{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/reinforcement-learning-2/papers/ran/2","list_of":"/task/reinforcement-learning-2","task":"reinforcement-learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"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":12,"rows_per_page":100,"rows":[101,200],"of":1165,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/reinforcement-learning-2/papers/ran/1","prev":"/task/reinforcement-learning-2/papers/ran/1","next":"/task/reinforcement-learning-2/papers/ran/3","papers":[{"url":"/paper/model-based-transfer-learning-for-contextual","slug":"model-based-transfer-learning-for-contextual","title":"Model-Based Transfer Learning for Contextual Reinforcement Learning","date":"2024-08-08","arxiv_id":"2408.04498","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/model-based-transfer-learning-for-contextual#ran","syntology_url":"https://syntology.ai/paper/2408.04498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04498"}},"official":{"repos":["jhoon-cho/mbtl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-03195","slug":"2408-03195","title":"RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning","date":"2024-08-06","arxiv_id":"2408.03195","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":15,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/2408-03195#ran","syntology_url":"https://syntology.ai/paper/2408.03195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03195"}},"official":{"repos":["JasonZhujp/RELIEF"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-01942","slug":"2408-01942","title":"Visual Grounding for Object-Level Generalization in Reinforcement Learning","date":"2024-08-04","arxiv_id":"2408.01942","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/2408-01942#ran","syntology_url":"https://syntology.ai/paper/2408.01942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01942"}},"official":{"repos":["pku-rl/copl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/arcle-the-abstraction-and-reasoning-corpus","slug":"arcle-the-abstraction-and-reasoning-corpus","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","date":"2024-07-30","arxiv_id":"2407.20806","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/arcle-the-abstraction-and-reasoning-corpus#ran","syntology_url":"https://syntology.ai/paper/2407.20806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20806"}},"official":{"repos":["confeitohs/arcle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dataset-distillation-for-offline","slug":"dataset-distillation-for-offline","title":"Dataset Distillation for Offline Reinforcement Learning","date":"2024-07-29","arxiv_id":"2407.20299","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":6,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":6,"n_pointer_only":2,"phrase":"11 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/dataset-distillation-for-offline#ran","syntology_url":"https://syntology.ai/paper/2407.20299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20299"}},"official":{"repos":["ggflow123/ddrl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["community","official"]}}},{"url":"/paper/navix-scaling-minigrid-environments-with-jax","slug":"navix-scaling-minigrid-environments-with-jax","title":"NAVIX: Scaling MiniGrid Environments with JAX","date":"2024-07-28","arxiv_id":"2407.19396","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/navix-scaling-minigrid-environments-with-jax#ran","syntology_url":"https://syntology.ai/paper/2407.19396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19396"}},"official":{"repos":["epignatelli/navix"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gymnasium-a-standard-interface-for","slug":"gymnasium-a-standard-interface-for","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","date":"2024-07-24","arxiv_id":"2407.17032","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gymnasium-a-standard-interface-for#ran","syntology_url":"https://syntology.ai/paper/2407.17032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17032"}},"official":{"repos":["farama-foundation/gymnasium"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-for-verilog-generation","slug":"large-language-model-for-verilog-generation","title":"Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning","date":"2024-07-21","arxiv_id":"2407.18271","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-model-for-verilog-generation#ran","syntology_url":"https://syntology.ai/paper/2407.18271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18271"}},"official":{"repos":["CatIIIIIIII/veriseek"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/oasis-conditional-distribution-shaping-for","slug":"oasis-conditional-distribution-shaping-for","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","date":"2024-07-19","arxiv_id":"2407.14653","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/oasis-conditional-distribution-shaping-for#ran","syntology_url":"https://syntology.ai/paper/2407.14653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14653"}},"official":{"repos":["yihangyao/OASIS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-empowered-state-representation-for","slug":"llm-empowered-state-representation-for","title":"LLM-Empowered State Representation for Reinforcement Learning","date":"2024-07-18","arxiv_id":"2407.13237","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-empowered-state-representation-for#ran","syntology_url":"https://syntology.ai/paper/2407.13237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13237"}},"official":{"repos":["thu-rllab/LESR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/energy-guided-diffusion-sampling-for-offline","slug":"energy-guided-diffusion-sampling-for-offline","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.12448","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":4,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/energy-guided-diffusion-sampling-for-offline#ran","syntology_url":"https://syntology.ai/paper/2407.12448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12448"}},"official":{"repos":["liuxhym/edis"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/constrained-intrinsic-motivation-for","slug":"constrained-intrinsic-motivation-for","title":"Constrained Intrinsic Motivation for Reinforcement Learning","date":"2024-07-12","arxiv_id":"2407.09247","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/constrained-intrinsic-motivation-for#ran","syntology_url":"https://syntology.ai/paper/2407.09247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09247"}},"official":{"repos":["x-zheng16/cim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-generative-approach-to-control-complex","slug":"a-generative-approach-to-control-complex","title":"DiffPhyCon: A Generative Approach to Control Complex Physical Systems","date":"2024-07-09","arxiv_id":"2407.06494","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-generative-approach-to-control-complex#ran","syntology_url":"https://syntology.ai/paper/2407.06494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06494"}},"official":{"repos":["ai4science-westlakeu/diffphycon"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/can-learned-optimization-make-reinforcement","slug":"can-learned-optimization-make-reinforcement","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","date":"2024-07-09","arxiv_id":"2407.07082","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-learned-optimization-make-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2407.07082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07082"}},"official":{"repos":["alexgoldie/rl-learned-optimization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/q-adapter-training-your-llm-adapter-as-a","slug":"q-adapter-training-your-llm-adapter-as-a","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","date":"2024-07-04","arxiv_id":"2407.03856","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/q-adapter-training-your-llm-adapter-as-a#ran","syntology_url":"https://syntology.ai/paper/2407.03856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03856"}},"official":{"repos":["mansicer/Q-Adapter"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/craftium-an-extensible-framework-for-creating","slug":"craftium-an-extensible-framework-for-creating","title":"Craftium: An Extensible Framework for Creating Reinforcement Learning Environments","date":"2024-07-04","arxiv_id":"2407.03969","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/craftium-an-extensible-framework-for-creating#ran","syntology_url":"https://syntology.ai/paper/2407.03969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03969"}},"official":{"repos":["mikelma/craftium"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/confidence-aware-inverse-constrained","slug":"confidence-aware-inverse-constrained","title":"Confidence Aware Inverse Constrained Reinforcement Learning","date":"2024-06-24","arxiv_id":"2406.16782","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/confidence-aware-inverse-constrained#ran","syntology_url":"https://syntology.ai/paper/2406.16782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16782"}},"official":{"repos":["sriram94/confidenceawareicrl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/macrohft-memory-augmented-context-aware","slug":"macrohft-memory-augmented-context-aware","title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","date":"2024-06-20","arxiv_id":"2406.14537","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/macrohft-memory-augmented-context-aware#ran","syntology_url":"https://syntology.ai/paper/2406.14537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14537"}},"official":{"repos":["ZONG0004/MacroHFT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/more-efficient-randomized-exploration-for","slug":"more-efficient-randomized-exploration-for","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","date":"2024-06-18","arxiv_id":"2406.12241","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/more-efficient-randomized-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2406.12241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12241"}},"official":{"repos":["panxulab/lsvi-ase"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/is-poisoning-a-real-threat-to-llm-alignment","slug":"is-poisoning-a-real-threat-to-llm-alignment","title":"Is poisoning a real threat to LLM alignment? Maybe more so than you think","date":"2024-06-17","arxiv_id":"2406.12091","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/is-poisoning-a-real-threat-to-llm-alignment#ran","syntology_url":"https://syntology.ai/paper/2406.12091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12091"}},"official":{"repos":["pankayaraj/RLHFPoisoning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adding-conditional-control-to-diffusion","slug":"adding-conditional-control-to-diffusion","title":"Adding Conditional Control to Diffusion Models with Reinforcement Learning","date":"2024-06-17","arxiv_id":"2406.12120","repositories_listed":0,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"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) · 5 unverified","sample_list":"/paper/adding-conditional-control-to-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.12120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12120"}},"official":null}},{"url":"/paper/toward-optimal-llm-alignments-using-two","slug":"toward-optimal-llm-alignments-using-two","title":"Toward Optimal LLM Alignments Using Two-Player Games","date":"2024-06-16","arxiv_id":"2406.10977","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/toward-optimal-llm-alignments-using-two#ran","syntology_url":"https://syntology.ai/paper/2406.10977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10977"}},"official":{"repos":["ruizheng20/gpo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-model-based-reinforcement-learning-1","slug":"robust-model-based-reinforcement-learning-1","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","date":"2024-06-14","arxiv_id":"2406.09976","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-model-based-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2406.09976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09976"}},"official":{"repos":["rmbpo-eval/rmbpo-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-max-min-formulation-of-multi-objective","slug":"the-max-min-formulation-of-multi-objective","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","date":"2024-06-12","arxiv_id":"2406.07826","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-max-min-formulation-of-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2406.07826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07826"}},"official":{"repos":["giseung-park/maxmin-morl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rrls-robust-reinforcement-learning-suite","slug":"rrls-robust-reinforcement-learning-suite","title":"RRLS : Robust Reinforcement Learning Suite","date":"2024-06-12","arxiv_id":"2406.08406","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rrls-robust-reinforcement-learning-suite#ran","syntology_url":"https://syntology.ai/paper/2406.08406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08406"}},"official":{"repos":["sureli/rrls"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/coprocessor-actor-critic-a-model-based","slug":"coprocessor-actor-critic-a-model-based","title":"Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation","date":"2024-06-10","arxiv_id":"2406.06714","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coprocessor-actor-critic-a-model-based#ran","syntology_url":"https://syntology.ai/paper/2406.06714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06714"}},"official":{"repos":["michelllepan/neural-coprocessors"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/probabilistic-perspectives-on-error","slug":"probabilistic-perspectives-on-error","title":"Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.04724","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/probabilistic-perspectives-on-error#ran","syntology_url":"https://syntology.ai/paper/2406.04724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04724"}},"official":{"repos":["romanbelaire/acoe-robust-rl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/skill-aware-mutual-information-optimisation","slug":"skill-aware-mutual-information-optimisation","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.04815","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/skill-aware-mutual-information-optimisation#ran","syntology_url":"https://syntology.ai/paper/2406.04815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04815"}},"official":{"repos":["uoe-agents/sami"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/optimizing-automatic-differentiation-with","slug":"optimizing-automatic-differentiation-with","title":"Optimizing Automatic Differentiation with Deep Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.05027","repositories_listed":0,"syntology":{"n":29,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":17,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/optimizing-automatic-differentiation-with#ran","syntology_url":"https://syntology.ai/paper/2406.05027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05027"}},"official":null}},{"url":"/paper/hackatari-atari-learning-environments-for","slug":"hackatari-atari-learning-environments-for","title":"HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.03997","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/hackatari-atari-learning-environments-for#ran","syntology_url":"https://syntology.ai/paper/2406.03997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03997"}},"official":{"repos":["k4ntz/HackAtari"],"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/spatio-temporal-early-prediction-based-on","slug":"spatio-temporal-early-prediction-based-on","title":"STEMO: Early Spatio-temporal Forecasting with Multi-Objective Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.04035","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/spatio-temporal-early-prediction-based-on#ran","syntology_url":"https://syntology.ai/paper/2406.04035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04035"}},"official":{"repos":["coco0106/MO-STEP"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stochastic-bilevel-optimization-with-lower","slug":"stochastic-bilevel-optimization-with-lower","title":"Contextual Bilevel Reinforcement Learning for Incentive Alignment","date":"2024-06-03","arxiv_id":"2406.01575","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/stochastic-bilevel-optimization-with-lower#ran","syntology_url":"https://syntology.ai/paper/2406.01575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01575"}},"official":{"repos":["lasgroup/hpgd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/reciprocal-reward-influence-encourages","slug":"reciprocal-reward-influence-encourages","title":"Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents","date":"2024-06-03","arxiv_id":"2406.01641","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/reciprocal-reward-influence-encourages#ran","syntology_url":"https://syntology.ai/paper/2406.01641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01641"}},"official":{"repos":["johnlyzhou/reciprocator"],"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/furl-visual-language-models-as-fuzzy-rewards","slug":"furl-visual-language-models-as-fuzzy-rewards","title":"FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning","date":"2024-06-02","arxiv_id":"2406.00645","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/furl-visual-language-models-as-fuzzy-rewards#ran","syntology_url":"https://syntology.ai/paper/2406.00645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00645"}},"official":{"repos":["fuyw/furl"],"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/artificial-generational-intelligence-cultural","slug":"artificial-generational-intelligence-cultural","title":"Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning","date":"2024-06-01","arxiv_id":"2406.00392","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":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/artificial-generational-intelligence-cultural#ran","syntology_url":"https://syntology.ai/paper/2406.00392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00392"}},"official":{"repos":["flairox/cultural-accumulation"],"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/in-context-decision-transformer-reinforcement","slug":"in-context-decision-transformer-reinforcement","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","date":"2024-05-31","arxiv_id":"2405.20692","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/in-context-decision-transformer-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2405.20692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20692"}},"official":{"repos":["silihuang-ai/idt"],"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/amortizing-intractable-inference-in-diffusion","slug":"amortizing-intractable-inference-in-diffusion","title":"Amortizing intractable inference in diffusion models for vision, language, and control","date":"2024-05-31","arxiv_id":"2405.20971","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/amortizing-intractable-inference-in-diffusion#ran","syntology_url":"https://syntology.ai/paper/2405.20971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20971"}},"official":{"repos":["gfnorg/diffusion-finetuning"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-policies-creating-a-trust-region","slug":"diffusion-policies-creating-a-trust-region","title":"Diffusion Policies creating a Trust Region for Offline Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.19690","repositories_listed":1,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":20,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffusion-policies-creating-a-trust-region#ran","syntology_url":"https://syntology.ai/paper/2405.19690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19690"}},"official":{"repos":["tianyucodings/diffusion_trusted_q_learning"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-advantage-guided-policy","slug":"adaptive-advantage-guided-policy","title":"Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.19909","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-advantage-guided-policy#ran","syntology_url":"https://syntology.ai/paper/2405.19909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19909"}},"official":{"repos":["ltlhuuu/a2pr"],"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/getting-more-juice-out-of-the-sft-data-reward","slug":"getting-more-juice-out-of-the-sft-data-reward","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","date":"2024-05-28","arxiv_id":"2405.17888","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/getting-more-juice-out-of-the-sft-data-reward#ran","syntology_url":"https://syntology.ai/paper/2405.17888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17888"}},"official":{"repos":["jasonjiaxiangli/reward_learning_sft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-in-dynamic-treatment","slug":"reinforcement-learning-in-dynamic-treatment","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","date":"2024-05-28","arxiv_id":"2405.18556","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/reinforcement-learning-in-dynamic-treatment#ran","syntology_url":"https://syntology.ai/paper/2405.18556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18556"}},"official":{"repos":["gilesluo/reassessdtr"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/gta-generative-trajectory-augmentation-with","slug":"gta-generative-trajectory-augmentation-with","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.16907","repositories_listed":1,"syntology":{"n":37,"n_ran":34,"n_constructed":0,"n_ran_checked":29,"n_instrument":5,"n_unverified":3,"n_honours":3,"n_violates":4,"n_no_contract":22,"n_pointer_only":5,"phrase":"34 ran (of which 0 constructed an object rather than computing a result; 29 with no instrument failure: 3 honoured, 4 violated, 22 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/gta-generative-trajectory-augmentation-with#ran","syntology_url":"https://syntology.ai/paper/2405.16907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16907"}},"official":{"repos":["jaewoopudding/gta"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/q-value-regularized-transformer-for-offline","slug":"q-value-regularized-transformer-for-offline","title":"Q-value Regularized Transformer for Offline Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17098","repositories_listed":2,"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":3,"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/q-value-regularized-transformer-for-offline#ran","syntology_url":"https://syntology.ai/paper/2405.17098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17098"}},"official":null}},{"url":"/paper/a-recipe-for-unbounded-data-augmentation-in","slug":"a-recipe-for-unbounded-data-augmentation-in","title":"A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17416","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-recipe-for-unbounded-data-augmentation-in#ran","syntology_url":"https://syntology.ai/paper/2405.17416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17416"}},"official":{"repos":["aalmuzairee/dmcgb2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-and-balanced-a-framework-for-constrained","slug":"safe-and-balanced-a-framework-for-constrained","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","date":"2024-05-26","arxiv_id":"2405.16390","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/safe-and-balanced-a-framework-for-constrained#ran","syntology_url":"https://syntology.ai/paper/2405.16390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16390"}},"official":{"repos":["SafeRL-Lab/Safe-Multi-Objective-MuJoCo"],"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/adaptive-q-network-on-the-fly-target","slug":"adaptive-q-network-on-the-fly-target","title":"Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning","date":"2024-05-25","arxiv_id":"2405.16195","repositories_listed":0,"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/adaptive-q-network-on-the-fly-target#ran","syntology_url":"https://syntology.ai/paper/2405.16195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16195"}},"official":null}},{"url":"/paper/ivideogpt-interactive-videogpts-are-scalable","slug":"ivideogpt-interactive-videogpts-are-scalable","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","date":"2024-05-24","arxiv_id":"2405.15223","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/ivideogpt-interactive-videogpts-are-scalable#ran","syntology_url":"https://syntology.ai/paper/2405.15223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15223"}},"official":{"repos":["thuml/iVideoGPT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/peac-unsupervised-pre-training-for-cross","slug":"peac-unsupervised-pre-training-for-cross","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","date":"2024-05-23","arxiv_id":"2405.14073","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/peac-unsupervised-pre-training-for-cross#ran","syntology_url":"https://syntology.ai/paper/2405.14073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14073"}},"official":{"repos":["thu-ml/CEURL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-reinforcement-learning-from-datasets","slug":"offline-reinforcement-learning-from-datasets","title":"Offline Reinforcement Learning from Datasets with Structured Non-Stationarity","date":"2024-05-23","arxiv_id":"2405.14114","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/offline-reinforcement-learning-from-datasets#ran","syntology_url":"https://syntology.ai/paper/2405.14114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14114"}},"official":{"repos":["johannesack/offlinerlstructurednonstationarity"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/agile-a-novel-framework-of-llm-agents","slug":"agile-a-novel-framework-of-llm-agents","title":"AGILE: A Novel Reinforcement Learning Framework of LLM Agents","date":"2024-05-23","arxiv_id":"2405.14751","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/agile-a-novel-framework-of-llm-agents#ran","syntology_url":"https://syntology.ai/paper/2405.14751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14751"}},"official":{"repos":["bytarnish/agile"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/controlling-behavioral-diversity-in-multi","slug":"controlling-behavioral-diversity-in-multi","title":"Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning","date":"2024-05-23","arxiv_id":"2405.15054","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":6,"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/controlling-behavioral-diversity-in-multi#ran","syntology_url":"https://syntology.ai/paper/2405.15054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15054"}},"official":{"repos":["proroklab/controllingbehavioraldiversity"],"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/feasibility-consistent-representation","slug":"feasibility-consistent-representation","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","date":"2024-05-20","arxiv_id":"2405.11718","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/feasibility-consistent-representation#ran","syntology_url":"https://syntology.ai/paper/2405.11718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11718"}},"official":{"repos":["czp16/fcsrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/is-mamba-compatible-with-trajectory","slug":"is-mamba-compatible-with-trajectory","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","date":"2024-05-20","arxiv_id":"2405.12094","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/is-mamba-compatible-with-trajectory#ran","syntology_url":"https://syntology.ai/paper/2405.12094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12094"}},"official":{"repos":["AndssY/DeMa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-for-world-modeling-visual-details","slug":"diffusion-for-world-modeling-visual-details","title":"Diffusion for World Modeling: Visual Details Matter in Atari","date":"2024-05-20","arxiv_id":"2405.12399","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-for-world-modeling-visual-details#ran","syntology_url":"https://syntology.ai/paper/2405.12399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12399"}},"official":{"repos":["eloialonso/diamond"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reward-centering","slug":"reward-centering","title":"Reward Centering","date":"2024-05-16","arxiv_id":"2405.09999","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reward-centering#ran","syntology_url":"https://syntology.ai/paper/2405.09999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09999"}},"official":{"repos":["abhisheknaik96/continuing-rl-exps"],"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":["listed","official"]}}},{"url":"/paper/reinforcement-learning-1","slug":"reinforcement-learning-1","title":"Reinforcement learning","date":"2024-05-16","arxiv_id":"2405.10369","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2405.10369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10369"}},"official":{"repos":["sarodyatawatta/hintrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-representation-for-data-filtering","slug":"contrastive-representation-for-data-filtering","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","date":"2024-05-10","arxiv_id":"2405.06192","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contrastive-representation-for-data-filtering#ran","syntology_url":"https://syntology.ai/paper/2405.06192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06192"}},"official":{"repos":["battlewen/igdf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sequence-compression-speeds-up-credit","slug":"sequence-compression-speeds-up-credit","title":"Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning","date":"2024-05-06","arxiv_id":"2405.03878","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sequence-compression-speeds-up-credit#ran","syntology_url":"https://syntology.ai/paper/2405.03878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03878"}},"official":{"repos":["aditya-ramesh-10/chunktd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rice-breaking-through-the-training","slug":"rice-breaking-through-the-training","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","date":"2024-05-05","arxiv_id":"2405.03064","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rice-breaking-through-the-training#ran","syntology_url":"https://syntology.ai/paper/2405.03064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03064"}},"official":{"repos":["chengzelei/rice"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/hard-thresholding-meets-evolution-strategies","slug":"hard-thresholding-meets-evolution-strategies","title":"Hard-Thresholding Meets Evolution Strategies in Reinforcement Learning","date":"2024-05-02","arxiv_id":"2405.01615","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hard-thresholding-meets-evolution-strategies#ran","syntology_url":"https://syntology.ai/paper/2405.01615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01615"}},"official":{"repos":["cangcn/nes-ht"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dpo-meets-ppo-reinforced-token-optimization","slug":"dpo-meets-ppo-reinforced-token-optimization","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","date":"2024-04-29","arxiv_id":"2404.18922","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dpo-meets-ppo-reinforced-token-optimization#ran","syntology_url":"https://syntology.ai/paper/2404.18922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18922"}},"official":{"repos":["zkshan2002/rto"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rebel-reinforcement-learning-via-regressing","slug":"rebel-reinforcement-learning-via-regressing","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","date":"2024-04-25","arxiv_id":"2404.16767","repositories_listed":3,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":6,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rebel-reinforcement-learning-via-regressing#ran","syntology_url":"https://syntology.ai/paper/2404.16767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16767"}},"official":{"repos":["Owen-Oertell/rlcm","zhaolingao/rebel"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/dpo-differential-reinforcement-learning-with","slug":"dpo-differential-reinforcement-learning-with","title":"DPO: A Differential and Pointwise Control Approach to Reinforcement Learning","date":"2024-04-24","arxiv_id":"2404.15617","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":0,"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/dpo-differential-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2404.15617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15617"}},"official":null}},{"url":"/paper/multi-view-disentanglement-for-reinforcement","slug":"multi-view-disentanglement-for-reinforcement","title":"Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras","date":"2024-04-22","arxiv_id":"2404.14064","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-view-disentanglement-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2404.14064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14064"}},"official":{"repos":["uoe-agents/mvd"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/continual-offline-reinforcement-learning-via","slug":"continual-offline-reinforcement-learning-via","title":"Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay","date":"2024-04-16","arxiv_id":"2404.10662","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continual-offline-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2404.10662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10662"}},"official":{"repos":["nju-rl/cugro"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/randomized-exploration-in-cooperative-multi","slug":"randomized-exploration-in-cooperative-multi","title":"Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning","date":"2024-04-16","arxiv_id":"2404.10728","repositories_listed":0,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/randomized-exploration-in-cooperative-multi#ran","syntology_url":"https://syntology.ai/paper/2404.10728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10728"}},"official":null}},{"url":"/paper/n-agent-ad-hoc-teamwork","slug":"n-agent-ad-hoc-teamwork","title":"N-Agent Ad Hoc Teamwork","date":"2024-04-16","arxiv_id":"2404.10740","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":5,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/n-agent-ad-hoc-teamwork#ran","syntology_url":"https://syntology.ai/paper/2404.10740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10740"}},"official":{"repos":["carolinewang01/naht"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/what-hides-behind-unfairness-exploring","slug":"what-hides-behind-unfairness-exploring","title":"What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning","date":"2024-04-16","arxiv_id":"2404.10942","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/what-hides-behind-unfairness-exploring#ran","syntology_url":"https://syntology.ai/paper/2404.10942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10942"}},"official":{"repos":["familyld/insightfair"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generalized-population-based-training-for","slug":"generalized-population-based-training-for","title":"Generalized Population-Based Training for Hyperparameter Optimization in Reinforcement Learning","date":"2024-04-12","arxiv_id":"2404.08233","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-population-based-training-for#ran","syntology_url":"https://syntology.ai/paper/2404.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08233"}},"official":{"repos":["emi-group/gpbt-pl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/percentile-criterion-optimization-in-offline-1","slug":"percentile-criterion-optimization-in-offline-1","title":"Percentile Criterion Optimization in Offline Reinforcement Learning","date":"2024-04-07","arxiv_id":"2404.05055","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/percentile-criterion-optimization-in-offline-1#ran","syntology_url":"https://syntology.ai/paper/2404.05055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05055"}},"official":{"repos":["elitalobo/varframework"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/compositional-conservatism-a-transductive","slug":"compositional-conservatism-a-transductive","title":"Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning","date":"2024-04-06","arxiv_id":"2404.04682","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/compositional-conservatism-a-transductive#ran","syntology_url":"https://syntology.ai/paper/2404.04682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04682"}},"official":{"repos":["runamu/compositional-conservatism"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-reinforcement-learning-for-7","slug":"model-based-reinforcement-learning-for-7","title":"Model-based Reinforcement Learning for Parameterized Action Spaces","date":"2024-04-03","arxiv_id":"2404.03037","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-based-reinforcement-learning-for-7#ran","syntology_url":"https://syntology.ai/paper/2404.03037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03037"}},"official":{"repos":["valarzz/dlpa","valarzz/model-based-reinforcement-learning-for-parameterized-action-spaces"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/entity-centric-reinforcement-learning-for","slug":"entity-centric-reinforcement-learning-for","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","date":"2024-04-01","arxiv_id":"2404.01220","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/entity-centric-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2404.01220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01220"}},"official":{"repos":["danhrmti/ecrl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/decision-mamba-reinforcement-learning-via","slug":"decision-mamba-reinforcement-learning-via","title":"Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces","date":"2024-03-29","arxiv_id":"2403.19925","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/decision-mamba-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2403.19925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19925"}},"official":{"repos":["toshihiro-ota/decision-mamba"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/disentangling-length-from-quality-in-direct","slug":"disentangling-length-from-quality-in-direct","title":"Disentangling Length from Quality in Direct Preference Optimization","date":"2024-03-28","arxiv_id":"2403.19159","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disentangling-length-from-quality-in-direct#ran","syntology_url":"https://syntology.ai/paper/2403.19159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19159"}},"official":null}},{"url":"/paper/clha-a-simple-yet-effective-contrastive","slug":"clha-a-simple-yet-effective-contrastive","title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","date":"2024-03-25","arxiv_id":"2403.16649","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clha-a-simple-yet-effective-contrastive#ran","syntology_url":"https://syntology.ai/paper/2403.16649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16649"}},"official":{"repos":["calubkk/clha"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-n-implementation-details-of-rlhf-with-ppo","slug":"the-n-implementation-details-of-rlhf-with-ppo","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","date":"2024-03-24","arxiv_id":"2403.17031","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-n-implementation-details-of-rlhf-with-ppo#ran","syntology_url":"https://syntology.ai/paper/2403.17031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17031"}},"official":{"repos":["vwxyzjn/summarize_from_feedback_details"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/insight-end-to-end-neuro-symbolic-visual","slug":"insight-end-to-end-neuro-symbolic-visual","title":"End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations","date":"2024-03-19","arxiv_id":"2403.12451","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/insight-end-to-end-neuro-symbolic-visual#ran","syntology_url":"https://syntology.ai/paper/2403.12451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12451"}},"official":{"repos":["liruiluo/nsrl-vision-pub"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-from-delayed","slug":"reinforcement-learning-from-delayed","title":"Reinforcement Learning from Delayed Observations via World Models","date":"2024-03-18","arxiv_id":"2403.12309","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/reinforcement-learning-from-delayed#ran","syntology_url":"https://syntology.ai/paper/2403.12309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12309"}},"official":{"repos":["indylab/delayeddreamer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/quality-diversity-actor-critic-learning-high","slug":"quality-diversity-actor-critic-learning-high","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","date":"2024-03-15","arxiv_id":"2403.09930","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quality-diversity-actor-critic-learning-high#ran","syntology_url":"https://syntology.ai/paper/2403.09930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09930"}},"official":{"repos":["adaptive-intelligent-robotics/qdac"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sindy-rl-interpretable-and-efficient-model","slug":"sindy-rl-interpretable-and-efficient-model","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09110","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sindy-rl-interpretable-and-efficient-model#ran","syntology_url":"https://syntology.ai/paper/2403.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09110"}},"official":{"repos":["nzolman/sindy-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mamba-an-effective-world-model-approach-for","slug":"mamba-an-effective-world-model-approach-for","title":"MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09859","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mamba-an-effective-world-model-approach-for#ran","syntology_url":"https://syntology.ai/paper/2403.09859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09859"}},"official":{"repos":["zoharri/mamba"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-watermark-llm-generated-text-via","slug":"learning-to-watermark-llm-generated-text-via","title":"Learning to Watermark LLM-generated Text via Reinforcement Learning","date":"2024-03-13","arxiv_id":"2403.10553","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-watermark-llm-generated-text-via#ran","syntology_url":"https://syntology.ai/paper/2403.10553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10553"}},"official":{"repos":["xiaojunxu/learning-to-watermark-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-online-exploration-via-coverability","slug":"scalable-online-exploration-via-coverability","title":"Scalable Online Exploration via Coverability","date":"2024-03-11","arxiv_id":"2403.06571","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scalable-online-exploration-via-coverability#ran","syntology_url":"https://syntology.ai/paper/2403.06571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06571"}},"official":{"repos":["philip-amortila/l1-coverability"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/splagger-split-aggregation-for-meta","slug":"splagger-split-aggregation-for-meta","title":"SplAgger: Split Aggregation for Meta-Reinforcement Learning","date":"2024-03-05","arxiv_id":"2403.03020","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/splagger-split-aggregation-for-meta#ran","syntology_url":"https://syntology.ai/paper/2403.03020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03020"}},"official":{"repos":["jacooba/hyper"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-episodic-memory-utilization-of","slug":"efficient-episodic-memory-utilization-of","title":"Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01112","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/efficient-episodic-memory-utilization-of#ran","syntology_url":"https://syntology.ai/paper/2403.01112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01112"}},"official":{"repos":["hyunghona/emu"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-the-validity-of-automatically","slug":"improving-the-validity-of-automatically","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01304","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/improving-the-validity-of-automatically#ran","syntology_url":"https://syntology.ai/paper/2403.01304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01304"}},"official":{"repos":["umass-ml4ed/feedback-gen-dpo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-iterative-combinatorial-auction","slug":"understanding-iterative-combinatorial-auction","title":"Understanding Iterative Combinatorial Auction Designs via Multi-Agent Reinforcement Learning","date":"2024-02-29","arxiv_id":"2402.19420","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-iterative-combinatorial-auction#ran","syntology_url":"https://syntology.ai/paper/2402.19420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19420"}},"official":{"repos":["newmanne/open_spiel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-zero-shot-reinforcement-learning","slug":"unsupervised-zero-shot-reinforcement-learning","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","date":"2024-02-27","arxiv_id":"2402.17135","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unsupervised-zero-shot-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2402.17135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17135"}},"official":{"repos":["kvfrans/fre"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rime-robust-preference-based-reinforcement","slug":"rime-robust-preference-based-reinforcement","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","date":"2024-02-27","arxiv_id":"2402.17257","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rime-robust-preference-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2402.17257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17257"}},"official":{"repos":["cjreinforce/rime_icml2024"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/feedback-efficient-online-fine-tuning-of","slug":"feedback-efficient-online-fine-tuning-of","title":"Feedback Efficient Online Fine-Tuning of Diffusion Models","date":"2024-02-26","arxiv_id":"2402.16359","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/feedback-efficient-online-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2402.16359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16359"}},"official":null}},{"url":"/paper/craftax-a-lightning-fast-benchmark-for-open","slug":"craftax-a-lightning-fast-benchmark-for-open","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16801","repositories_listed":1,"syntology":{"n":16,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/craftax-a-lightning-fast-benchmark-for-open#ran","syntology_url":"https://syntology.ai/paper/2402.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16801"}},"official":{"repos":["michaeltmatthews/craftax"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/spatially-aware-transformer-memory-for","slug":"spatially-aware-transformer-memory-for","title":"Spatially-Aware Transformer for Embodied Agents","date":"2024-02-23","arxiv_id":"2402.15160","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/spatially-aware-transformer-memory-for#ran","syntology_url":"https://syntology.ai/paper/2402.15160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15160"}},"official":{"repos":["junmokane/spatially-aware-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-data-augmentation-in-deep","slug":"revisiting-data-augmentation-in-deep","title":"Revisiting Data Augmentation in Deep Reinforcement Learning","date":"2024-02-19","arxiv_id":"2402.12181","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/revisiting-data-augmentation-in-deep#ran","syntology_url":"https://syntology.ai/paper/2402.12181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12181"}},"official":{"repos":["jianshu-hu/drqv2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-critical-evaluation-of-ai-feedback-for","slug":"a-critical-evaluation-of-ai-feedback-for","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","date":"2024-02-19","arxiv_id":"2402.12366","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-critical-evaluation-of-ai-feedback-for#ran","syntology_url":"https://syntology.ai/paper/2402.12366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12366"}},"official":{"repos":["architsharma97/dpo-rlaif"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/performative-reinforcement-learning-in","slug":"performative-reinforcement-learning-in","title":"Performative Reinforcement Learning in Gradually Shifting Environments","date":"2024-02-15","arxiv_id":"2402.09838","repositories_listed":2,"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/performative-reinforcement-learning-in#ran","syntology_url":"https://syntology.ai/paper/2402.09838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09838"}},"official":{"repos":["bsen/performative-rl-gradually-shifting-envs","rank-and-files/performative-rl-gradually-shifting-envs"],"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/revisiting-recurrent-reinforcement-learning","slug":"revisiting-recurrent-reinforcement-learning","title":"Recurrent Reinforcement Learning with Memoroids","date":"2024-02-15","arxiv_id":"2402.09900","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revisiting-recurrent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2402.09900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09900"}},"official":{"repos":["proroklab/memory-monoids"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/conservative-and-risk-aware-offline-multi","slug":"conservative-and-risk-aware-offline-multi","title":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","date":"2024-02-13","arxiv_id":"2402.08421","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/conservative-and-risk-aware-offline-multi#ran","syntology_url":"https://syntology.ai/paper/2402.08421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08421"}},"official":{"repos":["eslam211/conservative-and-distributional-marl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-distributional-analogue-to-the-successor","slug":"a-distributional-analogue-to-the-successor","title":"A Distributional Analogue to the Successor Representation","date":"2024-02-13","arxiv_id":"2402.08530","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-distributional-analogue-to-the-successor#ran","syntology_url":"https://syntology.ai/paper/2402.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08530"}},"official":{"repos":["jessefarebro/distributional-sr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/divide-and-conquer-provably-unveiling-the","slug":"divide-and-conquer-provably-unveiling-the","title":"Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning","date":"2024-02-11","arxiv_id":"2402.07182","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":17,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/divide-and-conquer-provably-unveiling-the#ran","syntology_url":"https://syntology.ai/paper/2402.07182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07182"}},"official":{"repos":["wilrop/ipro"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"790eeb43f3b3340ad685a02c67accab9c5ea8a4ce22e450fba7533793f272885","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}