{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V3IASIGUXBINQVLILZNIW5NIAO","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":"ecd0808b0cd012f33f829eea729d65b1ee73578d6100286c4669681cf9ec2621","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T00:00:43Z","title_canon_sha256":"071ed0d21385dd78b97a4a5a296ffeca799a8d9c7883662bbedb6d53d5683a42"},"schema_version":"1.0","source":{"id":"2505.18433","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18433","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18433v2","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18433","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"V3IASIGUXBIN","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"pith_short_16","alias_value":"V3IASIGUXBINQVLI","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"pith_short_8","alias_value":"V3IASIGU","created_at":"2026-07-05T11:53:03Z"}],"graph_snapshots":[{"event_id":"sha256:510370e2aae030ede7005bbec4727b2feecc8f38f469ccac19b3e95ec0dc49fd","target":"graph","created_at":"2026-07-05T11:53:03Z","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/2505.18433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Actor-critic methods for decentralized multi-agent reinforcement learning (MARL) facilitate collaborative optimal decision making without centralized coordination, thus enabling a wide range of applications in practice. To date, however, most theoretical convergence studies for existing actor-critic decentralized MARL methods are limited to the guarantee of a stationary solution under the linear function approximation. This leaves a significant gap between the highly successful use of deep neural actor-critic for decentralized MARL in practice and the current theoretical understanding. To brid","authors_text":"Alvaro Velasquez, Fnu Hairi, Jia Liu, Myeung Suk Oh, Zhiyao Zhang, Ziyue Luo","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T00:00:43Z","title":"Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18433","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":"sha256:489c1a49b8a7d866aa759026bd7d0f727708ce22be151757c3260f06886fa2a4","target":"record","created_at":"2026-07-05T11:53:03Z","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":"ecd0808b0cd012f33f829eea729d65b1ee73578d6100286c4669681cf9ec2621","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T00:00:43Z","title_canon_sha256":"071ed0d21385dd78b97a4a5a296ffeca799a8d9c7883662bbedb6d53d5683a42"},"schema_version":"1.0","source":{"id":"2505.18433","kind":"arxiv","version":2}},"canonical_sha256":"aed00920d4b850d855685e5a8b75a803aac0865ad2fa7264cdef8cbeb333181a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aed00920d4b850d855685e5a8b75a803aac0865ad2fa7264cdef8cbeb333181a","first_computed_at":"2026-07-05T11:53:03.515115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:03.515115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yuqzyYSP0GCYecdwTGm2/SkfDhghbr+GH+aVpDdAL5c2tz00DmgIplRqKIAnVgHzxzbkAJA7IV2GUPtmEIDPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:03.515584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18433","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:489c1a49b8a7d866aa759026bd7d0f727708ce22be151757c3260f06886fa2a4","sha256:510370e2aae030ede7005bbec4727b2feecc8f38f469ccac19b3e95ec0dc49fd"],"state_sha256":"e1b47ab8c89a9174634663ca69e132b5b891dc0d69284a5e190db9241aad9ed3"}