{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TTOFZDRZLCF5GSYWZE6L6PNK3O","short_pith_number":"pith:TTOFZDRZ","schema_version":"1.0","canonical_sha256":"9cdc5c8e39588bd34b16c93cbf3daadbb381a9e354aa932bd4e3bb87e106ed92","source":{"kind":"arxiv","id":"2208.10458","version":2},"attestation_state":"computed","paper":{"title":"Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.IT","cs.SY","eess.SY","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2022-08-22T17:24:55Z","abstract_excerpt":"This paper studies multi-agent reinforcement learning in Markov games, with the goal of learning Nash equilibria or coarse correlated equilibria (CCE) sample-optimally. All prior results suffer from at least one of the two obstacles: the curse of multiple agents and the barrier of long horizon, regardless of the sampling protocol in use. We take a step towards settling this problem, assuming access to a flexible sampling mechanism: the generative model. Focusing on non-stationary finite-horizon Markov games, we develop a fast learning algorithm called \\myalg~and an adaptive sampling scheme tha"},"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":"2208.10458","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T17:24:55Z","cross_cats_sorted":["cs.GT","cs.IT","cs.SY","eess.SY","math.IT","stat.ML"],"title_canon_sha256":"01baf57247e938b494eee6d5465019d106f6316f5c6a7f313e39aebada7a60aa","abstract_canon_sha256":"721a68393c5342e77106b6b3d4b3a9fe6010a19e5c1f67c02bd06718201fd686"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:50.319601Z","signature_b64":"WtD9bsOSF/hgaiRVc6DonYXFi1OIKQhpvIT55ICuTajhLaciYPZ+BIROBvr5TX+HnUEIezkRfEvs0TIrJkamCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cdc5c8e39588bd34b16c93cbf3daadbb381a9e354aa932bd4e3bb87e106ed92","last_reissued_at":"2026-07-05T05:05:50.319112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:50.319112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.IT","cs.SY","eess.SY","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2022-08-22T17:24:55Z","abstract_excerpt":"This paper studies multi-agent reinforcement learning in Markov games, with the goal of learning Nash equilibria or coarse correlated equilibria (CCE) sample-optimally. All prior results suffer from at least one of the two obstacles: the curse of multiple agents and the barrier of long horizon, regardless of the sampling protocol in use. We take a step towards settling this problem, assuming access to a flexible sampling mechanism: the generative model. Focusing on non-stationary finite-horizon Markov games, we develop a fast learning algorithm called \\myalg~and an adaptive sampling scheme tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10458","kind":"arxiv","version":2},"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/2208.10458/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":"2208.10458","created_at":"2026-07-05T05:05:50.319169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.10458v2","created_at":"2026-07-05T05:05:50.319169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10458","created_at":"2026-07-05T05:05:50.319169+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTOFZDRZLCF5","created_at":"2026-07-05T05:05:50.319169+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTOFZDRZLCF5GSYW","created_at":"2026-07-05T05:05:50.319169+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTOFZDRZ","created_at":"2026-07-05T05:05:50.319169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17189","citing_title":"Sample-efficient inductive matrix completion with noise and inexact side-information","ref_index":161,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTOFZDRZLCF5GSYWZE6L6PNK3O","json":"https://pith.science/pith/TTOFZDRZLCF5GSYWZE6L6PNK3O.json","graph_json":"https://pith.science/api/pith-number/TTOFZDRZLCF5GSYWZE6L6PNK3O/graph.json","events_json":"https://pith.science/api/pith-number/TTOFZDRZLCF5GSYWZE6L6PNK3O/events.json","paper":"https://pith.science/paper/TTOFZDRZ"},"agent_actions":{"view_html":"https://pith.science/pith/TTOFZDRZLCF5GSYWZE6L6PNK3O","download_json":"https://pith.science/pith/TTOFZDRZLCF5GSYWZE6L6PNK3O.json","view_paper":"https://pith.science/paper/TTOFZDRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.10458&json=true","fetch_graph":"https://pith.science/api/pith-number/TTOFZDRZLCF5GSYWZE6L6PNK3O/graph.json","fetch_events":"https://pith.science/api/pith-number/TTOFZDRZLCF5GSYWZE6L6PNK3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTOFZDRZLCF5GSYWZE6L6PNK3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTOFZDRZLCF5GSYWZE6L6PNK3O/action/storage_attestation","attest_author":"https://pith.science/pith/TTOFZDRZLCF5GSYWZE6L6PNK3O/action/author_attestation","sign_citation":"https://pith.science/pith/TTOFZDRZLCF5GSYWZE6L6PNK3O/action/citation_signature","submit_replication":"https://pith.science/pith/TTOFZDRZLCF5GSYWZE6L6PNK3O/action/replication_record"}},"created_at":"2026-07-05T05:05:50.319169+00:00","updated_at":"2026-07-05T05:05:50.319169+00:00"}