{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TTOFZDRZLCF5GSYWZE6L6PNK3O","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"721a68393c5342e77106b6b3d4b3a9fe6010a19e5c1f67c02bd06718201fd686","cross_cats_sorted":["cs.GT","cs.IT","cs.SY","eess.SY","math.IT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T17:24:55Z","title_canon_sha256":"01baf57247e938b494eee6d5465019d106f6316f5c6a7f313e39aebada7a60aa"},"schema_version":"1.0","source":{"id":"2208.10458","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10458","created_at":"2026-07-05T05:05:50Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10458v2","created_at":"2026-07-05T05:05:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10458","created_at":"2026-07-05T05:05:50Z"},{"alias_kind":"pith_short_12","alias_value":"TTOFZDRZLCF5","created_at":"2026-07-05T05:05:50Z"},{"alias_kind":"pith_short_16","alias_value":"TTOFZDRZLCF5GSYW","created_at":"2026-07-05T05:05:50Z"},{"alias_kind":"pith_short_8","alias_value":"TTOFZDRZ","created_at":"2026-07-05T05:05:50Z"}],"graph_snapshots":[{"event_id":"sha256:94940d58907fee1723976f1363b1e74687c8fca3b0d3e0597d1d3e9fbe60ebc7","target":"graph","created_at":"2026-07-05T05:05:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.10458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen","cross_cats":["cs.GT","cs.IT","cs.SY","eess.SY","math.IT","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T17:24:55Z","title":"Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10458","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7231f1740e404ee50c70c09f6f5b3bc852deb01c6f99c5973460653d66993ae5","target":"record","created_at":"2026-07-05T05:05:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"721a68393c5342e77106b6b3d4b3a9fe6010a19e5c1f67c02bd06718201fd686","cross_cats_sorted":["cs.GT","cs.IT","cs.SY","eess.SY","math.IT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T17:24:55Z","title_canon_sha256":"01baf57247e938b494eee6d5465019d106f6316f5c6a7f313e39aebada7a60aa"},"schema_version":"1.0","source":{"id":"2208.10458","kind":"arxiv","version":2}},"canonical_sha256":"9cdc5c8e39588bd34b16c93cbf3daadbb381a9e354aa932bd4e3bb87e106ed92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cdc5c8e39588bd34b16c93cbf3daadbb381a9e354aa932bd4e3bb87e106ed92","first_computed_at":"2026-07-05T05:05:50.319112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:50.319112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WtD9bsOSF/hgaiRVc6DonYXFi1OIKQhpvIT55ICuTajhLaciYPZ+BIROBvr5TX+HnUEIezkRfEvs0TIrJkamCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:50.319601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.10458","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7231f1740e404ee50c70c09f6f5b3bc852deb01c6f99c5973460653d66993ae5","sha256:94940d58907fee1723976f1363b1e74687c8fca3b0d3e0597d1d3e9fbe60ebc7"],"state_sha256":"d6fd661086aced77e4d7d84efae3046ed5f25214be62f2d9cc1d93d860897d4e"}