{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QAAVI3DURFSG7BNCPH2TCT5N3A","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":"11f619807d559040a921a1ce7d829bcc7cf4afc4fab2651f961b2233d6ac855d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-06T05:38:23Z","title_canon_sha256":"797ab774fb6f42cd223258fe4ac3d4ae04768ee401fb9060d7546e855f10c22f"},"schema_version":"1.0","source":{"id":"2211.03032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.03032","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2211.03032v1","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03032","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"QAAVI3DURFSG","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"QAAVI3DURFSG7BNC","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"QAAVI3DU","created_at":"2026-07-05T05:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:048cbadec8692b64f090f84e7d0063d572478536a73056d23252071214f4beda","target":"graph","created_at":"2026-07-05T05:13:43Z","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/2211.03032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The study of decentralized learning or independent learning in cooperative multi-agent reinforcement learning has a history of decades. Recently empirical studies show that independent PPO (IPPO) can obtain good performance, close to or even better than the methods of centralized training with decentralized execution, in several benchmarks. However, decentralized actor-critic with convergence guarantee is still open. In this paper, we propose \\textit{decentralized policy optimization} (DPO), a decentralized actor-critic algorithm with monotonic improvement and convergence guarantee. We derive ","authors_text":"Kefan Su, Zongqing Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-06T05:38:23Z","title":"Decentralized Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03032","kind":"arxiv","version":1},"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":"sha256:78c54c35d0cba77143395f4f1673ef5d7ba92beec4d805d07c7b874a080c44df","target":"record","created_at":"2026-07-05T05:13:43Z","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":"11f619807d559040a921a1ce7d829bcc7cf4afc4fab2651f961b2233d6ac855d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-06T05:38:23Z","title_canon_sha256":"797ab774fb6f42cd223258fe4ac3d4ae04768ee401fb9060d7546e855f10c22f"},"schema_version":"1.0","source":{"id":"2211.03032","kind":"arxiv","version":1}},"canonical_sha256":"8001546c7489646f85a279f5314fadd8317f221a71eaea965fc5ade2d9c3a5f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8001546c7489646f85a279f5314fadd8317f221a71eaea965fc5ade2d9c3a5f9","first_computed_at":"2026-07-05T05:13:43.753172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:43.753172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SIVBQfoMAN0D3zjVUSae4aha1zXthRjbgKXkUPGXSQuZh8Ub4PRCCPr9e4NOmoOQuK9foYNTwzXM7mtWL1lAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:43.753621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.03032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78c54c35d0cba77143395f4f1673ef5d7ba92beec4d805d07c7b874a080c44df","sha256:048cbadec8692b64f090f84e7d0063d572478536a73056d23252071214f4beda"],"state_sha256":"0c3976affbc0109352d93a19e0aa150066a5eb2a936b00039874a9c2bc00d489"}