{"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/15","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":15,"pages_in_order":135,"rows_per_page":100,"rows":[1401,1500],"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/14","next":"/task/reinforcement-learning-2/papers/16","papers":[{"url":"/paper/model-based-deep-reinforcement-learning-for-2","slug":"model-based-deep-reinforcement-learning-for-2","title":"Model-based deep reinforcement learning for accelerated learning from flow simulations","date":"2024-02-26","arxiv_id":"2402.16543","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-volt-var-optimization-using-rllib","slug":"scalable-volt-var-optimization-using-rllib","title":"Scalable Volt-VAR Optimization using RLlib-IMPALA Framework: A Reinforcement Learning Approach","date":"2024-02-24","arxiv_id":"2402.15932","repositories_listed":1,"syntology":null},{"url":"/paper/spatially-aware-transformer-memory-for","slug":"spatially-aware-transformer-memory-for","title":"Spatially-Aware Transformer for Embodied Agents","date":"2024-02-23","arxiv_id":"2402.15160","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/spatially-aware-transformer-memory-for#ran","syntology_url":"https://syntology.ai/paper/2402.15160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15160"}},"official":{"repos":["junmokane/spatially-aware-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mentor-guiding-hierarchical-reinforcement","slug":"mentor-guiding-hierarchical-reinforcement","title":"MENTOR: Guiding Hierarchical Reinforcement Learning with Human Feedback and Dynamic Distance Constraint","date":"2024-02-22","arxiv_id":"2402.14244","repositories_listed":1,"syntology":null},{"url":"/paper/transformable-gaussian-reward-function-for","slug":"transformable-gaussian-reward-function-for","title":"Transformable Gaussian Reward Function for Socially-Aware Navigation with Deep Reinforcement Learning","date":"2024-02-22","arxiv_id":"2402.14569","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-reinforcement-learning-agents-with","slug":"enhancing-reinforcement-learning-agents-with","title":"Enhancing Reinforcement Learning Agents with Local Guides","date":"2024-02-21","arxiv_id":"2402.13930","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-based-human-agent","slug":"large-language-model-based-human-agent","title":"Large Language Model-based Human-Agent Collaboration for Complex Task Solving","date":"2024-02-20","arxiv_id":"2402.12914","repositories_listed":1,"syntology":null},{"url":"/paper/more-3s-multimodal-based-offline","slug":"more-3s-multimodal-based-offline","title":"MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces","date":"2024-02-20","arxiv_id":"2402.12845","repositories_listed":1,"syntology":null},{"url":"/paper/tiny-reinforcement-learning-for-quadruped","slug":"tiny-reinforcement-learning-for-quadruped","title":"Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers","date":"2024-02-20","arxiv_id":"2402.13201","repositories_listed":1,"syntology":null},{"url":"/paper/a-critical-evaluation-of-ai-feedback-for","slug":"a-critical-evaluation-of-ai-feedback-for","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","date":"2024-02-19","arxiv_id":"2402.12366","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-critical-evaluation-of-ai-feedback-for#ran","syntology_url":"https://syntology.ai/paper/2402.12366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12366"}},"official":{"repos":["architsharma97/dpo-rlaif"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-data-augmentation-in-deep","slug":"revisiting-data-augmentation-in-deep","title":"Revisiting Data Augmentation in Deep Reinforcement Learning","date":"2024-02-19","arxiv_id":"2402.12181","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":0,"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/revisiting-data-augmentation-in-deep#ran","syntology_url":"https://syntology.ai/paper/2402.12181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12181"}},"official":{"repos":["jianshu-hu/drqv2"],"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/modelling-crypto-markets-by-multi-agent","slug":"modelling-crypto-markets-by-multi-agent","title":"Modelling crypto markets by multi-agent reinforcement learning","date":"2024-02-16","arxiv_id":"2402.10803","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-recurrent-reinforcement-learning","slug":"revisiting-recurrent-reinforcement-learning","title":"Recurrent Reinforcement Learning with Memoroids","date":"2024-02-15","arxiv_id":"2402.09900","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revisiting-recurrent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2402.09900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09900"}},"official":{"repos":["proroklab/memory-monoids"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/risk-sensitive-soft-actor-critic-for-robust","slug":"risk-sensitive-soft-actor-critic-for-robust","title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts","date":"2024-02-15","arxiv_id":"2402.09992","repositories_listed":1,"syntology":null},{"url":"/paper/fgeo-drl-deductive-reasoning-for-geometric","slug":"fgeo-drl-deductive-reasoning-for-geometric","title":"FGeo-DRL: Deductive Reasoning for Geometric Problems through Deep Reinforcement Learning","date":"2024-02-14","arxiv_id":"2402.09051","repositories_listed":1,"syntology":null},{"url":"/paper/a-distributional-analogue-to-the-successor","slug":"a-distributional-analogue-to-the-successor","title":"A Distributional Analogue to the Successor Representation","date":"2024-02-13","arxiv_id":"2402.08530","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/a-distributional-analogue-to-the-successor#ran","syntology_url":"https://syntology.ai/paper/2402.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08530"}},"official":{"repos":["jessefarebro/distributional-sr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/conservative-and-risk-aware-offline-multi","slug":"conservative-and-risk-aware-offline-multi","title":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","date":"2024-02-13","arxiv_id":"2402.08421","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/conservative-and-risk-aware-offline-multi#ran","syntology_url":"https://syntology.ai/paper/2402.08421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08421"}},"official":{"repos":["eslam211/conservative-and-distributional-marl"],"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/hybrid-inverse-reinforcement-learning","slug":"hybrid-inverse-reinforcement-learning","title":"Hybrid Inverse Reinforcement Learning","date":"2024-02-13","arxiv_id":"2402.08848","repositories_listed":1,"syntology":null},{"url":"/paper/mixtures-of-experts-unlock-parameter-scaling","slug":"mixtures-of-experts-unlock-parameter-scaling","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","date":"2024-02-13","arxiv_id":"2402.08609","repositories_listed":1,"syntology":null},{"url":"/paper/a-competition-winning-deep-reinforcement","slug":"a-competition-winning-deep-reinforcement","title":"A Competition Winning Deep Reinforcement Learning Agent in microRTS","date":"2024-02-12","arxiv_id":"2402.08112","repositories_listed":1,"syntology":null},{"url":"/paper/divide-and-conquer-provably-unveiling-the","slug":"divide-and-conquer-provably-unveiling-the","title":"Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning","date":"2024-02-11","arxiv_id":"2402.07182","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":17,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/divide-and-conquer-provably-unveiling-the#ran","syntology_url":"https://syntology.ai/paper/2402.07182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07182"}},"official":{"repos":["wilrop/ipro"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/echoes-of-socratic-doubt-embracing","slug":"echoes-of-socratic-doubt-embracing","title":"Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning","date":"2024-02-11","arxiv_id":"2402.07107","repositories_listed":1,"syntology":null},{"url":"/paper/informativeness-of-reward-functions-in","slug":"informativeness-of-reward-functions-in","title":"Informativeness of Reward Functions in Reinforcement Learning","date":"2024-02-10","arxiv_id":"2402.07019","repositories_listed":1,"syntology":null},{"url":"/paper/solving-deep-reinforcement-learning","slug":"solving-deep-reinforcement-learning","title":"Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks","date":"2024-02-10","arxiv_id":"2402.06912","repositories_listed":1,"syntology":null},{"url":"/paper/deceptive-path-planning-via-reinforcement","slug":"deceptive-path-planning-via-reinforcement","title":"Deceptive Path Planning via Reinforcement Learning with Graph Neural Networks","date":"2024-02-09","arxiv_id":"2402.06552","repositories_listed":1,"syntology":null},{"url":"/paper/predictive-representations-building-blocks-of","slug":"predictive-representations-building-blocks-of","title":"Predictive representations: building blocks of intelligence","date":"2024-02-09","arxiv_id":"2402.06590","repositories_listed":1,"syntology":null},{"url":"/paper/decision-theory-guided-deep-reinforcement","slug":"decision-theory-guided-deep-reinforcement","title":"Decision Theory-Guided Deep Reinforcement Learning for Fast Learning","date":"2024-02-08","arxiv_id":"2402.06023","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-temporally-aware-reinforcement","slug":"discovering-temporally-aware-reinforcement","title":"Discovering Temporally-Aware Reinforcement Learning Algorithms","date":"2024-02-08","arxiv_id":"2402.05828","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"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 1 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/discovering-temporally-aware-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2402.05828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05828"}},"official":{"repos":["EmptyJackson/groove"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-timescale-ensemble-q-learning-for","slug":"multi-timescale-ensemble-q-learning-for","title":"Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization","date":"2024-02-08","arxiv_id":"2402.05476","repositories_listed":1,"syntology":null},{"url":"/paper/training-large-language-models-for-reasoning","slug":"training-large-language-models-for-reasoning","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","date":"2024-02-08","arxiv_id":"2402.05808","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":19,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/training-large-language-models-for-reasoning#ran","syntology_url":"https://syntology.ai/paper/2402.05808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05808"}},"official":{"repos":["woooodyy/llm-reverse-curriculum-rl"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-reinforcement-learning-with-dynamic-1","slug":"deep-reinforcement-learning-with-dynamic-1","title":"Deep Reinforcement Learning with Dynamic Graphs for Adaptive Informative Path Planning","date":"2024-02-07","arxiv_id":"2402.04894","repositories_listed":1,"syntology":null},{"url":"/paper/towards-generalizability-of-multi-agent","slug":"towards-generalizability-of-multi-agent","title":"Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message Passing","date":"2024-02-07","arxiv_id":"2402.05027","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/towards-generalizability-of-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2402.05027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05027"}},"official":{"repos":["jw3il/graph-marl"],"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/entropy-regularized-diffusion-policy-with-q","slug":"entropy-regularized-diffusion-policy-with-q","title":"Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning","date":"2024-02-06","arxiv_id":"2402.04080","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/entropy-regularized-diffusion-policy-with-q#ran","syntology_url":"https://syntology.ai/paper/2402.04080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04080"}},"official":{"repos":["ruoqizzz/entropy-offlineRL"],"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/informed-reinforcement-learning-for-situation","slug":"informed-reinforcement-learning-for-situation","title":"Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions","date":"2024-02-06","arxiv_id":"2402.04168","repositories_listed":1,"syntology":null},{"url":"/paper/logical-specifications-guided-dynamic-task","slug":"logical-specifications-guided-dynamic-task","title":"Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents","date":"2024-02-06","arxiv_id":"2402.03678","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-ensemble-model","slug":"reinforcement-learning-with-ensemble-model","title":"Reinforcement Learning with Ensemble Model Predictive Safety Certification","date":"2024-02-06","arxiv_id":"2402.04182","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":4,"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/reinforcement-learning-with-ensemble-model#ran","syntology_url":"https://syntology.ai/paper/2402.04182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04182"}},"official":{"repos":["svengronauer/x-mpsc"],"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/rl-vlm-f-reinforcement-learning-from-vision","slug":"rl-vlm-f-reinforcement-learning-from-vision","title":"RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback","date":"2024-02-06","arxiv_id":"2402.03681","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-long-delayed-reinforcement-learning","slug":"boosting-long-delayed-reinforcement-learning","title":"Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays","date":"2024-02-05","arxiv_id":"2402.03141","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"phrase":"10 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/boosting-long-delayed-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2402.03141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03141"}},"official":{"repos":["qingyuanwunothing/ad-rl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-tuning-reinforcement-learning-models-is","slug":"fine-tuning-reinforcement-learning-models-is","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","date":"2024-02-05","arxiv_id":"2402.02868","repositories_listed":1,"syntology":null},{"url":"/paper/open-rl-benchmark-comprehensive-tracked","slug":"open-rl-benchmark-comprehensive-tracked","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","date":"2024-02-05","arxiv_id":"2402.03046","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/open-rl-benchmark-comprehensive-tracked#ran","syntology_url":"https://syntology.ai/paper/2402.03046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03046"}},"official":null}},{"url":"/paper/towards-an-information-theoretic-framework-of","slug":"towards-an-information-theoretic-framework-of","title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","date":"2024-02-04","arxiv_id":"2402.02429","repositories_listed":1,"syntology":null},{"url":"/paper/inverse-reinforcement-learning-by-estimating","slug":"inverse-reinforcement-learning-by-estimating","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators","date":"2024-02-02","arxiv_id":"2402.01886","repositories_listed":1,"syntology":null},{"url":"/paper/stepcoder-improve-code-generation-with","slug":"stepcoder-improve-code-generation-with","title":"StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback","date":"2024-02-02","arxiv_id":"2402.01391","repositories_listed":1,"syntology":null},{"url":"/paper/to-the-max-reinventing-reward-in","slug":"to-the-max-reinventing-reward-in","title":"To the Max: Reinventing Reward in Reinforcement Learning","date":"2024-02-02","arxiv_id":"2402.01361","repositories_listed":1,"syntology":null},{"url":"/paper/dense-reward-for-free-in-reinforcement","slug":"dense-reward-for-free-in-reinforcement","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","date":"2024-02-01","arxiv_id":"2402.00782","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/dense-reward-for-free-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2402.00782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00782"}},"official":{"repos":["xanderjc/attention-based-credit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/developing-a-multi-agent-and-self-adaptive","slug":"developing-a-multi-agent-and-self-adaptive","title":"Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management","date":"2024-02-01","arxiv_id":"2402.00515","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-hybrid-modeling-for-flexible","slug":"hierarchical-hybrid-modeling-for-flexible","title":"Deep hybrid models: infer and plan in a dynamic world","date":"2024-02-01","arxiv_id":"2402.10088","repositories_listed":1,"syntology":null},{"url":"/paper/augmenting-replay-in-world-models-for","slug":"augmenting-replay-in-world-models-for","title":"Augmenting Replay in World Models for Continual Reinforcement Learning","date":"2024-01-30","arxiv_id":"2401.16650","repositories_listed":1,"syntology":null},{"url":"/paper/core-towards-scalable-and-efficient-causal","slug":"core-towards-scalable-and-efficient-causal","title":"CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning","date":"2024-01-30","arxiv_id":"2401.16974","repositories_listed":1,"syntology":null},{"url":"/paper/m2curl-sample-efficient-multimodal","slug":"m2curl-sample-efficient-multimodal","title":"M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation","date":"2024-01-30","arxiv_id":"2401.17032","repositories_listed":1,"syntology":null},{"url":"/paper/a-centralized-reinforcement-learning","slug":"a-centralized-reinforcement-learning","title":"LEACH-RLC: Enhancing IoT Data Transmission with Optimized Clustering and Reinforcement Learning","date":"2024-01-28","arxiv_id":"2401.15767","repositories_listed":1,"syntology":null},{"url":"/paper/fully-independent-communication-in-multi","slug":"fully-independent-communication-in-multi","title":"Fully Independent Communication in Multi-Agent Reinforcement Learning","date":"2024-01-26","arxiv_id":"2401.15059","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/fully-independent-communication-in-multi#ran","syntology_url":"https://syntology.ai/paper/2401.15059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15059"}},"official":{"repos":["rafaelmp2/marl-indep-comm"],"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/health-text-simplification-an-annotated","slug":"health-text-simplification-an-annotated","title":"Health Text Simplification: An Annotated Corpus for Digestive Cancer Education and Novel Strategies for Reinforcement Learning","date":"2024-01-26","arxiv_id":"2401.15043","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-hidden-markov","slug":"reinforcement-learning-with-hidden-markov","title":"HMM for Discovering Decision-Making Dynamics Using Reinforcement Learning Experiments","date":"2024-01-25","arxiv_id":"2401.13929","repositories_listed":1,"syntology":null},{"url":"/paper/seer-facilitating-structured-reasoning-and","slug":"seer-facilitating-structured-reasoning-and","title":"SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning","date":"2024-01-24","arxiv_id":"2401.13246","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seer-facilitating-structured-reasoning-and#ran","syntology_url":"https://syntology.ai/paper/2401.13246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13246"}},"official":{"repos":["chen-gx/seer"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/bridging-evolutionary-algorithms-and","slug":"bridging-evolutionary-algorithms-and","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","date":"2024-01-22","arxiv_id":"2401.11963","repositories_listed":1,"syntology":null},{"url":"/paper/self-labeling-the-job-shop-scheduling-problem","slug":"self-labeling-the-job-shop-scheduling-problem","title":"Self-Labeling the Job Shop Scheduling Problem","date":"2024-01-22","arxiv_id":"2401.11849","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/self-labeling-the-job-shop-scheduling-problem#ran","syntology_url":"https://syntology.ai/paper/2401.11849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11849"}},"official":{"repos":["andreacorsini1/selflabelingjobshop"],"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/emergent-dominance-hierarchies-in","slug":"emergent-dominance-hierarchies-in","title":"Emergent Dominance Hierarchies in Reinforcement Learning Agents","date":"2024-01-21","arxiv_id":"2401.12258","repositories_listed":1,"syntology":null},{"url":"/paper/information-theoretic-state-variable","slug":"information-theoretic-state-variable","title":"Information-Theoretic State Variable Selection for Reinforcement Learning","date":"2024-01-21","arxiv_id":"2401.11512","repositories_listed":1,"syntology":null},{"url":"/paper/reframing-offline-reinforcement-learning-as-a","slug":"reframing-offline-reinforcement-learning-as-a","title":"Solving Offline Reinforcement Learning with Decision Tree Regression","date":"2024-01-21","arxiv_id":"2401.11630","repositories_listed":1,"syntology":null},{"url":"/paper/vqc-based-reinforcement-learning-with-data-re","slug":"vqc-based-reinforcement-learning-with-data-re","title":"VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability","date":"2024-01-21","arxiv_id":"2401.11555","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-policy-distance-for-multi-agent","slug":"measuring-policy-distance-for-multi-agent","title":"Measuring Policy Distance for Multi-Agent Reinforcement Learning","date":"2024-01-20","arxiv_id":"2401.11257","repositories_listed":1,"syntology":null},{"url":"/paper/safe-offline-reinforcement-learning-with","slug":"safe-offline-reinforcement-learning-with","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","date":"2024-01-19","arxiv_id":"2401.10700","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":5,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/safe-offline-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2401.10700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10700"}},"official":{"repos":["zhengyinan-air/fisor"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cooperative-edge-caching-based-on-elastic","slug":"cooperative-edge-caching-based-on-elastic","title":"Cooperative Edge Caching Based on Elastic Federated and Multi-Agent Deep Reinforcement Learning in Next-Generation Network","date":"2024-01-18","arxiv_id":"2401.09886","repositories_listed":1,"syntology":null},{"url":"/paper/langprop-a-code-optimization-framework-using","slug":"langprop-a-code-optimization-framework-using","title":"LangProp: A code optimization framework using Large Language Models applied to driving","date":"2024-01-18","arxiv_id":"2401.10314","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/langprop-a-code-optimization-framework-using#ran","syntology_url":"https://syntology.ai/paper/2401.10314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10314"}},"official":{"repos":["shuishida/langprop"],"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/deployable-reinforcement-learning-with","slug":"deployable-reinforcement-learning-with","title":"Deployable Reinforcement Learning with Variable Control Rate","date":"2024-01-17","arxiv_id":"2401.09286","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deployable-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2401.09286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09286"}},"official":{"repos":["alpaficia/SEAC_Pytorch_release"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sharing-knowledge-in-multi-task-deep-1","slug":"sharing-knowledge-in-multi-task-deep-1","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","date":"2024-01-17","arxiv_id":"2401.09561","repositories_listed":1,"syntology":null},{"url":"/paper/aquarium-a-comprehensive-framework-for","slug":"aquarium-a-comprehensive-framework-for","title":"Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics through Multi-Agent Reinforcement Learning Algorithms","date":"2024-01-13","arxiv_id":"2401.07056","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-reinforcement-learning-with-a","slug":"personalized-reinforcement-learning-with-a","title":"Personalized Reinforcement Learning with a Budget of Policies","date":"2024-01-12","arxiv_id":"2401.06514","repositories_listed":1,"syntology":null},{"url":"/paper/striking-a-balance-in-fairness-for-dynamic","slug":"striking-a-balance-in-fairness-for-dynamic","title":"Striking a Balance in Fairness for Dynamic Systems Through Reinforcement Learning","date":"2024-01-12","arxiv_id":"2401.06318","repositories_listed":1,"syntology":null},{"url":"/paper/an-experimental-evaluation-of-deep","slug":"an-experimental-evaluation-of-deep","title":"An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control","date":"2024-01-11","arxiv_id":"2401.05737","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-concept-bottlenecks-to-align","slug":"interpretable-concept-bottlenecks-to-align","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","date":"2024-01-11","arxiv_id":"2401.05821","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpretable-concept-bottlenecks-to-align#ran","syntology_url":"https://syntology.ai/paper/2401.05821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05821"}},"official":{"repos":["k4ntz/scobots"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-in-uncertain","slug":"safe-reinforcement-learning-in-uncertain","title":"Safe reinforcement learning in uncertain contexts","date":"2024-01-11","arxiv_id":"2401.05876","repositories_listed":1,"syntology":null},{"url":"/paper/secrets-of-rlhf-in-large-language-models-part-1","slug":"secrets-of-rlhf-in-large-language-models-part-1","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","date":"2024-01-11","arxiv_id":"2401.06080","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/secrets-of-rlhf-in-large-language-models-part-1#ran","syntology_url":"https://syntology.ai/paper/2401.06080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06080"}},"official":{"repos":["openlmlab/moss-rlhf"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-distributional-reward-critic-architecture","slug":"the-distributional-reward-critic-architecture","title":"The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards","date":"2024-01-11","arxiv_id":"2401.05710","repositories_listed":1,"syntology":null},{"url":"/paper/human-as-ai-mentor-enhanced-human-in-the-loop","slug":"human-as-ai-mentor-enhanced-human-in-the-loop","title":"HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving","date":"2024-01-06","arxiv_id":"2401.03160","repositories_listed":1,"syntology":null},{"url":"/paper/spqr-controlling-q-ensemble-independence-with-1","slug":"spqr-controlling-q-ensemble-independence-with-1","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","date":"2024-01-06","arxiv_id":"2401.03137","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/spqr-controlling-q-ensemble-independence-with-1#ran","syntology_url":"https://syntology.ai/paper/2401.03137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03137"}},"official":{"repos":["dohyeoklee/SPQR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-regularized-offline-multi-objective","slug":"policy-regularized-offline-multi-objective","title":"Policy-regularized Offline Multi-objective Reinforcement Learning","date":"2024-01-04","arxiv_id":"2401.02244","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"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) · 0 unverified","sample_list":"/paper/policy-regularized-offline-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2401.02244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02244"}},"official":{"repos":["qianlin04/prmorl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/data-assimilation-in-chaotic-systems-using","slug":"data-assimilation-in-chaotic-systems-using","title":"Data Assimilation in Chaotic Systems Using Deep Reinforcement Learning","date":"2024-01-01","arxiv_id":"2401.00916","repositories_listed":1,"syntology":null},{"url":"/paper/ensemble-diversity-facilitates-adversarial","slug":"ensemble-diversity-facilitates-adversarial","title":"Ensemble Diversity Facilitates Adversarial Transferability","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-unsupervised-hierarchical","slug":"improving-unsupervised-hierarchical","title":"Improving Unsupervised Hierarchical Representation with Reinforcement Learning","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/online-symbolic-music-alignment-with-offline","slug":"online-symbolic-music-alignment-with-offline","title":"Online Symbolic Music Alignment with Offline Reinforcement Learning","date":"2023-12-31","arxiv_id":"2401.00466","repositories_listed":1,"syntology":null},{"url":"/paper/causal-state-distillation-for-explainable","slug":"causal-state-distillation-for-explainable","title":"Causal State Distillation for Explainable Reinforcement Learning","date":"2023-12-30","arxiv_id":"2401.00104","repositories_listed":1,"syntology":null},{"url":"/paper/laboratory-experiments-of-model-based","slug":"laboratory-experiments-of-model-based","title":"Laboratory Experiments of Model-based Reinforcement Learning for Adaptive Optics Control","date":"2023-12-30","arxiv_id":"2401.00242","repositories_listed":1,"syntology":null},{"url":"/paper/can-active-sampling-reduce-causal-confusion","slug":"can-active-sampling-reduce-causal-confusion","title":"Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?","date":"2023-12-28","arxiv_id":"2312.17168","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-active-sampling-reduce-causal-confusion#ran","syntology_url":"https://syntology.ai/paper/2312.17168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17168"}},"official":{"repos":["gunshi/offline_active_rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalizable-visual-reinforcement-learning","slug":"generalizable-visual-reinforcement-learning","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","date":"2023-12-28","arxiv_id":"2312.17116","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generalizable-visual-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2312.17116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17116"}},"official":{"repos":["wadiuvatzy/sam-g"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-trajectory-constrained-exploration","slug":"adaptive-trajectory-constrained-exploration","title":"Adaptive trajectory-constrained exploration strategy for deep reinforcement learning","date":"2023-12-27","arxiv_id":"2312.16456","repositories_listed":1,"syntology":null},{"url":"/paper/generalizable-task-representation-learning-1","slug":"generalizable-task-representation-learning-1","title":"Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations","date":"2023-12-26","arxiv_id":"2312.15909","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/generalizable-task-representation-learning-1#ran","syntology_url":"https://syntology.ai/paper/2312.15909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15909"}},"official":{"repos":["lamda-rl/gentle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/optimistic-and-pessimistic-actor-in-rl","slug":"optimistic-and-pessimistic-actor-in-rl","title":"Efficient Reinforcement Learning via Decoupling Exploration and Utilization","date":"2023-12-26","arxiv_id":"2312.15965","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-unlearning","slug":"reinforcement-unlearning","title":"Reinforcement Unlearning","date":"2023-12-26","arxiv_id":"2312.15910","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-unlearning#ran","syntology_url":"https://syntology.ai/paper/2312.15910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15910"}},"official":{"repos":["cp-lab-uts/reinforcement-unlearning"],"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/context-aware-communication-for-multi-agent","slug":"context-aware-communication-for-multi-agent","title":"Context-aware Communication for Multi-agent Reinforcement Learning","date":"2023-12-25","arxiv_id":"2312.15600","repositories_listed":1,"syntology":null},{"url":"/paper/xuance-a-comprehensive-and-unified-deep","slug":"xuance-a-comprehensive-and-unified-deep","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","date":"2023-12-25","arxiv_id":"2312.16248","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/xuance-a-comprehensive-and-unified-deep#ran","syntology_url":"https://syntology.ai/paper/2312.16248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16248"}},"official":{"repos":["agi-brain/xuance"],"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/iterative-prompt-relabeling-for-diffusion","slug":"iterative-prompt-relabeling-for-diffusion","title":"Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training","date":"2023-12-23","arxiv_id":"2312.16204","repositories_listed":1,"syntology":null},{"url":"/paper/critic-guided-decision-transformer-for","slug":"critic-guided-decision-transformer-for","title":"Critic-Guided Decision Transformer for Offline Reinforcement Learning","date":"2023-12-21","arxiv_id":"2312.13716","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"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) · 4 unverified","sample_list":"/paper/critic-guided-decision-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2312.13716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13716"}},"official":{"repos":["sharkwyf/cgdt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-reinforcement-learning-for","slug":"in-context-reinforcement-learning-for","title":"In-Context Reinforcement Learning for Variable Action Spaces","date":"2023-12-20","arxiv_id":"2312.13327","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/in-context-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2312.13327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13327"}},"official":{"repos":["corl-team/headless-ad"],"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/openrl-a-unified-reinforcement-learning","slug":"openrl-a-unified-reinforcement-learning","title":"OpenRL: A Unified Reinforcement Learning Framework","date":"2023-12-20","arxiv_id":"2312.16189","repositories_listed":1,"syntology":null},{"url":"/paper/rfrl-gym-a-reinforcement-learning-testbed-for","slug":"rfrl-gym-a-reinforcement-learning-testbed-for","title":"RFRL Gym: A Reinforcement Learning Testbed for Cognitive Radio Applications","date":"2023-12-20","arxiv_id":"2401.05406","repositories_listed":1,"syntology":null},{"url":"/paper/badrl-sparse-targeted-backdoor-attack-against","slug":"badrl-sparse-targeted-backdoor-attack-against","title":"BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning","date":"2023-12-19","arxiv_id":"2312.12585","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/badrl-sparse-targeted-backdoor-attack-against#ran","syntology_url":"https://syntology.ai/paper/2312.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12585"}},"official":{"repos":["7777777cc/code"],"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/emergence-of-in-context-reinforcement","slug":"emergence-of-in-context-reinforcement","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","date":"2023-12-19","arxiv_id":"2312.12275","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/emergence-of-in-context-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2312.12275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12275"}},"official":{"repos":["corl-team/ad-eps"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-the-performance-and-reliability","slug":"investigating-the-performance-and-reliability","title":"Investigating the Performance and Reliability, of the Q-Learning Algorithm in Various Unknown Environments","date":"2023-12-19","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"215c336a8a0acda2352ea85e7759de4c2393515d58aa3c78b863087df8da7212","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}