{"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-1/papers/ran/2","list_of":"/task/reinforcement-learning-1","task":"Reinforcement Learning (RL)","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":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":2,"pages_in_order":15,"rows_per_page":100,"rows":[101,200],"of":1416,"counts":{"archive_papers_tagged":15113,"with_a_code_link":4749,"where_syntology_ran_a_sample":1416,"not_listed_spam_title":0,"listed":15113,"listed_where_code_ran":1416,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1186,"every_run_a_failure_of_syntologys_instrument":230,"listed_with_a_run_with_no_instrument_failure":1186,"listed_every_run_a_failure_of_syntologys_instrument":230,"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-1/papers/ran/1","prev":"/task/reinforcement-learning-1/papers/ran/1","next":"/task/reinforcement-learning-1/papers/ran/3","papers":[{"url":"/paper/handling-delay-in-real-time-reinforcement","slug":"handling-delay-in-real-time-reinforcement","title":"Handling Delay in Real-Time Reinforcement Learning","date":"2025-03-30","arxiv_id":"2503.23478","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/handling-delay-in-real-time-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2503.23478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23478"}},"official":{"repos":["avecplezir/realtime-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/ui-r1-enhancing-action-prediction-of-gui","slug":"ui-r1-enhancing-action-prediction-of-gui","title":"UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning","date":"2025-03-27","arxiv_id":"2503.21620","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/ui-r1-enhancing-action-prediction-of-gui#ran","syntology_url":"https://syntology.ai/paper/2503.21620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21620"}},"official":{"repos":["lll6gg/ui-r1"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/video-r1-reinforcing-video-reasoning-in-mllms","slug":"video-r1-reinforcing-video-reasoning-in-mllms","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","date":"2025-03-27","arxiv_id":"2503.21776","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/video-r1-reinforcing-video-reasoning-in-mllms#ran","syntology_url":"https://syntology.ai/paper/2503.21776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21776"}},"official":{"repos":["tulerfeng/video-r1"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/understanding-r1-zero-like-training-a","slug":"understanding-r1-zero-like-training-a","title":"Understanding R1-Zero-Like Training: A Critical Perspective","date":"2025-03-26","arxiv_id":"2503.20783","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-r1-zero-like-training-a#ran","syntology_url":"https://syntology.ai/paper/2503.20783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20783"}},"official":{"repos":["sail-sg/understand-r1-zero"],"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","unlocated"]}}},{"url":"/paper/metaspatial-reinforcing-3d-spatial-reasoning","slug":"metaspatial-reinforcing-3d-spatial-reasoning","title":"MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse","date":"2025-03-24","arxiv_id":"2503.18470","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/metaspatial-reinforcing-3d-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2503.18470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18470"}},"official":{"repos":["pzyseere/metaspatial"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/simplerl-zoo-investigating-and-taming-zero","slug":"simplerl-zoo-investigating-and-taming-zero","title":"SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild","date":"2025-03-24","arxiv_id":"2503.18892","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/simplerl-zoo-investigating-and-taming-zero#ran","syntology_url":"https://syntology.ai/paper/2503.18892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18892"}},"official":null}},{"url":"/paper/trajectory-balance-with-asynchrony-decoupling","slug":"trajectory-balance-with-asynchrony-decoupling","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","date":"2025-03-24","arxiv_id":"2503.18929","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/trajectory-balance-with-asynchrony-decoupling#ran","syntology_url":"https://syntology.ai/paper/2503.18929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18929"}},"official":null}},{"url":"/paper/surrogate-learning-in-meta-black-box","slug":"surrogate-learning-in-meta-black-box","title":"Surrogate Learning in Meta-Black-Box Optimization: A Preliminary Study","date":"2025-03-23","arxiv_id":"2503.18060","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/surrogate-learning-in-meta-black-box#ran","syntology_url":"https://syntology.ai/paper/2503.18060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18060"}},"official":{"repos":["gmc-drl/surr-rlde","GMC-DRL/MetaBox"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/causally-aligned-curriculum-learning","slug":"causally-aligned-curriculum-learning","title":"Causally Aligned Curriculum Learning","date":"2025-03-21","arxiv_id":"2503.16799","repositories_listed":0,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/causally-aligned-curriculum-learning#ran","syntology_url":"https://syntology.ai/paper/2503.16799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16799"}},"official":null}},{"url":"/paper/openvlthinker-an-early-exploration-to-complex","slug":"openvlthinker-an-early-exploration-to-complex","title":"OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement","date":"2025-03-21","arxiv_id":"2503.17352","repositories_listed":1,"syntology":{"n":21,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/openvlthinker-an-early-exploration-to-complex#ran","syntology_url":"https://syntology.ai/paper/2503.17352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.17352"}},"official":{"repos":["yihedeng9/openvlthinker"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/cls-rl-image-classification-with-rule-based","slug":"cls-rl-image-classification-with-rule-based","title":"Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning","date":"2025-03-20","arxiv_id":"2503.16188","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cls-rl-image-classification-with-rule-based#ran","syntology_url":"https://syntology.ai/paper/2503.16188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16188"}},"official":{"repos":["minglllli/CLS-RL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-for-reasoning-in-small","slug":"reinforcement-learning-for-reasoning-in-small","title":"Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't","date":"2025-03-20","arxiv_id":"2503.16219","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reinforcement-learning-for-reasoning-in-small#ran","syntology_url":"https://syntology.ai/paper/2503.16219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16219"}},"official":{"repos":["knoveleng/open-rs"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cosmos-reason1-from-physical-common-sense-to","slug":"cosmos-reason1-from-physical-common-sense-to","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","date":"2025-03-18","arxiv_id":"2503.15558","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/cosmos-reason1-from-physical-common-sense-to#ran","syntology_url":"https://syntology.ai/paper/2503.15558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15558"}},"official":{"repos":["nvidia-cosmos/cosmos-reason1"],"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/reinforcement-learning-outperforms-supervised","slug":"reinforcement-learning-outperforms-supervised","title":"Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering","date":"2025-03-14","arxiv_id":"2503.11197","repositories_listed":2,"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/reinforcement-learning-outperforms-supervised#ran","syntology_url":"https://syntology.ai/paper/2503.11197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.11197"}},"official":{"repos":["xiaomi-research/r1-aqa","huggingface.co/mispeech/r1-aqa"],"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/towards-better-alignment-training-diffusion","slug":"towards-better-alignment-training-diffusion","title":"Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards","date":"2025-03-14","arxiv_id":"2503.11240","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/towards-better-alignment-training-diffusion#ran","syntology_url":"https://syntology.ai/paper/2503.11240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.11240"}},"official":{"repos":["hu-zijing/b2-diffurl"],"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/search-r1-training-llms-to-reason-and","slug":"search-r1-training-llms-to-reason-and","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","date":"2025-03-12","arxiv_id":"2503.09516","repositories_listed":3,"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":1,"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/search-r1-training-llms-to-reason-and#ran","syntology_url":"https://syntology.ai/paper/2503.09516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09516"}},"official":{"repos":["petergriffinjin/search-r1"],"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","unlocated"]}}},{"url":"/paper/regulatory-dna-sequence-design-with","slug":"regulatory-dna-sequence-design-with","title":"Regulatory DNA sequence Design with Reinforcement Learning","date":"2025-03-11","arxiv_id":"2503.07981","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/regulatory-dna-sequence-design-with#ran","syntology_url":"https://syntology.ai/paper/2503.07981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07981"}},"official":{"repos":["yangzhao1230/taco"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lmm-r1-empowering-3b-lmms-with-strong","slug":"lmm-r1-empowering-3b-lmms-with-strong","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","date":"2025-03-10","arxiv_id":"2503.07536","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/lmm-r1-empowering-3b-lmms-with-strong#ran","syntology_url":"https://syntology.ai/paper/2503.07536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07536"}},"official":null}},{"url":"/paper/alphadrive-unleashing-the-power-of-vlms-in","slug":"alphadrive-unleashing-the-power-of-vlms-in","title":"AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning","date":"2025-03-10","arxiv_id":"2503.07608","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alphadrive-unleashing-the-power-of-vlms-in#ran","syntology_url":"https://syntology.ai/paper/2503.07608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07608"}},"official":{"repos":["hustvl/alphadrive"],"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/agent-models-internalizing-chain-of-action","slug":"agent-models-internalizing-chain-of-action","title":"Agent models: Internalizing Chain-of-Action Generation into Reasoning models","date":"2025-03-09","arxiv_id":"2503.06580","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/agent-models-internalizing-chain-of-action#ran","syntology_url":"https://syntology.ai/paper/2503.06580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06580"}},"official":{"repos":["adam-bjtu/autocoa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/automated-proof-of-polynomial-inequalities","slug":"automated-proof-of-polynomial-inequalities","title":"Automated Proof of Polynomial Inequalities via Reinforcement Learning","date":"2025-03-09","arxiv_id":"2503.06592","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/automated-proof-of-polynomial-inequalities#ran","syntology_url":"https://syntology.ai/paper/2503.06592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06592"}},"official":{"repos":["blliu6/appirl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/r1-searcher-incentivizing-the-search","slug":"r1-searcher-incentivizing-the-search","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","date":"2025-03-07","arxiv_id":"2503.05592","repositories_listed":5,"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":0,"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/r1-searcher-incentivizing-the-search#ran","syntology_url":"https://syntology.ai/paper/2503.05592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.05592"}},"official":null}},{"url":"/paper/cognitive-behaviors-that-enable-self","slug":"cognitive-behaviors-that-enable-self","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","date":"2025-03-03","arxiv_id":"2503.01307","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cognitive-behaviors-that-enable-self#ran","syntology_url":"https://syntology.ai/paper/2503.01307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01307"}},"official":{"repos":["kanishkg/cognitive-behaviors"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/discrete-codebook-world-models-for-continuous","slug":"discrete-codebook-world-models-for-continuous","title":"Discrete Codebook World Models for Continuous Control","date":"2025-03-01","arxiv_id":"2503.00653","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/discrete-codebook-world-models-for-continuous#ran","syntology_url":"https://syntology.ai/paper/2503.00653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00653"}},"official":{"repos":["aidanscannell/dcmpc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-with-combinatorial-1","slug":"reinforcement-learning-with-combinatorial-1","title":"Reinforcement learning with combinatorial actions for coupled restless bandits","date":"2025-03-01","arxiv_id":"2503.01919","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/reinforcement-learning-with-combinatorial-1#ran","syntology_url":"https://syntology.ai/paper/2503.01919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01919"}},"official":{"repos":["lily-x/combinatorial-rmab"],"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/deepretrieval-powerful-query-generation-for","slug":"deepretrieval-powerful-query-generation-for","title":"DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning","date":"2025-02-28","arxiv_id":"2503.00223","repositories_listed":1,"syntology":{"n":25,"n_ran":24,"n_constructed":0,"n_ran_checked":23,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":23,"n_pointer_only":0,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deepretrieval-powerful-query-generation-for#ran","syntology_url":"https://syntology.ai/paper/2503.00223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00223"}},"official":{"repos":["pat-jj/deepretrieval"],"state":"official (archive's flag): 24 ran","n_ran":24,"n_constructed":0,"n_ran_no_instrument_failure":23,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vem-environment-free-exploration-for-training","slug":"vem-environment-free-exploration-for-training","title":"VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model","date":"2025-02-26","arxiv_id":"2502.18906","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vem-environment-free-exploration-for-training#ran","syntology_url":"https://syntology.ai/paper/2502.18906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18906"}},"official":null}},{"url":"/paper/big-math-a-large-scale-high-quality-math","slug":"big-math-a-large-scale-high-quality-math","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","date":"2025-02-24","arxiv_id":"2502.17387","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/big-math-a-large-scale-high-quality-math#ran","syntology_url":"https://syntology.ai/paper/2502.17387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.17387"}},"official":{"repos":["synthlabsai/big-math"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperspherical-normalization-for-scalable","slug":"hyperspherical-normalization-for-scalable","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","date":"2025-02-21","arxiv_id":"2502.15280","repositories_listed":0,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":1,"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; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hyperspherical-normalization-for-scalable#ran","syntology_url":"https://syntology.ai/paper/2502.15280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15280"}},"official":null}},{"url":"/paper/logic-rl-unleashing-llm-reasoning-with-rule","slug":"logic-rl-unleashing-llm-reasoning-with-rule","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","date":"2025-02-20","arxiv_id":"2502.14768","repositories_listed":4,"syntology":{"n":23,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/logic-rl-unleashing-llm-reasoning-with-rule#ran","syntology_url":"https://syntology.ai/paper/2502.14768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14768"}},"official":{"repos":["Unakar/Logic-RL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/memory-benchmark-robots-a-benchmark-for","slug":"memory-benchmark-robots-a-benchmark-for","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","date":"2025-02-14","arxiv_id":"2502.10550","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/memory-benchmark-robots-a-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2502.10550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10550"}},"official":{"repos":["CognitiveAISystems/MIKASA-Robo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/digi-q-learning-q-value-functions-for","slug":"digi-q-learning-q-value-functions-for","title":"Digi-Q: Learning Q-Value Functions for Training Device-Control Agents","date":"2025-02-13","arxiv_id":"2502.15760","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/digi-q-learning-q-value-functions-for#ran","syntology_url":"https://syntology.ai/paper/2502.15760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15760"}},"official":{"repos":["digirl-agent/digiq"],"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","unlocated"]}}},{"url":"/paper/hierarchical-multi-agent-framework-for-carbon","slug":"hierarchical-multi-agent-framework-for-carbon","title":"Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters","date":"2025-02-12","arxiv_id":"2502.08337","repositories_listed":0,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hierarchical-multi-agent-framework-for-carbon#ran","syntology_url":"https://syntology.ai/paper/2502.08337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.08337"}},"official":null}},{"url":"/paper/active-advantage-aligned-online-reinforcement","slug":"active-advantage-aligned-online-reinforcement","title":"Active Advantage-Aligned Online Reinforcement Learning with Offline Data","date":"2025-02-11","arxiv_id":"2502.07937","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/active-advantage-aligned-online-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2502.07937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07937"}},"official":{"repos":["xuefeng-cs/a3rl"],"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/exploring-the-limit-of-outcome-reward-for","slug":"exploring-the-limit-of-outcome-reward-for","title":"Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning","date":"2025-02-10","arxiv_id":"2502.06781","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploring-the-limit-of-outcome-reward-for#ran","syntology_url":"https://syntology.ai/paper/2502.06781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06781"}},"official":{"repos":["internlm/oreal"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-conformal-abstention-policies-for","slug":"learning-conformal-abstention-policies-for","title":"Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models","date":"2025-02-08","arxiv_id":"2502.06884","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/learning-conformal-abstention-policies-for#ran","syntology_url":"https://syntology.ai/paper/2502.06884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06884"}},"official":{"repos":["sinatayebati/vlm-uncertainty"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/duoguard-a-two-player-rl-driven-framework-for","slug":"duoguard-a-two-player-rl-driven-framework-for","title":"DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails","date":"2025-02-07","arxiv_id":"2502.05163","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/duoguard-a-two-player-rl-driven-framework-for#ran","syntology_url":"https://syntology.ai/paper/2502.05163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05163"}},"official":{"repos":["yihedeng9/duoguard"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/training-language-models-to-reason","slug":"training-language-models-to-reason","title":"Training Language Models to Reason Efficiently","date":"2025-02-06","arxiv_id":"2502.04463","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/training-language-models-to-reason#ran","syntology_url":"https://syntology.ai/paper/2502.04463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04463"}},"official":{"repos":["Zanette-Labs/efficient-reasoning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/demystifying-long-chain-of-thought-reasoning","slug":"demystifying-long-chain-of-thought-reasoning","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","date":"2025-02-05","arxiv_id":"2502.03373","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"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; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/demystifying-long-chain-of-thought-reasoning#ran","syntology_url":"https://syntology.ai/paper/2502.03373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03373"}},"official":{"repos":["eddycmu/demystify-long-cot"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flow-q-learning","slug":"flow-q-learning","title":"Flow Q-Learning","date":"2025-02-04","arxiv_id":"2502.02538","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flow-q-learning#ran","syntology_url":"https://syntology.ai/paper/2502.02538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02538"}},"official":{"repos":["seohongpark/fql"],"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":["listed","official"]}}},{"url":"/paper/process-reinforcement-through-implicit","slug":"process-reinforcement-through-implicit","title":"Process Reinforcement through Implicit Rewards","date":"2025-02-03","arxiv_id":"2502.01456","repositories_listed":5,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/process-reinforcement-through-implicit#ran","syntology_url":"https://syntology.ai/paper/2502.01456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01456"}},"official":{"repos":["prime-rl/prime"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/langevin-soft-actor-critic-efficient","slug":"langevin-soft-actor-critic-efficient","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","date":"2025-01-29","arxiv_id":"2501.17827","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":1,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/langevin-soft-actor-critic-efficient#ran","syntology_url":"https://syntology.ai/paper/2501.17827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.17827"}},"official":{"repos":["hmishfaq/lsac"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-quantum-reinforcement-learning","slug":"benchmarking-quantum-reinforcement-learning","title":"Benchmarking Quantum Reinforcement Learning","date":"2025-01-27","arxiv_id":"2501.15893","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-quantum-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2501.15893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15893"}},"official":{"repos":["nicomeyer96/qrl-benchmark"],"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/towards-general-purpose-model-free","slug":"towards-general-purpose-model-free","title":"Towards General-Purpose Model-Free Reinforcement Learning","date":"2025-01-27","arxiv_id":"2501.16142","repositories_listed":0,"syntology":{"n":9,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/towards-general-purpose-model-free#ran","syntology_url":"https://syntology.ai/paper/2501.16142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.16142"}},"official":null}},{"url":"/paper/improving-retrieval-augmented-generation","slug":"improving-retrieval-augmented-generation","title":"Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning","date":"2025-01-25","arxiv_id":"2501.15228","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2501.15228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15228"}},"official":{"repos":["chenyiqun/mmoa-rag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/kimi-k1-5-scaling-reinforcement-learning-with","slug":"kimi-k1-5-scaling-reinforcement-learning-with","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","date":"2025-01-22","arxiv_id":"2501.12599","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/kimi-k1-5-scaling-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2501.12599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.12599"}},"official":null}},{"url":"/paper/optimistic-critic-reconstruction-and","slug":"optimistic-critic-reconstruction-and","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","date":"2024-12-25","arxiv_id":"2412.18855","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/optimistic-critic-reconstruction-and#ran","syntology_url":"https://syntology.ai/paper/2412.18855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18855"}},"official":{"repos":["QinwenLuo/OCR-CFT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-reinforcement-learning-for-llm-multi","slug":"offline-reinforcement-learning-for-llm-multi","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","date":"2024-12-20","arxiv_id":"2412.16145","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/offline-reinforcement-learning-for-llm-multi#ran","syntology_url":"https://syntology.ai/paper/2412.16145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.16145"}},"official":{"repos":["jwhj/oreo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-safe-reinforcement-learning-using","slug":"offline-safe-reinforcement-learning-using","title":"Offline Safe Reinforcement Learning Using Trajectory Classification","date":"2024-12-19","arxiv_id":"2412.15429","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/offline-safe-reinforcement-learning-using#ran","syntology_url":"https://syntology.ai/paper/2412.15429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15429"}},"official":{"repos":["zgong11/TraC"],"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/enabling-realtime-reinforcement-learning-at","slug":"enabling-realtime-reinforcement-learning-at","title":"Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference","date":"2024-12-18","arxiv_id":"2412.14355","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enabling-realtime-reinforcement-learning-at#ran","syntology_url":"https://syntology.ai/paper/2412.14355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14355"}},"official":{"repos":["cerc-aai/realtime_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/guiding-generative-protein-language-models","slug":"guiding-generative-protein-language-models","title":"Guiding Generative Protein Language Models with Reinforcement Learning","date":"2024-12-17","arxiv_id":"2412.12979","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/guiding-generative-protein-language-models#ran","syntology_url":"https://syntology.ai/paper/2412.12979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12979"}},"official":{"repos":["ai4pdlab/dpo_plm"],"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/efficient-policy-adaptation-with-contrastive-1","slug":"efficient-policy-adaptation-with-contrastive-1","title":"Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents","date":"2024-12-16","arxiv_id":"2412.11484","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/efficient-policy-adaptation-with-contrastive-1#ran","syntology_url":"https://syntology.ai/paper/2412.11484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11484"}},"official":null}},{"url":"/paper/entropy-regularized-process-reward-model","slug":"entropy-regularized-process-reward-model","title":"Entropy-Regularized Process Reward Model","date":"2024-12-15","arxiv_id":"2412.11006","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/entropy-regularized-process-reward-model#ran","syntology_url":"https://syntology.ai/paper/2412.11006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11006"}},"official":{"repos":["hanningzhang/er-prm"],"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","unlocated"]}}},{"url":"/paper/are-expressive-models-truly-necessary-for","slug":"are-expressive-models-truly-necessary-for","title":"Are Expressive Models Truly Necessary for Offline RL?","date":"2024-12-15","arxiv_id":"2412.11253","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/are-expressive-models-truly-necessary-for#ran","syntology_url":"https://syntology.ai/paper/2412.11253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11253"}},"official":{"repos":["imoneoi/RSP_JAX"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/latent-safety-constrained-policy-approach-for","slug":"latent-safety-constrained-policy-approach-for","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","date":"2024-12-11","arxiv_id":"2412.08794","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/latent-safety-constrained-policy-approach-for#ran","syntology_url":"https://syntology.ai/paper/2412.08794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08794"}},"official":{"repos":["PrajwalKoirala/LSPC-Safe-Offline-RL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-policy-as-macro","slug":"reinforcement-learning-policy-as-macro","title":"Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer","date":"2024-12-10","arxiv_id":"2412.07167","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/reinforcement-learning-policy-as-macro#ran","syntology_url":"https://syntology.ai/paper/2412.07167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07167"}},"official":{"repos":["lamda-bbo/macro-regulator"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-online-reinforcement-learning-fine","slug":"efficient-online-reinforcement-learning-fine","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","date":"2024-12-10","arxiv_id":"2412.07762","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-online-reinforcement-learning-fine#ran","syntology_url":"https://syntology.ai/paper/2412.07762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07762"}},"official":{"repos":["zhouzypaul/wsrl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/m-3-pc-test-time-model-predictive-control-for","slug":"m-3-pc-test-time-model-predictive-control-for","title":"M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model","date":"2024-12-07","arxiv_id":"2412.05675","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/m-3-pc-test-time-model-predictive-control-for#ran","syntology_url":"https://syntology.ai/paper/2412.05675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05675"}},"official":{"repos":["wkh923/m3pc"],"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/learning-on-one-mode-addressing-multi","slug":"learning-on-one-mode-addressing-multi","title":"Learning on One Mode: Addressing Multi-Modality in Offline Reinforcement Learning","date":"2024-12-04","arxiv_id":"2412.03258","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-on-one-mode-addressing-multi#ran","syntology_url":"https://syntology.ai/paper/2412.03258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03258"}},"official":{"repos":["MianchuWang/LOM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bots-batch-bayesian-optimization-of-extended","slug":"bots-batch-bayesian-optimization-of-extended","title":"BOTS: Batch Bayesian Optimization of Extended Thompson Sampling for Severely Episode-Limited RL Settings","date":"2024-11-30","arxiv_id":"2412.00308","repositories_listed":0,"syntology":{"n":9,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"3 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; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/bots-batch-bayesian-optimization-of-extended#ran","syntology_url":"https://syntology.ai/paper/2412.00308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00308"}},"official":null}},{"url":"/paper/o1-coder-an-o1-replication-for-coding","slug":"o1-coder-an-o1-replication-for-coding","title":"o1-Coder: an o1 Replication for Coding","date":"2024-11-29","arxiv_id":"2412.00154","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/o1-coder-an-o1-replication-for-coding#ran","syntology_url":"https://syntology.ai/paper/2412.00154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00154"}},"official":{"repos":["adam-bjtu/o1-coder"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/natural-language-reinforcement-learning-1","slug":"natural-language-reinforcement-learning-1","title":"Natural Language Reinforcement Learning","date":"2024-11-21","arxiv_id":"2411.14251","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/natural-language-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2411.14251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14251"}},"official":{"repos":["waterhorse1/natural-language-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/marco-o1-towards-open-reasoning-models-for","slug":"marco-o1-towards-open-reasoning-models-for","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","date":"2024-11-21","arxiv_id":"2411.14405","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":6,"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/marco-o1-towards-open-reasoning-models-for#ran","syntology_url":"https://syntology.ai/paper/2411.14405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14405"}},"official":{"repos":["aidc-ai/marco-o1"],"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/continual-task-learning-through-adaptive","slug":"continual-task-learning-through-adaptive","title":"Continual Task Learning through Adaptive Policy Self-Composition","date":"2024-11-18","arxiv_id":"2411.11364","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":4,"phrase":"11 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continual-task-learning-through-adaptive#ran","syntology_url":"https://syntology.ai/paper/2411.11364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11364"}},"official":{"repos":["charleshsc/CompoFormer"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/amago-2-breaking-the-multi-task-barrier-in","slug":"amago-2-breaking-the-multi-task-barrier-in","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","date":"2024-11-17","arxiv_id":"2411.11188","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/amago-2-breaking-the-multi-task-barrier-in#ran","syntology_url":"https://syntology.ai/paper/2411.11188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11188"}},"official":{"repos":["ut-austin-rpl/amago"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/doubly-mild-generalization-for-offline","slug":"doubly-mild-generalization-for-offline","title":"Doubly Mild Generalization for Offline Reinforcement Learning","date":"2024-11-12","arxiv_id":"2411.07934","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/doubly-mild-generalization-for-offline#ran","syntology_url":"https://syntology.ai/paper/2411.07934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07934"}},"official":{"repos":["maoyixiu/dmg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enabling-adaptive-agent-training-in-open","slug":"enabling-adaptive-agent-training-in-open","title":"Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity","date":"2024-11-07","arxiv_id":"2411.04466","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/enabling-adaptive-agent-training-in-open#ran","syntology_url":"https://syntology.ai/paper/2411.04466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04466"}},"official":{"repos":["robbycostales/diva"],"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/beyond-the-rainbow-high-performance-deep","slug":"beyond-the-rainbow-high-performance-deep","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","date":"2024-11-06","arxiv_id":"2411.03820","repositories_listed":3,"syntology":{"n":25,"n_ran":16,"n_constructed":10,"n_ran_checked":13,"n_instrument":3,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":21,"phrase":"16 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/beyond-the-rainbow-high-performance-deep#ran","syntology_url":"https://syntology.ai/paper/2411.03820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03820"}},"official":{"repos":["viptankz/btr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/uncertainty-based-offline-variational","slug":"uncertainty-based-offline-variational","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","date":"2024-11-01","arxiv_id":"2411.00465","repositories_listed":1,"syntology":{"n":13,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":9,"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) · 9 unverified","sample_list":"/paper/uncertainty-based-offline-variational#ran","syntology_url":"https://syntology.ai/paper/2411.00465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00465"}},"official":{"repos":["MIRALab-USTC/RL-TRACER"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-gradients-as-vitamin","slug":"reinforcement-learning-gradients-as-vitamin","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","date":"2024-10-31","arxiv_id":"2410.24108","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reinforcement-learning-gradients-as-vitamin#ran","syntology_url":"https://syntology.ai/paper/2410.24108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24108"}},"official":{"repos":["kaiyan289/rl_as_vitamin_for_online_decision_transformers"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/teaching-embodied-reinforcement-learning","slug":"teaching-embodied-reinforcement-learning","title":"Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use","date":"2024-10-31","arxiv_id":"2410.24218","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/teaching-embodied-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2410.24218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24218"}},"official":{"repos":["sled-group/teachable_rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-behavior-distillation","slug":"offline-behavior-distillation","title":"Offline Behavior Distillation","date":"2024-10-30","arxiv_id":"2410.22728","repositories_listed":1,"syntology":{"n":16,"n_ran":9,"n_constructed":1,"n_ran_checked":6,"n_instrument":3,"n_unverified":7,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":16,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/offline-behavior-distillation#ran","syntology_url":"https://syntology.ai/paper/2410.22728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22728"}},"official":{"repos":["leaveslei/obd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/online-intrinsic-rewards-for-decision-making","slug":"online-intrinsic-rewards-for-decision-making","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","date":"2024-10-30","arxiv_id":"2410.23022","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/online-intrinsic-rewards-for-decision-making#ran","syntology_url":"https://syntology.ai/paper/2410.23022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23022"}},"official":{"repos":["facebookresearch/oni"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/kinetix-investigating-the-training-of-general","slug":"kinetix-investigating-the-training-of-general","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","date":"2024-10-30","arxiv_id":"2410.23208","repositories_listed":1,"syntology":{"n":33,"n_ran":24,"n_constructed":6,"n_ran_checked":15,"n_instrument":9,"n_unverified":9,"n_honours":5,"n_violates":4,"n_no_contract":6,"n_pointer_only":0,"phrase":"24 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 5 honoured, 4 violated, 6 with no contract checked; 9 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/kinetix-investigating-the-training-of-general#ran","syntology_url":"https://syntology.ai/paper/2410.23208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23208"}},"official":{"repos":["michaeltmatthews/jax2d"],"state":"official (archive's flag): 24 ran","n_ran":24,"n_constructed":6,"n_ran_no_instrument_failure":15,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-successor-features-the-simple-way","slug":"learning-successor-features-the-simple-way","title":"Learning Successor Features the Simple Way","date":"2024-10-29","arxiv_id":"2410.22133","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/learning-successor-features-the-simple-way#ran","syntology_url":"https://syntology.ai/paper/2410.22133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22133"}},"official":{"repos":["raymondchua/simple_successor_features"],"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/a-large-recurrent-action-model-xlstm-enables","slug":"a-large-recurrent-action-model-xlstm-enables","title":"A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks","date":"2024-10-29","arxiv_id":"2410.22391","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":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-large-recurrent-action-model-xlstm-enables#ran","syntology_url":"https://syntology.ai/paper/2410.22391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22391"}},"official":{"repos":["ml-jku/lram"],"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/odrl-a-benchmark-for-off-dynamics","slug":"odrl-a-benchmark-for-off-dynamics","title":"ODRL: A Benchmark for Off-Dynamics Reinforcement Learning","date":"2024-10-28","arxiv_id":"2410.20750","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/odrl-a-benchmark-for-off-dynamics#ran","syntology_url":"https://syntology.ai/paper/2410.20750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20750"}},"official":{"repos":["offdynamicsrl/off-dynamics-rl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/longreward-improving-long-context-large","slug":"longreward-improving-long-context-large","title":"LongReward: Improving Long-context Large Language Models with AI Feedback","date":"2024-10-28","arxiv_id":"2410.21252","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":1,"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/longreward-improving-long-context-large#ran","syntology_url":"https://syntology.ai/paper/2410.21252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21252"}},"official":{"repos":["THUDM/LongReward"],"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","unlocated"]}}},{"url":"/paper/offline-reinforcement-learning-with-ood-state","slug":"offline-reinforcement-learning-with-ood-state","title":"Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression","date":"2024-10-25","arxiv_id":"2410.19400","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":1,"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/offline-reinforcement-learning-with-ood-state#ran","syntology_url":"https://syntology.ai/paper/2410.19400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19400"}},"official":{"repos":["MAOYIXIU/SCAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-versatile-skills-with-curriculum","slug":"learning-versatile-skills-with-curriculum","title":"Learning Versatile Skills with Curriculum Masking","date":"2024-10-23","arxiv_id":"2410.17744","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-versatile-skills-with-curriculum#ran","syntology_url":"https://syntology.ai/paper/2410.17744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17744"}},"official":{"repos":["yaotang23/currmask"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-skills-from-unlabeled-prior-data","slug":"leveraging-skills-from-unlabeled-prior-data","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","date":"2024-10-23","arxiv_id":"2410.18076","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/leveraging-skills-from-unlabeled-prior-data#ran","syntology_url":"https://syntology.ai/paper/2410.18076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18076"}},"official":{"repos":["rail-berkeley/supe"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/intersectionzoo-eco-driving-for-benchmarking","slug":"intersectionzoo-eco-driving-for-benchmarking","title":"IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning","date":"2024-10-19","arxiv_id":"2410.15221","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/intersectionzoo-eco-driving-for-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2410.15221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15221"}},"official":{"repos":["mit-wu-lab/IntersectionZoo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-effective-planning-strategies-for","slug":"towards-effective-planning-strategies-for","title":"Towards Effective Planning Strategies for Dynamic Opinion Networks","date":"2024-10-18","arxiv_id":"2410.14091","repositories_listed":2,"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/towards-effective-planning-strategies-for#ran","syntology_url":"https://syntology.ai/paper/2410.14091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14091"}},"official":{"repos":["ai4society/infospread-neurips-24","BharathMuppasani/NeurIPS-Submission-2024"],"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/streaming-deep-reinforcement-learning-finally","slug":"streaming-deep-reinforcement-learning-finally","title":"Streaming Deep Reinforcement Learning Finally Works","date":"2024-10-18","arxiv_id":"2410.14606","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/streaming-deep-reinforcement-learning-finally#ran","syntology_url":"https://syntology.ai/paper/2410.14606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14606"}},"official":{"repos":["mohmdelsayed/streaming-drl"],"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/fine-tuning-discrete-diffusion-models-via","slug":"fine-tuning-discrete-diffusion-models-via","title":"Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design","date":"2024-10-17","arxiv_id":"2410.13643","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fine-tuning-discrete-diffusion-models-via#ran","syntology_url":"https://syntology.ai/paper/2410.13643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13643"}},"official":{"repos":["chenyuwang-monica/drakes"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sliding-puzzles-gym-a-scalable-benchmark-for","slug":"sliding-puzzles-gym-a-scalable-benchmark-for","title":"Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning","date":"2024-10-17","arxiv_id":"2410.14038","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sliding-puzzles-gym-a-scalable-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2410.14038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14038"}},"official":{"repos":["bryanoliveira/sliding-puzzles-gym"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bayes-adaptive-monte-carlo-tree-search-for","slug":"bayes-adaptive-monte-carlo-tree-search-for","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","date":"2024-10-15","arxiv_id":"2410.11234","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bayes-adaptive-monte-carlo-tree-search-for#ran","syntology_url":"https://syntology.ai/paper/2410.11234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11234"}},"official":{"repos":["lucascjysdl/offline-rl-kit"],"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/meta-dt-offline-meta-rl-as-conditional","slug":"meta-dt-offline-meta-rl-as-conditional","title":"Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement","date":"2024-10-15","arxiv_id":"2410.11448","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/meta-dt-offline-meta-rl-as-conditional#ran","syntology_url":"https://syntology.ai/paper/2410.11448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11448"}},"official":{"repos":["nju-rl/meta-dt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/action-gaps-and-advantages-in-continuous-time","slug":"action-gaps-and-advantages-in-continuous-time","title":"Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning","date":"2024-10-14","arxiv_id":"2410.11022","repositories_listed":0,"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/action-gaps-and-advantages-in-continuous-time#ran","syntology_url":"https://syntology.ai/paper/2410.11022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11022"}},"official":null}},{"url":"/paper/improving-generalization-on-the-procgen","slug":"improving-generalization-on-the-procgen","title":"Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale","date":"2024-10-13","arxiv_id":"2410.10905","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/improving-generalization-on-the-procgen#ran","syntology_url":"https://syntology.ai/paper/2410.10905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10905"}},"official":{"repos":["anndvision/vsop-3d"],"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/reinforcement-learning-for-control-of-non","slug":"reinforcement-learning-for-control-of-non","title":"Reinforcement Learning for Control of Non-Markovian Cellular Population Dynamics","date":"2024-10-11","arxiv_id":"2410.08439","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-learning-for-control-of-non#ran","syntology_url":"https://syntology.ai/paper/2410.08439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08439"}},"official":{"repos":["JacobHA/RL4Dosing"],"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/drama-mamba-enabled-model-based-reinforcement","slug":"drama-mamba-enabled-model-based-reinforcement","title":"Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient","date":"2024-10-11","arxiv_id":"2410.08893","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/drama-mamba-enabled-model-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2410.08893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08893"}},"official":{"repos":["realwenlongwang/drama"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/overcoming-slow-decision-frequencies-in","slug":"overcoming-slow-decision-frequencies-in","title":"Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control","date":"2024-10-11","arxiv_id":"2410.08979","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":3,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/overcoming-slow-decision-frequencies-in#ran","syntology_url":"https://syntology.ai/paper/2410.08979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08979"}},"official":{"repos":["dee0512/Temporally-Layered-Architecture"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/stableprompt-automatic-prompt-tuning-using","slug":"stableprompt-automatic-prompt-tuning-using","title":"StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models","date":"2024-10-10","arxiv_id":"2410.07652","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"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) · 4 unverified","sample_list":"/paper/stableprompt-automatic-prompt-tuning-using#ran","syntology_url":"https://syntology.ai/paper/2410.07652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07652"}},"official":{"repos":["kmc0207/Stableprompt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-augmented-decision-transformer","slug":"retrieval-augmented-decision-transformer","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","date":"2024-10-09","arxiv_id":"2410.07071","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":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retrieval-augmented-decision-transformer#ran","syntology_url":"https://syntology.ai/paper/2410.07071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07071"}},"official":{"repos":["ml-jku/RA-DT"],"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/coevolving-with-the-other-you-fine-tuning-llm","slug":"coevolving-with-the-other-you-fine-tuning-llm","title":"Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning","date":"2024-10-08","arxiv_id":"2410.06101","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/coevolving-with-the-other-you-fine-tuning-llm#ran","syntology_url":"https://syntology.ai/paper/2410.06101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06101"}},"official":{"repos":["Harry67Hu/CORY"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improved-off-policy-reinforcement-learning-in","slug":"improved-off-policy-reinforcement-learning-in","title":"Improved Off-policy Reinforcement Learning in Biological Sequence Design","date":"2024-10-06","arxiv_id":"2410.04461","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improved-off-policy-reinforcement-learning-in#ran","syntology_url":"https://syntology.ai/paper/2410.04461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04461"}},"official":{"repos":["hyeonahkimm/delta_cs"],"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","unlocated"]}}},{"url":"/paper/spatial-aware-decision-making-with-ring","slug":"spatial-aware-decision-making-with-ring","title":"Spatial-aware decision-making with ring attractors in reinforcement learning systems","date":"2024-10-04","arxiv_id":"2410.03119","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatial-aware-decision-making-with-ring#ran","syntology_url":"https://syntology.ai/paper/2410.03119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03119"}},"official":null}},{"url":"/paper/closd-closing-the-loop-between-simulation-and","slug":"closd-closing-the-loop-between-simulation-and","title":"CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control","date":"2024-10-04","arxiv_id":"2410.03441","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/closd-closing-the-loop-between-simulation-and#ran","syntology_url":"https://syntology.ai/paper/2410.03441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03441"}},"official":{"repos":["GuyTevet/CLoSD"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/relic-a-recipe-for-64k-steps-of-in-context","slug":"relic-a-recipe-for-64k-steps-of-in-context","title":"ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI","date":"2024-10-03","arxiv_id":"2410.02751","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"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) · 2 unverified","sample_list":"/paper/relic-a-recipe-for-64k-steps-of-in-context#ran","syntology_url":"https://syntology.ai/paper/2410.02751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02751"}},"official":{"repos":["aielawady/relic"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"0664ba686ecd7c65438020076c3f978c037d82f0407e621bc0d67237adad15a5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}