{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DCJXHN4FINUYGD3J6DGXEXPF5A","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":"b3abd51364e49410a39b71412952744119a13fe229a5d5eeefb9adadc1730a74","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:06:22Z","title_canon_sha256":"4078a4ae94ccaad02a304372d6ba022c79884852a2d089a9491b0fba0018ac10"},"schema_version":"1.0","source":{"id":"2110.04184","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04184","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04184v2","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04184","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"pith_short_12","alias_value":"DCJXHN4FINUY","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"pith_short_16","alias_value":"DCJXHN4FINUYGD3J","created_at":"2026-07-05T04:10:23Z"},{"alias_kind":"pith_short_8","alias_value":"DCJXHN4F","created_at":"2026-07-05T04:10:23Z"}],"graph_snapshots":[{"event_id":"sha256:3a27f22f06e85be2afa555cff1fcf7dbeb1ab3d63fb781996c17299a0c9c2558","target":"graph","created_at":"2026-07-05T04:10:23Z","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/2110.04184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning has made substantial empirical progresses in solving games with a large number of players. However, theoretically, the best known sample complexity for finding a Nash equilibrium in general-sum games scales exponentially in the number of players due to the size of the joint action space, and there is a matching exponential lower bound. This paper investigates what learning goals admit better sample complexities in the setting of $m$-player general-sum Markov games with $H$ steps, $S$ states, and $A_i$ actions per player. First, we design algorithms for learni","authors_text":"Song Mei, Yu Bai, Ziang Song","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:06:22Z","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04184","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:c6b87db8a66de7a8585d4894e7fe551996c8f45e3682c928bf0eec36adaf7786","target":"record","created_at":"2026-07-05T04:10:23Z","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":"b3abd51364e49410a39b71412952744119a13fe229a5d5eeefb9adadc1730a74","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:06:22Z","title_canon_sha256":"4078a4ae94ccaad02a304372d6ba022c79884852a2d089a9491b0fba0018ac10"},"schema_version":"1.0","source":{"id":"2110.04184","kind":"arxiv","version":2}},"canonical_sha256":"189373b7854369830f69f0cd725de5e83e34c526554a1a538db3fe4094ebf4e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"189373b7854369830f69f0cd725de5e83e34c526554a1a538db3fe4094ebf4e3","first_computed_at":"2026-07-05T04:10:23.842988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:23.842988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oW4vnwIXAhDy+m6byGlMIQYiDEeOum0Cg8BJ4OoYf9hfvrieYMBr8A8HbWk+ve45HMtTgdE2dGBmGeNeJ1XsAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:23.843547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04184","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6b87db8a66de7a8585d4894e7fe551996c8f45e3682c928bf0eec36adaf7786","sha256:3a27f22f06e85be2afa555cff1fcf7dbeb1ab3d63fb781996c17299a0c9c2558"],"state_sha256":"23c32356526e7b900dbf9dd742d939065db06ad424096ba2ba525df3a978cd6e"}