{"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/14","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":14,"pages_in_order":132,"rows_per_page":100,"rows":[1301,1400],"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/13","next":"/task/reinforcement-learning/papers/15","papers":[{"url":"/paper/a-deep-reinforcement-learning-framework-for-8","slug":"a-deep-reinforcement-learning-framework-for-8","title":"A Deep Reinforcement Learning Framework For Financial Portfolio Management","date":"2024-09-03","arxiv_id":"2409.08426","repositories_listed":1,"syntology":null},{"url":"/paper/ai-olympics-challenge-with-evolutionary-soft","slug":"ai-olympics-challenge-with-evolutionary-soft","title":"AI Olympics challenge with Evolutionary Soft Actor Critic","date":"2024-09-02","arxiv_id":"2409.01104","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-recurrent-learning-using-trace","slug":"real-time-recurrent-learning-using-trace","title":"Real-Time Recurrent Learning using Trace Units in Reinforcement Learning","date":"2024-09-02","arxiv_id":"2409.01449","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":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/real-time-recurrent-learning-using-trace#ran","syntology_url":"https://syntology.ai/paper/2409.01449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01449"}},"official":{"repos":["esraaelelimy/rtus"],"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/trustworthy-human-ai-collaboration","slug":"trustworthy-human-ai-collaboration","title":"Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving","date":"2024-09-01","arxiv_id":"2409.00858","repositories_listed":1,"syntology":null},{"url":"/paper/miwaves-reinforcement-learning-algorithm","slug":"miwaves-reinforcement-learning-algorithm","title":"MiWaves Reinforcement Learning Algorithm","date":"2024-08-27","arxiv_id":"2408.15076","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-humanoid-locomotion-mastering","slug":"advancing-humanoid-locomotion-mastering","title":"Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning","date":"2024-08-26","arxiv_id":"2408.14472","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/advancing-humanoid-locomotion-mastering#ran","syntology_url":"https://syntology.ai/paper/2408.14472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14472"}},"official":{"repos":["roboterax/humanoid-gym"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-centralized-critics-in-multi-agent","slug":"on-centralized-critics-in-multi-agent","title":"On Centralized Critics in Multi-Agent Reinforcement Learning","date":"2024-08-26","arxiv_id":"2408.14597","repositories_listed":1,"syntology":null},{"url":"/paper/control-informed-reinforcement-learning-for","slug":"control-informed-reinforcement-learning-for","title":"Control-Informed Reinforcement Learning for Chemical Processes","date":"2024-08-24","arxiv_id":"2408.13566","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-interpretable-decision-tree","slug":"optimizing-interpretable-decision-tree","title":"Optimizing Interpretable Decision Tree Policies for Reinforcement Learning","date":"2024-08-21","arxiv_id":"2408.11632","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-goal-conditioned-rl-algorithms","slug":"accelerating-goal-conditioned-rl-algorithms","title":"Accelerating Goal-Conditioned RL Algorithms and Research","date":"2024-08-20","arxiv_id":"2408.11052","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":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/accelerating-goal-conditioned-rl-algorithms#ran","syntology_url":"https://syntology.ai/paper/2408.11052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11052"}},"official":{"repos":["michalbortkiewicz/jaxgcrl"],"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/hokoff-real-game-dataset-from-honor-of-kings-1","slug":"hokoff-real-game-dataset-from-honor-of-kings-1","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","date":"2024-08-20","arxiv_id":"2408.10556","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":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) · 0 unverified","sample_list":"/paper/hokoff-real-game-dataset-from-honor-of-kings-1#ran","syntology_url":"https://syntology.ai/paper/2408.10556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10556"}},"official":{"repos":["tencent-ailab/hokoff"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-sharing-and-transfer-via","slug":"knowledge-sharing-and-transfer-via","title":"Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning","date":"2024-08-20","arxiv_id":"2408.10858","repositories_listed":1,"syntology":null},{"url":"/paper/physics-aware-combinatorial-assembly-planning","slug":"physics-aware-combinatorial-assembly-planning","title":"Physics-Aware Combinatorial Assembly Sequence Planning using Data-free Action Masking","date":"2024-08-19","arxiv_id":"2408.10162","repositories_listed":1,"syntology":null},{"url":"/paper/histogym-a-reinforcement-learning-environment","slug":"histogym-a-reinforcement-learning-environment","title":"HistoGym: A Reinforcement Learning Environment for Histopathological Image Analysis","date":"2024-08-16","arxiv_id":"2408.08847","repositories_listed":1,"syntology":null},{"url":"/paper/sympol-symbolic-tree-based-on-policy","slug":"sympol-symbolic-tree-based-on-policy","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","date":"2024-08-16","arxiv_id":"2408.08761","repositories_listed":1,"syntology":null},{"url":"/paper/real-world-validation-of-safe-reinforcement","slug":"real-world-validation-of-safe-reinforcement","title":"Real-world validation of safe reinforcement learning, model predictive control and decision tree-based home energy management systems","date":"2024-08-14","arxiv_id":"2408.07435","repositories_listed":1,"syntology":null},{"url":"/paper/an-introduction-to-reinforcement-learning","slug":"an-introduction-to-reinforcement-learning","title":"Introduction to Reinforcement Learning","date":"2024-08-13","arxiv_id":"2408.07712","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-saliency-ranking-and","slug":"integrating-saliency-ranking-and","title":"Integrating Saliency Ranking and Reinforcement Learning for Enhanced Object Detection","date":"2024-08-13","arxiv_id":"2408.06803","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-dynamic-difficulty-adjustment","slug":"personalized-dynamic-difficulty-adjustment","title":"Personalized Dynamic Difficulty Adjustment -- Imitation Learning Meets Reinforcement Learning","date":"2024-08-13","arxiv_id":"2408.06818","repositories_listed":1,"syntology":null},{"url":"/paper/kolmogorov-arnold-network-for-online","slug":"kolmogorov-arnold-network-for-online","title":"Kolmogorov-Arnold Network for Online Reinforcement Learning","date":"2024-08-09","arxiv_id":"2408.04841","repositories_listed":1,"syntology":null},{"url":"/paper/assigning-credit-with-partial-reward","slug":"assigning-credit-with-partial-reward","title":"Assigning Credit with Partial Reward Decoupling in Multi-Agent Proximal Policy Optimization","date":"2024-08-08","arxiv_id":"2408.04295","repositories_listed":1,"syntology":null},{"url":"/paper/listwise-reward-estimation-for-offline","slug":"listwise-reward-estimation-for-offline","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","date":"2024-08-08","arxiv_id":"2408.04190","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/listwise-reward-estimation-for-offline#ran","syntology_url":"https://syntology.ai/paper/2408.04190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04190"}},"official":{"repos":["chwoong/lire"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-transfer-learning-for-contextual","slug":"model-based-transfer-learning-for-contextual","title":"Model-Based Transfer Learning for Contextual Reinforcement Learning","date":"2024-08-08","arxiv_id":"2408.04498","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/model-based-transfer-learning-for-contextual#ran","syntology_url":"https://syntology.ai/paper/2408.04498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04498"}},"official":{"repos":["jhoon-cho/mbtl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-rate-free-reinforcement-learning-a","slug":"learning-rate-free-reinforcement-learning-a","title":"Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives","date":"2024-08-07","arxiv_id":"2408.04046","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02976","slug":"2408-02976","title":"Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation","date":"2024-08-06","arxiv_id":"2408.02976","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03195","slug":"2408-03195","title":"RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning","date":"2024-08-06","arxiv_id":"2408.03195","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":15,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/2408-03195#ran","syntology_url":"https://syntology.ai/paper/2408.03195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03195"}},"official":{"repos":["JasonZhujp/RELIEF"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/generalized-gaussian-temporal-difference","slug":"generalized-gaussian-temporal-difference","title":"Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning","date":"2024-08-05","arxiv_id":"2408.02295","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01892","slug":"2408-01892","title":"Re-ENACT: Reinforcement Learning for Emotional Speech Generation using Actor-Critic Strategy","date":"2024-08-04","arxiv_id":"2408.01892","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01942","slug":"2408-01942","title":"Visual Grounding for Object-Level Generalization in Reinforcement Learning","date":"2024-08-04","arxiv_id":"2408.01942","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":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) · 3 unverified","sample_list":"/paper/2408-01942#ran","syntology_url":"https://syntology.ai/paper/2408.01942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01942"}},"official":{"repos":["pku-rl/copl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-00713","slug":"2408-00713","title":"Reinforcement Learning applied to Insurance Portfolio Pursuit","date":"2024-08-01","arxiv_id":"2408.00713","repositories_listed":1,"syntology":null},{"url":"/paper/discretizing-continuous-action-space-with","slug":"discretizing-continuous-action-space-with","title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning","date":"2024-08-01","arxiv_id":"2408.00309","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-perturbed-states-for-transformed-input","slug":"on-the-perturbed-states-for-transformed-input","title":"On the Perturbed States for Transformed Input-robust Reinforcement Learning","date":"2024-07-31","arxiv_id":"2408.00023","repositories_listed":1,"syntology":null},{"url":"/paper/arcle-the-abstraction-and-reasoning-corpus","slug":"arcle-the-abstraction-and-reasoning-corpus","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","date":"2024-07-30","arxiv_id":"2407.20806","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/arcle-the-abstraction-and-reasoning-corpus#ran","syntology_url":"https://syntology.ai/paper/2407.20806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20806"}},"official":{"repos":["confeitohs/arcle"],"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/dataset-distillation-for-offline","slug":"dataset-distillation-for-offline","title":"Dataset Distillation for Offline Reinforcement Learning","date":"2024-07-29","arxiv_id":"2407.20299","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":6,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":6,"n_pointer_only":2,"phrase":"11 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/dataset-distillation-for-offline#ran","syntology_url":"https://syntology.ai/paper/2407.20299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20299"}},"official":{"repos":["ggflow123/ddrl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["community","official"]}}},{"url":"/paper/navix-scaling-minigrid-environments-with-jax","slug":"navix-scaling-minigrid-environments-with-jax","title":"NAVIX: Scaling MiniGrid Environments with JAX","date":"2024-07-28","arxiv_id":"2407.19396","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/navix-scaling-minigrid-environments-with-jax#ran","syntology_url":"https://syntology.ai/paper/2407.19396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19396"}},"official":{"repos":["epignatelli/navix"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gymnasium-a-standard-interface-for","slug":"gymnasium-a-standard-interface-for","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","date":"2024-07-24","arxiv_id":"2407.17032","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/gymnasium-a-standard-interface-for#ran","syntology_url":"https://syntology.ai/paper/2407.17032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17032"}},"official":{"repos":["farama-foundation/gymnasium"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-models-as-optimizers-for-efficient","slug":"diffusion-models-as-optimizers-for-efficient","title":"Diffusion Models as Optimizers for Efficient Planning in Offline RL","date":"2024-07-23","arxiv_id":"2407.16142","repositories_listed":1,"syntology":null},{"url":"/paper/momaland-a-set-of-benchmarks-for-multi","slug":"momaland-a-set-of-benchmarks-for-multi","title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","date":"2024-07-23","arxiv_id":"2407.16312","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-pair-trading-a-dynamic","slug":"reinforcement-learning-pair-trading-a-dynamic","title":"Reinforcement Learning Pair Trading: A Dynamic Scaling approach","date":"2024-07-23","arxiv_id":"2407.16103","repositories_listed":1,"syntology":null},{"url":"/paper/on-shallow-planning-under-partial","slug":"on-shallow-planning-under-partial","title":"On shallow planning under partial observability","date":"2024-07-22","arxiv_id":"2407.15820","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-meets-visual-odometry","slug":"reinforcement-learning-meets-visual-odometry","title":"Reinforcement Learning Meets Visual Odometry","date":"2024-07-22","arxiv_id":"2407.15626","repositories_listed":1,"syntology":null},{"url":"/paper/sustainable-broadcasting-in-blockchain","slug":"sustainable-broadcasting-in-blockchain","title":"Sustainable broadcasting in Blockchain Networks with Reinforcement Learning","date":"2024-07-22","arxiv_id":"2407.15616","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-for-verilog-generation","slug":"large-language-model-for-verilog-generation","title":"Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning","date":"2024-07-21","arxiv_id":"2407.18271","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-model-for-verilog-generation#ran","syntology_url":"https://syntology.ai/paper/2407.18271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18271"}},"official":{"repos":["CatIIIIIIII/veriseek"],"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/oasis-conditional-distribution-shaping-for","slug":"oasis-conditional-distribution-shaping-for","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","date":"2024-07-19","arxiv_id":"2407.14653","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/oasis-conditional-distribution-shaping-for#ran","syntology_url":"https://syntology.ai/paper/2407.14653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14653"}},"official":{"repos":["yihangyao/OASIS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-empowered-state-representation-for","slug":"llm-empowered-state-representation-for","title":"LLM-Empowered State Representation for Reinforcement Learning","date":"2024-07-18","arxiv_id":"2407.13237","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-empowered-state-representation-for#ran","syntology_url":"https://syntology.ai/paper/2407.13237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13237"}},"official":{"repos":["thu-rllab/LESR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-label-relevance-ranking-via","slug":"multimodal-label-relevance-ranking-via","title":"Multimodal Label Relevance Ranking via Reinforcement Learning","date":"2024-07-18","arxiv_id":"2407.13221","repositories_listed":1,"syntology":null},{"url":"/paper/roler-effective-reward-shaping-in-offline","slug":"roler-effective-reward-shaping-in-offline","title":"ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems","date":"2024-07-18","arxiv_id":"2407.13163","repositories_listed":1,"syntology":null},{"url":"/paper/energy-guided-diffusion-sampling-for-offline","slug":"energy-guided-diffusion-sampling-for-offline","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.12448","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":4,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/energy-guided-diffusion-sampling-for-offline#ran","syntology_url":"https://syntology.ai/paper/2407.12448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12448"}},"official":{"repos":["liuxhym/edis"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/variable-agnostic-causal-exploration-for","slug":"variable-agnostic-causal-exploration-for","title":"Variable-Agnostic Causal Exploration for Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.12437","repositories_listed":1,"syntology":null},{"url":"/paper/pareto-local-search-for-a-multi-objective","slug":"pareto-local-search-for-a-multi-objective","title":"Pareto local search for a multi-objective demand response problem in residential areas with heat pumps and electric vehicles","date":"2024-07-16","arxiv_id":"2407.11719","repositories_listed":1,"syntology":null},{"url":"/paper/balancing-the-scales-reinforcement-learning","slug":"balancing-the-scales-reinforcement-learning","title":"Balancing the Scales: Reinforcement Learning for Fair Classification","date":"2024-07-15","arxiv_id":"2407.10629","repositories_listed":1,"syntology":null},{"url":"/paper/g-pcgrl-procedural-graph-data-generation-via","slug":"g-pcgrl-procedural-graph-data-generation-via","title":"G-PCGRL: Procedural Graph Data Generation via Reinforcement Learning","date":"2024-07-15","arxiv_id":"2407.10483","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21025","slug":"2407-21025","title":"Reinforcement Learning in High-frequency Market Making","date":"2024-07-14","arxiv_id":"2407.21025","repositories_listed":1,"syntology":null},{"url":"/paper/a-benchmark-environment-for-offline","slug":"a-benchmark-environment-for-offline","title":"A Benchmark Environment for Offline Reinforcement Learning in Racing Games","date":"2024-07-12","arxiv_id":"2407.09415","repositories_listed":1,"syntology":null},{"url":"/paper/constrained-intrinsic-motivation-for","slug":"constrained-intrinsic-motivation-for","title":"Constrained Intrinsic Motivation for Reinforcement Learning","date":"2024-07-12","arxiv_id":"2407.09247","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 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; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/constrained-intrinsic-motivation-for#ran","syntology_url":"https://syntology.ai/paper/2407.09247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09247"}},"official":{"repos":["x-zheng16/cim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/instruction-following-with-goal-conditioned","slug":"instruction-following-with-goal-conditioned","title":"Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments","date":"2024-07-12","arxiv_id":"2407.09287","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-sequential","slug":"deep-reinforcement-learning-for-sequential","title":"Deep Reinforcement Learning for Sequential Combinatorial Auctions","date":"2024-07-10","arxiv_id":"2407.08022","repositories_listed":1,"syntology":null},{"url":"/paper/structural-design-through-reinforcement","slug":"structural-design-through-reinforcement","title":"Structural Design Through Reinforcement Learning","date":"2024-07-10","arxiv_id":"2407.07288","repositories_listed":1,"syntology":null},{"url":"/paper/a-generative-approach-to-control-complex","slug":"a-generative-approach-to-control-complex","title":"DiffPhyCon: A Generative Approach to Control Complex Physical Systems","date":"2024-07-09","arxiv_id":"2407.06494","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-generative-approach-to-control-complex#ran","syntology_url":"https://syntology.ai/paper/2407.06494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06494"}},"official":{"repos":["ai4science-westlakeu/diffphycon"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/can-learned-optimization-make-reinforcement","slug":"can-learned-optimization-make-reinforcement","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","date":"2024-07-09","arxiv_id":"2407.07082","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":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) · 0 unverified","sample_list":"/paper/can-learned-optimization-make-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2407.07082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07082"}},"official":{"repos":["alexgoldie/rl-learned-optimization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/preference-guided-reinforcement-learning-for","slug":"preference-guided-reinforcement-learning-for","title":"Preference-Guided Reinforcement Learning for Efficient Exploration","date":"2024-07-09","arxiv_id":"2407.06503","repositories_listed":1,"syntology":null},{"url":"/paper/fedmrl-data-heterogeneity-aware-federated","slug":"fedmrl-data-heterogeneity-aware-federated","title":"FedMRL: Data Heterogeneity Aware Federated Multi-agent Deep Reinforcement Learning for Medical Imaging","date":"2024-07-08","arxiv_id":"2407.05800","repositories_listed":1,"syntology":null},{"url":"/paper/hindsight-preference-learning-for-offline","slug":"hindsight-preference-learning-for-offline","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","date":"2024-07-05","arxiv_id":"2407.04451","repositories_listed":1,"syntology":null},{"url":"/paper/craftium-an-extensible-framework-for-creating","slug":"craftium-an-extensible-framework-for-creating","title":"Craftium: An Extensible Framework for Creating Reinforcement Learning Environments","date":"2024-07-04","arxiv_id":"2407.03969","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/craftium-an-extensible-framework-for-creating#ran","syntology_url":"https://syntology.ai/paper/2407.03969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03969"}},"official":{"repos":["mikelma/craftium"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/q-adapter-training-your-llm-adapter-as-a","slug":"q-adapter-training-your-llm-adapter-as-a","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","date":"2024-07-04","arxiv_id":"2407.03856","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"13 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/q-adapter-training-your-llm-adapter-as-a#ran","syntology_url":"https://syntology.ai/paper/2407.03856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03856"}},"official":{"repos":["mansicer/Q-Adapter"],"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":["found_in_text","official"]}}},{"url":"/paper/robocupgym-a-challenging-continuous-control","slug":"robocupgym-a-challenging-continuous-control","title":"RobocupGym: A challenging continuous control benchmark in Robocup","date":"2024-07-03","arxiv_id":"2407.14516","repositories_listed":1,"syntology":null},{"url":"/paper/value-penalized-auxiliary-control-from","slug":"value-penalized-auxiliary-control-from","title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","date":"2024-07-03","arxiv_id":"2407.03311","repositories_listed":1,"syntology":null},{"url":"/paper/weight-clipping-for-deep-continual-and","slug":"weight-clipping-for-deep-continual-and","title":"Weight Clipping for Deep Continual and Reinforcement Learning","date":"2024-07-01","arxiv_id":"2407.01704","repositories_listed":1,"syntology":null},{"url":"/paper/model-free-active-exploration-in-1","slug":"model-free-active-exploration-in-1","title":"Model-Free Active Exploration in Reinforcement Learning","date":"2024-06-30","arxiv_id":"2407.00801","repositories_listed":1,"syntology":null},{"url":"/paper/a-two-stage-reinforcement-learning-based","slug":"a-two-stage-reinforcement-learning-based","title":"A Two-stage Reinforcement Learning-based Approach for Multi-entity Task Allocation","date":"2024-06-29","arxiv_id":"2407.00496","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-constant-negative-rewards-for-goal","slug":"revisiting-constant-negative-rewards-for-goal","title":"Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning","date":"2024-06-29","arxiv_id":"2407.00324","repositories_listed":1,"syntology":null},{"url":"/paper/external-model-motivated-agents-reinforcement","slug":"external-model-motivated-agents-reinforcement","title":"External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling","date":"2024-06-28","arxiv_id":"2407.00264","repositories_listed":1,"syntology":null},{"url":"/paper/operator-world-models-for-reinforcement","slug":"operator-world-models-for-reinforcement","title":"Operator World Models for Reinforcement Learning","date":"2024-06-28","arxiv_id":"2406.19861","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-reachable-hierarchical","slug":"bidirectional-reachable-hierarchical","title":"Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies","date":"2024-06-26","arxiv_id":"2406.18053","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptation-of-echocardiography","slug":"domain-adaptation-of-echocardiography","title":"Domain Adaptation of Echocardiography Segmentation Via Reinforcement Learning","date":"2024-06-25","arxiv_id":"2406.17902","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-consistency-of-hyper-parameter","slug":"on-the-consistency-of-hyper-parameter","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","date":"2024-06-25","arxiv_id":"2406.17523","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-aware-inverse-constrained","slug":"confidence-aware-inverse-constrained","title":"Confidence Aware Inverse Constrained Reinforcement Learning","date":"2024-06-24","arxiv_id":"2406.16782","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/confidence-aware-inverse-constrained#ran","syntology_url":"https://syntology.ai/paper/2406.16782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16782"}},"official":{"repos":["sriram94/confidenceawareicrl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/kehrl-learning-knowledge-enhanced-language","slug":"kehrl-learning-knowledge-enhanced-language","title":"KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning","date":"2024-06-24","arxiv_id":"2406.16374","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-subgoal-representations-for","slug":"probabilistic-subgoal-representations-for","title":"Probabilistic Subgoal Representations for Hierarchical Reinforcement learning","date":"2024-06-24","arxiv_id":"2406.16707","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-via-auxiliary-task","slug":"reinforcement-learning-via-auxiliary-task","title":"Reinforcement Learning via Auxiliary Task Distillation","date":"2024-06-24","arxiv_id":"2406.17168","repositories_listed":1,"syntology":null},{"url":"/paper/bounding-box-inference-for-error-aware-model","slug":"bounding-box-inference-for-error-aware-model","title":"Bounding-Box Inference for Error-Aware Model-Based Reinforcement Learning","date":"2024-06-23","arxiv_id":"2406.16006","repositories_listed":1,"syntology":null},{"url":"/paper/sit-symmetry-invariant-transformers-for","slug":"sit-symmetry-invariant-transformers-for","title":"SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learning","date":"2024-06-21","arxiv_id":"2406.15025","repositories_listed":1,"syntology":null},{"url":"/paper/towards-general-negotiation-strategies-with","slug":"towards-general-negotiation-strategies-with","title":"Towards General Negotiation Strategies with End-to-End Reinforcement Learning","date":"2024-06-21","arxiv_id":"2406.15096","repositories_listed":1,"syntology":null},{"url":"/paper/a-benchmark-study-of-deep-rl-methods-for","slug":"a-benchmark-study-of-deep-rl-methods-for","title":"A Benchmark Study of Deep-RL Methods for Maximum Coverage Problems over Graphs","date":"2024-06-20","arxiv_id":"2406.14697","repositories_listed":1,"syntology":null},{"url":"/paper/macrohft-memory-augmented-context-aware","slug":"macrohft-memory-augmented-context-aware","title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","date":"2024-06-20","arxiv_id":"2406.14537","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/macrohft-memory-augmented-context-aware#ran","syntology_url":"https://syntology.ai/paper/2406.14537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14537"}},"official":{"repos":["ZONG0004/MacroHFT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/soft-qmix-integrating-maximum-entropy-for","slug":"soft-qmix-integrating-maximum-entropy-for","title":"Soft-QMIX: Integrating Maximum Entropy For Monotonic Value Function Factorization","date":"2024-06-20","arxiv_id":"2406.13930","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-offline-reinforcement-learning-the","slug":"efficient-offline-reinforcement-learning-the","title":"Efficient Offline Reinforcement Learning: The Critic is Critical","date":"2024-06-19","arxiv_id":"2406.13376","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-minimal-reinforcement-learning","slug":"discovering-minimal-reinforcement-learning","title":"Discovering Minimal Reinforcement Learning Environments","date":"2024-06-18","arxiv_id":"2406.12589","repositories_listed":1,"syntology":null},{"url":"/paper/more-efficient-randomized-exploration-for","slug":"more-efficient-randomized-exploration-for","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","date":"2024-06-18","arxiv_id":"2406.12241","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/more-efficient-randomized-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2406.12241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12241"}},"official":{"repos":["panxulab/lsvi-ase"],"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"]}}},{"url":"/paper/is-poisoning-a-real-threat-to-llm-alignment","slug":"is-poisoning-a-real-threat-to-llm-alignment","title":"Is poisoning a real threat to LLM alignment? Maybe more so than you think","date":"2024-06-17","arxiv_id":"2406.12091","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/is-poisoning-a-real-threat-to-llm-alignment#ran","syntology_url":"https://syntology.ai/paper/2406.12091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12091"}},"official":{"repos":["pankayaraj/RLHFPoisoning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/toward-optimal-llm-alignments-using-two","slug":"toward-optimal-llm-alignments-using-two","title":"Toward Optimal LLM Alignments Using Two-Player Games","date":"2024-06-16","arxiv_id":"2406.10977","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/toward-optimal-llm-alignments-using-two#ran","syntology_url":"https://syntology.ai/paper/2406.10977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10977"}},"official":{"repos":["ruizheng20/gpo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-model-based-reinforcement-learning-1","slug":"robust-model-based-reinforcement-learning-1","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","date":"2024-06-14","arxiv_id":"2406.09976","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/robust-model-based-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2406.09976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09976"}},"official":{"repos":["rmbpo-eval/rmbpo-eval"],"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/hierarchical-reinforcement-learning-for-swarm","slug":"hierarchical-reinforcement-learning-for-swarm","title":"Hierarchical Reinforcement Learning for Swarm Confrontation with High Uncertainty","date":"2024-06-12","arxiv_id":"2406.07877","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-to-disentangle","slug":"reinforcement-learning-to-disentangle","title":"Reinforcement Learning to Disentangle Multiqubit Quantum States from Partial Observations","date":"2024-06-12","arxiv_id":"2406.07884","repositories_listed":1,"syntology":null},{"url":"/paper/rrls-robust-reinforcement-learning-suite","slug":"rrls-robust-reinforcement-learning-suite","title":"RRLS : Robust Reinforcement Learning Suite","date":"2024-06-12","arxiv_id":"2406.08406","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/rrls-robust-reinforcement-learning-suite#ran","syntology_url":"https://syntology.ai/paper/2406.08406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08406"}},"official":{"repos":["sureli/rrls"],"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/the-max-min-formulation-of-multi-objective","slug":"the-max-min-formulation-of-multi-objective","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","date":"2024-06-12","arxiv_id":"2406.07826","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/the-max-min-formulation-of-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2406.07826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07826"}},"official":{"repos":["giseung-park/maxmin-morl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-objective-reinforcement-learning-from","slug":"multi-objective-reinforcement-learning-from","title":"Multi-objective Reinforcement learning from AI Feedback","date":"2024-06-11","arxiv_id":"2406.07295","repositories_listed":1,"syntology":null},{"url":"/paper/pufferlib-making-reinforcement-learning","slug":"pufferlib-making-reinforcement-learning","title":"PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice","date":"2024-06-11","arxiv_id":"2406.12905","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-aware-spectrum-sharing-in-internet","slug":"semantic-aware-spectrum-sharing-in-internet","title":"Semantic-Aware Spectrum Sharing in Internet of Vehicles Based on Deep Reinforcement Learning","date":"2024-06-11","arxiv_id":"2406.07213","repositories_listed":1,"syntology":null},{"url":"/paper/coprocessor-actor-critic-a-model-based","slug":"coprocessor-actor-critic-a-model-based","title":"Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation","date":"2024-06-10","arxiv_id":"2406.06714","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":3,"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/coprocessor-actor-critic-a-model-based#ran","syntology_url":"https://syntology.ai/paper/2406.06714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06714"}},"official":{"repos":["michelllepan/neural-coprocessors"],"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"]}}}],"record_sha256":"70b6a3a1bb2e4ffd2605edcfce8cdb58084d64c94b7b67a81d2172988067d57a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}