{"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/16","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":16,"pages_in_order":132,"rows_per_page":100,"rows":[1501,1600],"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/15","next":"/task/reinforcement-learning/papers/17","papers":[{"url":"/paper/prior-constraints-based-reward-model-training","slug":"prior-constraints-based-reward-model-training","title":"Prior Constraints-based Reward Model Training for Aligning Large Language Models","date":"2024-04-01","arxiv_id":"2404.00978","repositories_listed":1,"syntology":null},{"url":"/paper/decision-mamba-reinforcement-learning-via","slug":"decision-mamba-reinforcement-learning-via","title":"Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces","date":"2024-03-29","arxiv_id":"2403.19925","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/decision-mamba-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2403.19925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19925"}},"official":{"repos":["toshihiro-ota/decision-mamba"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mol-air-molecular-reinforcement-learning-with","slug":"mol-air-molecular-reinforcement-learning-with","title":"Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Rewards for Goal-directed Molecular Generation","date":"2024-03-29","arxiv_id":"2403.20109","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-length-from-quality-in-direct","slug":"disentangling-length-from-quality-in-direct","title":"Disentangling Length from Quality in Direct Preference Optimization","date":"2024-03-28","arxiv_id":"2403.19159","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disentangling-length-from-quality-in-direct#ran","syntology_url":"https://syntology.ai/paper/2403.19159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19159"}},"official":null}},{"url":"/paper/the-new-agronomists-language-models-are","slug":"the-new-agronomists-language-models-are","title":"The New Agronomists: Language Models are Experts in Crop Management","date":"2024-03-28","arxiv_id":"2403.19839","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-symmetry-in-dynamics-for-model","slug":"exploiting-symmetry-in-dynamics-for-model","title":"Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards","date":"2024-03-27","arxiv_id":"2403.19024","repositories_listed":1,"syntology":null},{"url":"/paper/from-two-dimensional-to-three-dimensional-1","slug":"from-two-dimensional-to-three-dimensional-1","title":"From Two-Dimensional to Three-Dimensional Environment with Q-Learning: Modeling Autonomous Navigation with Reinforcement Learning and no Libraries","date":"2024-03-27","arxiv_id":"2403.18219","repositories_listed":1,"syntology":null},{"url":"/paper/compressed-federated-reinforcement-learning","slug":"compressed-federated-reinforcement-learning","title":"Compressed Federated Reinforcement Learning with a Generative Model","date":"2024-03-26","arxiv_id":"2404.10635","repositories_listed":1,"syntology":null},{"url":"/paper/imitating-cost-constrained-behaviors-in","slug":"imitating-cost-constrained-behaviors-in","title":"Imitating Cost-Constrained Behaviors in Reinforcement Learning","date":"2024-03-26","arxiv_id":"2403.17456","repositories_listed":1,"syntology":null},{"url":"/paper/clha-a-simple-yet-effective-contrastive","slug":"clha-a-simple-yet-effective-contrastive","title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","date":"2024-03-25","arxiv_id":"2403.16649","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clha-a-simple-yet-effective-contrastive#ran","syntology_url":"https://syntology.ai/paper/2403.16649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16649"}},"official":{"repos":["calubkk/clha"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/physics-informed-rl-for-maximal-safety","slug":"physics-informed-rl-for-maximal-safety","title":"Physics-informed RL for Maximal Safety Probability Estimation","date":"2024-03-25","arxiv_id":"2403.16391","repositories_listed":1,"syntology":null},{"url":"/paper/rl-for-consistency-models-faster-reward","slug":"rl-for-consistency-models-faster-reward","title":"RL for Consistency Models: Faster Reward Guided Text-to-Image Generation","date":"2024-03-25","arxiv_id":"2404.03673","repositories_listed":1,"syntology":null},{"url":"/paper/a-reinforcement-learning-guided-hybrid","slug":"a-reinforcement-learning-guided-hybrid","title":"A reinforcement learning guided hybrid evolutionary algorithm for the latency location routing problem","date":"2024-03-21","arxiv_id":"2403.14405","repositories_listed":1,"syntology":null},{"url":"/paper/reactor-optimization-benchmark-by","slug":"reactor-optimization-benchmark-by","title":"Reactor Optimization Benchmark by Reinforcement Learning","date":"2024-03-21","arxiv_id":"2403.14273","repositories_listed":1,"syntology":null},{"url":"/paper/towards-principled-representation-learning-1","slug":"towards-principled-representation-learning-1","title":"Towards Principled Representation Learning from Videos for Reinforcement Learning","date":"2024-03-20","arxiv_id":"2403.13765","repositories_listed":1,"syntology":null},{"url":"/paper/insight-end-to-end-neuro-symbolic-visual","slug":"insight-end-to-end-neuro-symbolic-visual","title":"End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations","date":"2024-03-19","arxiv_id":"2403.12451","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/insight-end-to-end-neuro-symbolic-visual#ran","syntology_url":"https://syntology.ai/paper/2403.12451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12451"}},"official":{"repos":["liruiluo/nsrl-vision-pub"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-bifurcation-in-safe-reinforcement","slug":"policy-bifurcation-in-safe-reinforcement","title":"Policy Bifurcation in Safe Reinforcement Learning","date":"2024-03-19","arxiv_id":"2403.12847","repositories_listed":1,"syntology":null},{"url":"/paper/decomposing-control-lyapunov-functions-for","slug":"decomposing-control-lyapunov-functions-for","title":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","date":"2024-03-18","arxiv_id":"2403.12210","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-from-delayed","slug":"reinforcement-learning-from-delayed","title":"Reinforcement Learning from Delayed Observations via World Models","date":"2024-03-18","arxiv_id":"2403.12309","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/reinforcement-learning-from-delayed#ran","syntology_url":"https://syntology.ai/paper/2403.12309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12309"}},"official":{"repos":["indylab/delayeddreamer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-with-token-level","slug":"reinforcement-learning-with-token-level","title":"Reinforcement Learning with Token-level Feedback for Controllable Text Generation","date":"2024-03-18","arxiv_id":"2403.11558","repositories_listed":1,"syntology":null},{"url":"/paper/single-agent-actor-critic-for-decentralized","slug":"single-agent-actor-critic-for-decentralized","title":"Agent-Agnostic Centralized Training for Decentralized Multi-Agent Cooperative Driving","date":"2024-03-18","arxiv_id":"2403.11914","repositories_listed":1,"syntology":null},{"url":"/paper/explorer-exploration-guided-reasoning-for","slug":"explorer-exploration-guided-reasoning-for","title":"EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning","date":"2024-03-15","arxiv_id":"2403.10692","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-symmetries-in-gaits-for","slug":"leveraging-symmetries-in-gaits-for","title":"Symmetry-Guided Reinforcement Learning for Versatile Quadrupedal Gait Generation","date":"2024-03-15","arxiv_id":"2403.10723","repositories_listed":1,"syntology":null},{"url":"/paper/quality-diversity-actor-critic-learning-high","slug":"quality-diversity-actor-critic-learning-high","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","date":"2024-03-15","arxiv_id":"2403.09930","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quality-diversity-actor-critic-learning-high#ran","syntology_url":"https://syntology.ai/paper/2403.09930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09930"}},"official":{"repos":["adaptive-intelligent-robotics/qdac"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mamba-an-effective-world-model-approach-for","slug":"mamba-an-effective-world-model-approach-for","title":"MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09859","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mamba-an-effective-world-model-approach-for#ran","syntology_url":"https://syntology.ai/paper/2403.09859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09859"}},"official":{"repos":["zoharri/mamba"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sindy-rl-interpretable-and-efficient-model","slug":"sindy-rl-interpretable-and-efficient-model","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09110","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sindy-rl-interpretable-and-efficient-model#ran","syntology_url":"https://syntology.ai/paper/2403.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09110"}},"official":{"repos":["nzolman/sindy-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-watermark-llm-generated-text-via","slug":"learning-to-watermark-llm-generated-text-via","title":"Learning to Watermark LLM-generated Text via Reinforcement Learning","date":"2024-03-13","arxiv_id":"2403.10553","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-watermark-llm-generated-text-via#ran","syntology_url":"https://syntology.ai/paper/2403.10553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10553"}},"official":{"repos":["xiaojunxu/learning-to-watermark-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/teams-rl-teaching-llms-to-teach-themselves","slug":"teams-rl-teaching-llms-to-teach-themselves","title":"TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning","date":"2024-03-13","arxiv_id":"2403.08694","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-gain-scheduling-using-reinforcement","slug":"adaptive-gain-scheduling-using-reinforcement","title":"Adaptive Gain Scheduling using Reinforcement Learning for Quadcopter Control","date":"2024-03-12","arxiv_id":"2403.07216","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-online-exploration-via-coverability","slug":"scalable-online-exploration-via-coverability","title":"Scalable Online Exploration via Coverability","date":"2024-03-11","arxiv_id":"2403.06571","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scalable-online-exploration-via-coverability#ran","syntology_url":"https://syntology.ai/paper/2403.06571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06571"}},"official":{"repos":["philip-amortila/l1-coverability"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-gptrec-with-beyond-accuracy-goals","slug":"aligning-gptrec-with-beyond-accuracy-goals","title":"Aligning GPTRec with Beyond-Accuracy Goals with Reinforcement Learning","date":"2024-03-07","arxiv_id":"2403.04875","repositories_listed":1,"syntology":null},{"url":"/paper/sampling-based-safe-reinforcement-learning","slug":"sampling-based-safe-reinforcement-learning","title":"Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems","date":"2024-03-06","arxiv_id":"2403.04007","repositories_listed":1,"syntology":null},{"url":"/paper/pps-qmix-periodically-parameter-sharing-for","slug":"pps-qmix-periodically-parameter-sharing-for","title":"PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning","date":"2024-03-05","arxiv_id":"2403.02635","repositories_listed":1,"syntology":null},{"url":"/paper/preventing-reward-hacking-with-occupancy","slug":"preventing-reward-hacking-with-occupancy","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","date":"2024-03-05","arxiv_id":"2403.03185","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/preventing-reward-hacking-with-occupancy#ran","syntology_url":"https://syntology.ai/paper/2403.03185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03185"}},"official":{"repos":["cassidylaidlaw/orpo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/splagger-split-aggregation-for-meta","slug":"splagger-split-aggregation-for-meta","title":"SplAgger: Split Aggregation for Meta-Reinforcement Learning","date":"2024-03-05","arxiv_id":"2403.03020","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/splagger-split-aggregation-for-meta#ran","syntology_url":"https://syntology.ai/paper/2403.03020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03020"}},"official":{"repos":["jacooba/hyper"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-episodic-memory-utilization-of","slug":"efficient-episodic-memory-utilization-of","title":"Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01112","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/efficient-episodic-memory-utilization-of#ran","syntology_url":"https://syntology.ai/paper/2403.01112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01112"}},"official":{"repos":["hyunghona/emu"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/snapshot-reinforcement-learning-leveraging","slug":"snapshot-reinforcement-learning-leveraging","title":"Snapshot Reinforcement Learning: Leveraging Prior Trajectories for Efficiency","date":"2024-03-01","arxiv_id":"2403.00673","repositories_listed":1,"syntology":null},{"url":"/paper/a-model-based-approach-for-improving","slug":"a-model-based-approach-for-improving","title":"A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations","date":"2024-02-29","arxiv_id":"2402.18836","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-iterative-combinatorial-auction","slug":"understanding-iterative-combinatorial-auction","title":"Understanding Iterative Combinatorial Auction Designs via Multi-Agent Reinforcement Learning","date":"2024-02-29","arxiv_id":"2402.19420","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-iterative-combinatorial-auction#ran","syntology_url":"https://syntology.ai/paper/2402.19420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19420"}},"official":{"repos":["newmanne/open_spiel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-preference-based","slug":"sample-efficient-preference-based","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","date":"2024-02-28","arxiv_id":"2402.17975","repositories_listed":1,"syntology":null},{"url":"/paper/rime-robust-preference-based-reinforcement","slug":"rime-robust-preference-based-reinforcement","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","date":"2024-02-27","arxiv_id":"2402.17257","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rime-robust-preference-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2402.17257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17257"}},"official":{"repos":["cjreinforce/rime_icml2024"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-zero-shot-reinforcement-learning","slug":"unsupervised-zero-shot-reinforcement-learning","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","date":"2024-02-27","arxiv_id":"2402.17135","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unsupervised-zero-shot-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2402.17135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17135"}},"official":{"repos":["kvfrans/fre"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/craftax-a-lightning-fast-benchmark-for-open","slug":"craftax-a-lightning-fast-benchmark-for-open","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16801","repositories_listed":1,"syntology":{"n":16,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/craftax-a-lightning-fast-benchmark-for-open#ran","syntology_url":"https://syntology.ai/paper/2402.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16801"}},"official":{"repos":["michaeltmatthews/craftax"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/feedback-efficient-online-fine-tuning-of","slug":"feedback-efficient-online-fine-tuning-of","title":"Feedback Efficient Online Fine-Tuning of Diffusion Models","date":"2024-02-26","arxiv_id":"2402.16359","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/feedback-efficient-online-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2402.16359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16359"}},"official":null}},{"url":"/paper/flexible-robust-beamforming-for-multibeam","slug":"flexible-robust-beamforming-for-multibeam","title":"Flexible Robust Beamforming for Multibeam Satellite Downlink using Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16563","repositories_listed":1,"syntology":null},{"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/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/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/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/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/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/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/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/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/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"]}}}],"record_sha256":"6ff4c4cee16628b0039594ee978ad56b141eea78d50d8b2b1ed4b2393eb4bf89","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}