{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RVVYFYMWQ2NOVZRUBC2RGIMNUM","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":"e6f5ec59b0778c65e704d685fae48f63cf6fe3a231c5a7a1648630b3a3e03f1d","cross_cats_sorted":["cs.GT","cs.MA","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-08T20:09:47Z","title_canon_sha256":"6f7fac9bf0898109d5d8859055d483c9de5f7415bef5640b425df6b1b86178b5"},"schema_version":"1.0","source":{"id":"2202.04129","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.04129","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"2202.04129v3","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04129","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"RVVYFYMWQ2NO","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"pith_short_16","alias_value":"RVVYFYMWQ2NOVZRU","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"pith_short_8","alias_value":"RVVYFYMW","created_at":"2026-07-05T04:46:13Z"}],"graph_snapshots":[{"event_id":"sha256:22a12138787e028061446b44a8301b81109068f121a10e15ff510c13281664c7","target":"graph","created_at":"2026-07-05T04:46:13Z","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/2202.04129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We examine global non-asymptotic convergence properties of policy gradient methods for multi-agent reinforcement learning (RL) problems in Markov potential games (MPG). To learn a Nash equilibrium of an MPG in which the size of state space and/or the number of players can be very large, we propose new independent policy gradient algorithms that are run by all players in tandem. When there is no uncertainty in the gradient evaluation, we show that our algorithm finds an $\\epsilon$-Nash equilibrium with $O(1/\\epsilon^2)$ iteration complexity which does not explicitly depend on the state space si","authors_text":"Chen-Yu Wei, Dongsheng Ding, Kaiqing Zhang, Mihailo R. Jovanovi\\'c","cross_cats":["cs.GT","cs.MA","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-08T20:09:47Z","title":"Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04129","kind":"arxiv","version":3},"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":"sha256:49dbc1d9905717ea9e7757096141efa2cf55c26df73e390e5b85430578f96aed","target":"record","created_at":"2026-07-05T04:46:13Z","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":"e6f5ec59b0778c65e704d685fae48f63cf6fe3a231c5a7a1648630b3a3e03f1d","cross_cats_sorted":["cs.GT","cs.MA","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-08T20:09:47Z","title_canon_sha256":"6f7fac9bf0898109d5d8859055d483c9de5f7415bef5640b425df6b1b86178b5"},"schema_version":"1.0","source":{"id":"2202.04129","kind":"arxiv","version":3}},"canonical_sha256":"8d6b82e196869aeae63408b513218da33fea352d81a7d50b4a267229f192c2d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d6b82e196869aeae63408b513218da33fea352d81a7d50b4a267229f192c2d9","first_computed_at":"2026-07-05T04:46:13.503339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:13.503339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eQpRl8gr7i0FYqGBtMTBXesw/rvNV5fgvoy2q/LQMQFYpSuRQlIhJLvBubO/WLXdXGhag0zQik4mtW9FtvdPCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:13.503718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.04129","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49dbc1d9905717ea9e7757096141efa2cf55c26df73e390e5b85430578f96aed","sha256:22a12138787e028061446b44a8301b81109068f121a10e15ff510c13281664c7"],"state_sha256":"5c5d92f53b6039b1c6c6eae8c12531a613ad3fab1c88513de7b76de21717d1a9"}