{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SP4U6PAK2O5HGN2ZVGFHQGORRT","short_pith_number":"pith:SP4U6PAK","schema_version":"1.0","canonical_sha256":"93f94f3c0ad3ba733759a98a7819d18cd0203f2f5e773997c31de220a532524c","source":{"kind":"arxiv","id":"2409.00717","version":3},"attestation_state":"computed","paper":{"title":"Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Natalia Zhang, Qiwen Cui, Runlong Zhou, Sham M. Kakade, Simon S. Du, Xinqi Wang","submitted_at":"2024-09-01T13:14:41Z","abstract_excerpt":"We initiate the study of Preference-Based Multi-Agent Reinforcement Learning (PbMARL), exploring both theoretical foundations and empirical validations. We define the task as identifying the Nash equilibrium from a preference-only offline dataset in general-sum games, a problem marked by the challenge of sparse feedback signals. Our theory establishes the upper complexity bounds for Nash Equilibrium in effective PbMARL, demonstrating that single-policy coverage is inadequate and highlighting the importance of unilateral dataset coverage. These theoretical insights are verified through comprehe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.00717","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-01T13:14:41Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"title_canon_sha256":"c6cc578ebfca8a50415cc6d7850c44e36aaea28375d0fe43f9c6d14571e67531","abstract_canon_sha256":"138e00ccd9e1e58c2ba4456b1a4c3010d6b2a4b19252fdd1710a836793a59a99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:59.569702Z","signature_b64":"v7l9aTcsMzMUqVKv2LS1DHvMZHDtbUFErLaYewu3BvT1uf3ZcB0rMALgOPtCMjmIPN65KEL5Y3UJSUOeygseDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93f94f3c0ad3ba733759a98a7819d18cd0203f2f5e773997c31de220a532524c","last_reissued_at":"2026-07-05T09:58:59.569222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:59.569222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Natalia Zhang, Qiwen Cui, Runlong Zhou, Sham M. Kakade, Simon S. Du, Xinqi Wang","submitted_at":"2024-09-01T13:14:41Z","abstract_excerpt":"We initiate the study of Preference-Based Multi-Agent Reinforcement Learning (PbMARL), exploring both theoretical foundations and empirical validations. We define the task as identifying the Nash equilibrium from a preference-only offline dataset in general-sum games, a problem marked by the challenge of sparse feedback signals. Our theory establishes the upper complexity bounds for Nash Equilibrium in effective PbMARL, demonstrating that single-policy coverage is inadequate and highlighting the importance of unilateral dataset coverage. These theoretical insights are verified through comprehe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00717","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.00717/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.00717","created_at":"2026-07-05T09:58:59.569279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00717v3","created_at":"2026-07-05T09:58:59.569279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00717","created_at":"2026-07-05T09:58:59.569279+00:00"},{"alias_kind":"pith_short_12","alias_value":"SP4U6PAK2O5H","created_at":"2026-07-05T09:58:59.569279+00:00"},{"alias_kind":"pith_short_16","alias_value":"SP4U6PAK2O5HGN2Z","created_at":"2026-07-05T09:58:59.569279+00:00"},{"alias_kind":"pith_short_8","alias_value":"SP4U6PAK","created_at":"2026-07-05T09:58:59.569279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.28281","citing_title":"Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SP4U6PAK2O5HGN2ZVGFHQGORRT","json":"https://pith.science/pith/SP4U6PAK2O5HGN2ZVGFHQGORRT.json","graph_json":"https://pith.science/api/pith-number/SP4U6PAK2O5HGN2ZVGFHQGORRT/graph.json","events_json":"https://pith.science/api/pith-number/SP4U6PAK2O5HGN2ZVGFHQGORRT/events.json","paper":"https://pith.science/paper/SP4U6PAK"},"agent_actions":{"view_html":"https://pith.science/pith/SP4U6PAK2O5HGN2ZVGFHQGORRT","download_json":"https://pith.science/pith/SP4U6PAK2O5HGN2ZVGFHQGORRT.json","view_paper":"https://pith.science/paper/SP4U6PAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00717&json=true","fetch_graph":"https://pith.science/api/pith-number/SP4U6PAK2O5HGN2ZVGFHQGORRT/graph.json","fetch_events":"https://pith.science/api/pith-number/SP4U6PAK2O5HGN2ZVGFHQGORRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SP4U6PAK2O5HGN2ZVGFHQGORRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SP4U6PAK2O5HGN2ZVGFHQGORRT/action/storage_attestation","attest_author":"https://pith.science/pith/SP4U6PAK2O5HGN2ZVGFHQGORRT/action/author_attestation","sign_citation":"https://pith.science/pith/SP4U6PAK2O5HGN2ZVGFHQGORRT/action/citation_signature","submit_replication":"https://pith.science/pith/SP4U6PAK2O5HGN2ZVGFHQGORRT/action/replication_record"}},"created_at":"2026-07-05T09:58:59.569279+00:00","updated_at":"2026-07-05T09:58:59.569279+00:00"}