{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZOMOHONRI57DMLUZ5L7U2YNMEF","short_pith_number":"pith:ZOMOHONR","schema_version":"1.0","canonical_sha256":"cb98e3b9b1477e362e99eaff4d61ac21511587ba10511480d669cd68a25e16d0","source":{"kind":"arxiv","id":"2412.19873","version":1},"attestation_state":"computed","paper":{"title":"Minimax-Optimal Multi-Agent Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gen Li, Yuchen Jiao","submitted_at":"2024-12-27T16:37:33Z","abstract_excerpt":"Multi-agent robust reinforcement learning, also known as multi-player robust Markov games (RMGs), is a crucial framework for modeling competitive interactions under environmental uncertainties, with wide applications in multi-agent systems. However, existing results on sample complexity in RMGs suffer from at least one of three obstacles: restrictive range of uncertainty level or accuracy, the curse of multiple agents, and the barrier of long horizons, all of which cause existing results to significantly exceed the information-theoretic lower bound. To close this gap, we extend the Q-FTRL algo"},"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":"2412.19873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T16:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"d014264d83a047ec5f5a8b1d86c1aa6c154c4498d5423f9579b16178b5a99977","abstract_canon_sha256":"ad5c1ef5b77e349d58ba15906d2b4be842973bedf97ece6569b3f40bb5b1530c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:50.916137Z","signature_b64":"ClmqEOQRdyYxHi+zS6PK+bEXYavl/LiA2EZQf0BcasBKRViPUVkmSEHSxfL6Zxnrwe9IzckjFefQr3KFuXmYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb98e3b9b1477e362e99eaff4d61ac21511587ba10511480d669cd68a25e16d0","last_reissued_at":"2026-07-05T09:54:50.915656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:50.915656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimax-Optimal Multi-Agent Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gen Li, Yuchen Jiao","submitted_at":"2024-12-27T16:37:33Z","abstract_excerpt":"Multi-agent robust reinforcement learning, also known as multi-player robust Markov games (RMGs), is a crucial framework for modeling competitive interactions under environmental uncertainties, with wide applications in multi-agent systems. However, existing results on sample complexity in RMGs suffer from at least one of three obstacles: restrictive range of uncertainty level or accuracy, the curse of multiple agents, and the barrier of long horizons, all of which cause existing results to significantly exceed the information-theoretic lower bound. To close this gap, we extend the Q-FTRL algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19873","kind":"arxiv","version":1},"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/2412.19873/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":"2412.19873","created_at":"2026-07-05T09:54:50.915719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19873v1","created_at":"2026-07-05T09:54:50.915719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19873","created_at":"2026-07-05T09:54:50.915719+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOMOHONRI57D","created_at":"2026-07-05T09:54:50.915719+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOMOHONRI57DMLUZ","created_at":"2026-07-05T09:54:50.915719+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOMOHONR","created_at":"2026-07-05T09:54:50.915719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF","json":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF.json","graph_json":"https://pith.science/api/pith-number/ZOMOHONRI57DMLUZ5L7U2YNMEF/graph.json","events_json":"https://pith.science/api/pith-number/ZOMOHONRI57DMLUZ5L7U2YNMEF/events.json","paper":"https://pith.science/paper/ZOMOHONR"},"agent_actions":{"view_html":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF","download_json":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF.json","view_paper":"https://pith.science/paper/ZOMOHONR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19873&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOMOHONRI57DMLUZ5L7U2YNMEF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOMOHONRI57DMLUZ5L7U2YNMEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/action/storage_attestation","attest_author":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/action/author_attestation","sign_citation":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/action/citation_signature","submit_replication":"https://pith.science/pith/ZOMOHONRI57DMLUZ5L7U2YNMEF/action/replication_record"}},"created_at":"2026-07-05T09:54:50.915719+00:00","updated_at":"2026-07-05T09:54:50.915719+00:00"}