":"/paper/what-hides-behind-unfairness-exploring","slug":"what-hides-behind-unfairness-exploring","title":"What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning","date":"2024-04-16","arxiv_id":"2404.10942","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/what-hides-behind-unfairness-exploring#ran","syntology_url":"https://syntology.ai/paper/2404.10942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10942"}},"official":{"repos":["familyld/insightfair"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/inferring-behavior-specific-context-improves","slug":"inferring-behavior-specific-context-improves","title":"Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning","date":"2024-04-15","arxiv_id":"2404.09521","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-population-based-training-for","slug":"generalized-population-based-training-for","title":"Generalized Population-Based Training for Hyperparameter Optimization in Reinforcement Learning","date":"2024-04-12","arxiv_id":"2404.08233","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/generalized-population-based-training-for#ran","syntology_url":"https://syntology.ai/paper/2404.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08233"}},"official":{"repos":["emi-group/gpbt-pl"],"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/sequential-decision-making-with-expert","slug":"sequential-decision-making-with-expert","title":"Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity","date":"2024-04-10","arxiv_id":"2404.07266","repositories_listed":1,"syntology":null},{"url":"/paper/percentile-criterion-optimization-in-offline-1","slug":"percentile-criterion-optimization-in-offline-1","title":"Percentile Criterion Optimization in Offline Reinforcement Learning","date":"2024-04-07","arxiv_id":"2404.05055","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"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) · 3 unverified","sample_list":"/paper/percentile-criterion-optimization-in-offline-1#ran","syntology_url":"https://syntology.ai/paper/2404.05055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05055"}},"official":{"repos":["elitalobo/varframework"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/compositional-conservatism-a-transductive","slug":"compositional-conservatism-a-transductive","title":"Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning","date":"2024-04-06","arxiv_id":"2404.04682","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/compositional-conservatism-a-transductive#ran","syntology_url":"https://syntology.ai/paper/2404.04682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04682"}},"official":{"repos":["runamu/compositional-conservatism"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/suppressing-modulation-instability-with","slug":"suppressing-modulation-instability-with","title":"Suppressing Modulation Instability with Reinforcement Learning","date":"2024-04-05","arxiv_id":"2404.04310","repositories_listed":1,"syntology":null},{"url":"/paper/grid-mapping-pseudo-count-constraint-for","slug":"grid-mapping-pseudo-count-constraint-for","title":"Grid-Mapping Pseudo-Count Constraint for Offline Reinforcement Learning","date":"2024-04-03","arxiv_id":"2404.02545","repositories_listed":1,"syntology":null},{"url":"/paper/llm-abr-designing-adaptive-bitrate-algorithms","slug":"llm-abr-designing-adaptive-bitrate-algorithms","title":"Designing Network Algorithms via Large Language Models","date":"2024-04-02","arxiv_id":"2404.01617","repositories_listed":1,"syntology":null},{"url":"/paper/entity-centric-reinforcement-learning-for","slug":"entity-centric-reinforcement-learning-for","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","date":"2024-04-01","arxiv_id":"2404.01220","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/entity-centric-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2404.01220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01220"}},"official":{"repos":["danhrmti/ecrl"],"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/prior-constraints-based-reward-model-training","slug":"prior-constraints-based-reward-model-training","title":"Prior Constraints-based Reward Model Training for Aligning Large Language Models","date":"2024-04-01","arxiv_id":"2404.00978","repositories_listed":1,"syntology":null},{"url":"/paper/a-ppo-based-drl-auto-tuning-nonlinear-pid","slug":"a-ppo-based-drl-auto-tuning-nonlinear-pid","title":"AirPilot: Interpretable PPO-based DRL Auto-Tuned Nonlinear PID Drone Controller for Robust Autonomous Flights","date":"2024-03-30","arxiv_id":"2404.00204","repositories_listed":1,"syntology":null},{"url":"/paper/decision-mamba-reinforcement-learning-via","slug":"decision-mamba-reinforcement-learning-via","title":"Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces","date":"2024-03-29","arxiv_id":"2403.19925","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/decision-mamba-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2403.19925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19925"}},"official":{"repos":["toshihiro-ota/decision-mamba"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mol-air-molecular-reinforcement-learning-with","slug":"mol-air-molecular-reinforcement-learning-with","title":"Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Rewards for Goal-directed Molecular Generation","date":"2024-03-29","arxiv_id":"2403.20109","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-length-from-quality-in-direct","slug":"disentangling-length-from-quality-in-direct","title":"Disentangling Length from Quality in Direct Preference Optimization","date":"2024-03-28","arxiv_id":"2403.19159","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disentangling-length-from-quality-in-direct#ran","syntology_url":"https://syntology.ai/paper/2403.19159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19159"}},"official":null}},{"url":"/paper/human-compatible-driving-partners-through","slug":"human-compatible-driving-partners-through","title":"Human-compatible driving partners through data-regularized self-play reinforcement learning","date":"2024-03-28","arxiv_id":"2403.19648","repositories_listed":1,"syntology":null},{"url":"/paper/the-new-agronomists-language-models-are","slug":"the-new-agronomists-language-models-are","title":"The New Agronomists: Language Models are Experts in Crop Management","date":"2024-03-28","arxiv_id":"2403.19839","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-symmetry-in-dynamics-for-model","slug":"exploiting-symmetry-in-dynamics-for-model","title":"Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards","date":"2024-03-27","arxiv_id":"2403.19024","repositories_listed":1,"syntology":null},{"url":"/paper/from-two-dimensional-to-three-dimensional-1","slug":"from-two-dimensional-to-three-dimensional-1","title":"From Two-Dimensional to Three-Dimensional Environment with Q-Learning: Modeling Autonomous Navigation with Reinforcement Learning and no Libraries","date":"2024-03-27","arxiv_id":"2403.18219","repositories_listed":1,"syntology":null},{"url":"/paper/compressed-federated-reinforcement-learning","slug":"compressed-federated-reinforcement-learning","title":"Compressed Federated Reinforcement Learning with a Generative Model","date":"2024-03-26","arxiv_id":"2404.10635","repositories_listed":1,"syntology":null},{"url":"/paper/imitating-cost-constrained-behaviors-in","slug":"imitating-cost-constrained-behaviors-in","title":"Imitating Cost-Constrained Behaviors in Reinforcement Learning","date":"2024-03-26","arxiv_id":"2403.17456","repositories_listed":1,"syntology":null},{"url":"/paper/clha-a-simple-yet-effective-contrastive","slug":"clha-a-simple-yet-effective-contrastive","title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","date":"2024-03-25","arxiv_id":"2403.16649","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clha-a-simple-yet-effective-contrastive#ran","syntology_url":"https://syntology.ai/paper/2403.16649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16649"}},"official":{"repos":["calubkk/clha"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/physics-informed-rl-for-maximal-safety","slug":"physics-informed-rl-for-maximal-safety","title":"Physics-informed RL for Maximal Safety Probability Estimation","date":"2024-03-25","arxiv_id":"2403.16391","repositories_listed":1,"syntology":null},{"url":"/paper/rl-for-consistency-models-faster-reward","slug":"rl-for-consistency-models-faster-reward","title":"RL for Consistency Models: Faster Reward Guided Text-to-Image Generation","date":"2024-03-25","arxiv_id":"2404.03673","repositories_listed":1,"syntology":null},{"url":"/paper/the-n-implementation-details-of-rlhf-with-ppo","slug":"the-n-implementation-details-of-rlhf-with-ppo","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","date":"2024-03-24","arxiv_id":"2403.17031","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-n-implementation-details-of-rlhf-with-ppo#ran","syntology_url":"https://syntology.ai/paper/2403.17031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17031"}},"official":{"repos":["vwxyzjn/summarize_from_feedback_details"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/a-reinforcement-learning-guided-hybrid","slug":"a-reinforcement-learning-guided-hybrid","title":"A reinforcement learning guided hybrid evolutionary algorithm for the latency location routing problem","date":"2024-03-21","arxiv_id":"2403.14405","repositories_listed":1,"syntology":null},{"url":"/paper/reactor-optimization-benchmark-by","slug":"reactor-optimization-benchmark-by","title":"Reactor Optimization Benchmark by Reinforcement Learning","date":"2024-03-21","arxiv_id":"2403.14273","repositories_listed":1,"syntology":null},{"url":"/paper/towards-principled-representation-learning-1","slug":"towards-principled-representation-learning-1","title":"Towards Principled Representation Learning from Videos for Reinforcement Learning","date":"2024-03-20","arxiv_id":"2403.13765","repositories_listed":1,"syntology":null},{"url":"/paper/insight-end-to-end-neuro-symbolic-visual","slug":"insight-end-to-end-neuro-symbolic-visual","title":"End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations","date":"2024-03-19","arxiv_id":"2403.12451","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":2,"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/insight-end-to-end-neuro-symbolic-visual#ran","syntology_url":"https://syntology.ai/paper/2403.12451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12451"}},"official":{"repos":["liruiluo/nsrl-vision-pub"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-bifurcation-in-safe-reinforcement","slug":"policy-bifurcation-in-safe-reinforcement","title":"Policy Bifurcation in Safe Reinforcement Learning","date":"2024-03-19","arxiv_id":"2403.12847","repositories_listed":1,"syntology":null},{"url":"/paper/decomposing-control-lyapunov-functions-for","slug":"decomposing-control-lyapunov-functions-for","title":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","date":"2024-03-18","arxiv_id":"2403.12210","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-from-delayed","slug":"reinforcement-learning-from-delayed","title":"Reinforcement Learning from Delayed Observations via World Models","date":"2024-03-18","arxiv_id":"2403.12309","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/reinforcement-learning-from-delayed#ran","syntology_url":"https://syntology.ai/paper/2403.12309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12309"}},"official":{"repos":["indylab/delayeddreamer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-with-token-level","slug":"reinforcement-learning-with-token-level","title":"Reinforcement Learning with Token-level Feedback for Controllable Text Generation","date":"2024-03-18","arxiv_id":"2403.11558","repositories_listed":1,"syntology":null},{"url":"/paper/single-agent-actor-critic-for-decentralized","slug":"single-agent-actor-critic-for-decentralized","title":"Agent-Agnostic Centralized Training for Decentralized Multi-Agent Cooperative Driving","date":"2024-03-18","arxiv_id":"2403.11914","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-reinforcement-learning-hierarchical","slug":"diffusion-reinforcement-learning-hierarchical","title":"Diffusion-Reinforcement Learning Hierarchical Motion Planning in Multi-agent Adversarial Games","date":"2024-03-16","arxiv_id":"2403.10794","repositories_listed":1,"syntology":null},{"url":"/paper/explorer-exploration-guided-reasoning-for","slug":"explorer-exploration-guided-reasoning-for","title":"EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning","date":"2024-03-15","arxiv_id":"2403.10692","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-symmetries-in-gaits-for","slug":"leveraging-symmetries-in-gaits-for","title":"Symmetry-Guided Reinforcement Learning for Versatile Quadrupedal Gait Generation","date":"2024-03-15","arxiv_id":"2403.10723","repositories_listed":1,"syntology":null},{"url":"/paper/quality-diversity-actor-critic-learning-high","slug":"quality-diversity-actor-critic-learning-high","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","date":"2024-03-15","arxiv_id":"2403.09930","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/quality-diversity-actor-critic-learning-high#ran","syntology_url":"https://syntology.ai/paper/2403.09930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09930"}},"official":{"repos":["adaptive-intelligent-robotics/qdac"],"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/incorporating-graph-attention-mechanism-into-1","slug":"incorporating-graph-attention-mechanism-into-1","title":"Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.14690","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-an-effective-world-model-approach-for","slug":"mamba-an-effective-world-model-approach-for","title":"MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09859","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mamba-an-effective-world-model-approach-for#ran","syntology_url":"https://syntology.ai/paper/2403.09859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09859"}},"official":{"repos":["zoharri/mamba"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sindy-rl-interpretable-and-efficient-model","slug":"sindy-rl-interpretable-and-efficient-model","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09110","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/sindy-rl-interpretable-and-efficient-model#ran","syntology_url":"https://syntology.ai/paper/2403.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09110"}},"official":{"repos":["nzolman/sindy-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-watermark-llm-generated-text-via","slug":"learning-to-watermark-llm-generated-text-via","title":"Learning to Watermark LLM-generated Text via Reinforcement Learning","date":"2024-03-13","arxiv_id":"2403.10553","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-watermark-llm-generated-text-via#ran","syntology_url":"https://syntology.ai/paper/2403.10553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10553"}},"official":{"repos":["xiaojunxu/learning-to-watermark-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/teams-rl-teaching-llms-to-teach-themselves","slug":"teams-rl-teaching-llms-to-teach-themselves","title":"TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning","date":"2024-03-13","arxiv_id":"2403.08694","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-gain-scheduling-using-reinforcement","slug":"adaptive-gain-scheduling-using-reinforcement","title":"Adaptive Gain Scheduling using Reinforcement Learning for Quadcopter Control","date":"2024-03-12","arxiv_id":"2403.07216","repositories_listed":1,"syntology":null},{"url":"/paper/advantage-aware-policy-optimization-for","slug":"advantage-aware-policy-optimization-for","title":"A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective","date":"2024-03-12","arxiv_id":"2403.07262","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-online-exploration-via-coverability","slug":"scalable-online-exploration-via-coverability","title":"Scalable Online Exploration via Coverability","date":"2024-03-11","arxiv_id":"2403.06571","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":1,"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/scalable-online-exploration-via-coverability#ran","syntology_url":"https://syntology.ai/paper/2403.06571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06571"}},"official":{"repos":["philip-amortila/l1-coverability"],"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/aligning-gptrec-with-beyond-accuracy-goals","slug":"aligning-gptrec-with-beyond-accuracy-goals","title":"Aligning GPTRec with Beyond-Accuracy Goals with Reinforcement Learning","date":"2024-03-07","arxiv_id":"2403.04875","repositories_listed":1,"syntology":null},{"url":"/paper/sampling-based-safe-reinforcement-learning","slug":"sampling-based-safe-reinforcement-learning","title":"Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems","date":"2024-03-06","arxiv_id":"2403.04007","repositories_listed":1,"syntology":null},{"url":"/paper/pps-qmix-periodically-parameter-sharing-for","slug":"pps-qmix-periodically-parameter-sharing-for","title":"PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning","date":"2024-03-05","arxiv_id":"2403.02635","repositories_listed":1,"syntology":null},{"url":"/paper/preventing-reward-hacking-with-occupancy","slug":"preventing-reward-hacking-with-occupancy","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","date":"2024-03-05","arxiv_id":"2403.03185","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/preventing-reward-hacking-with-occupancy#ran","syntology_url":"https://syntology.ai/paper/2403.03185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03185"}},"official":{"repos":["cassidylaidlaw/orpo"],"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/splagger-split-aggregation-for-meta","slug":"splagger-split-aggregation-for-meta","title":"SplAgger: Split Aggregation for Meta-Reinforcement Learning","date":"2024-03-05","arxiv_id":"2403.03020","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/splagger-split-aggregation-for-meta#ran","syntology_url":"https://syntology.ai/paper/2403.03020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03020"}},"official":{"repos":["jacooba/hyper"],"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/efficient-episodic-memory-utilization-of","slug":"efficient-episodic-memory-utilization-of","title":"Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01112","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/efficient-episodic-memory-utilization-of#ran","syntology_url":"https://syntology.ai/paper/2403.01112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01112"}},"official":{"repos":["hyunghona/emu"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-the-validity-of-automatically","slug":"improving-the-validity-of-automatically","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01304","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":13,"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) · 4 unverified","sample_list":"/paper/improving-the-validity-of-automatically#ran","syntology_url":"https://syntology.ai/paper/2403.01304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01304"}},"official":{"repos":["umass-ml4ed/feedback-gen-dpo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/snapshot-reinforcement-learning-leveraging","slug":"snapshot-reinforcement-learning-leveraging","title":"Snapshot Reinforcement Learning: Leveraging Prior Trajectories for Efficiency","date":"2024-03-01","arxiv_id":"2403.00673","repositories_listed":1,"syntology":null},{"url":"/paper/a-model-based-approach-for-improving","slug":"a-model-based-approach-for-improving","title":"A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations","date":"2024-02-29","arxiv_id":"2402.18836","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-iterative-combinatorial-auction","slug":"understanding-iterative-combinatorial-auction","title":"Understanding Iterative Combinatorial Auction Designs via Multi-Agent Reinforcement Learning","date":"2024-02-29","arxiv_id":"2402.19420","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/understanding-iterative-combinatorial-auction#ran","syntology_url":"https://syntology.ai/paper/2402.19420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19420"}},"official":{"repos":["newmanne/open_spiel"],"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/sample-efficient-preference-based","slug":"sample-efficient-preference-based","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","date":"2024-02-28","arxiv_id":"2402.17975","repositories_listed":1,"syntology":null},{"url":"/paper/rime-robust-preference-based-reinforcement","slug":"rime-robust-preference-based-reinforcement","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","date":"2024-02-27","arxiv_id":"2402.17257","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rime-robust-preference-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2402.17257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17257"}},"official":{"repos":["cjreinforce/rime_icml2024"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-zero-shot-reinforcement-learning","slug":"unsupervised-zero-shot-reinforcement-learning","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","date":"2024-02-27","arxiv_id":"2402.17135","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unsupervised-zero-shot-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2402.17135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17135"}},"official":{"repos":["kvfrans/fre"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/craftax-a-lightning-fast-benchmark-for-open","slug":"craftax-a-lightning-fast-benchmark-for-open","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16801","repositories_listed":1,"syntology":{"n":16,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":14,"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) · 14 unverified","sample_list":"/paper/craftax-a-lightning-fast-benchmark-for-open#ran","syntology_url":"https://syntology.ai/paper/2402.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16801"}},"official":{"repos":["michaeltmatthews/craftax"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/feedback-efficient-online-fine-tuning-of","slug":"feedback-efficient-online-fine-tuning-of","title":"Feedback Efficient Online Fine-Tuning of Diffusion Models","date":"2024-02-26","arxiv_id":"2402.16359","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 3 unverified","sample_list":"/paper/feedback-efficient-online-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2402.16359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16359"}},"official":null}},{"url":"/paper/flexible-robust-beamforming-for-multibeam","slug":"flexible-robust-beamforming-for-multibeam","title":"Flexible Robust Beamforming for Multibeam Satellite Downlink using Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16563","repositories_listed":1,"syntology":null}],"record_sha256":"d19340e830b76261ce6ce08081cdcb4f1d15f0b6d2a8331a5686ea6747f13d82","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}