{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QAAVI3DURFSG7BNCPH2TCT5N3A","short_pith_number":"pith:QAAVI3DU","canonical_record":{"source":{"id":"2211.03032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-06T05:38:23Z","cross_cats_sorted":[],"title_canon_sha256":"797ab774fb6f42cd223258fe4ac3d4ae04768ee401fb9060d7546e855f10c22f","abstract_canon_sha256":"11f619807d559040a921a1ce7d829bcc7cf4afc4fab2651f961b2233d6ac855d"},"schema_version":"1.0"},"canonical_sha256":"8001546c7489646f85a279f5314fadd8317f221a71eaea965fc5ade2d9c3a5f9","source":{"kind":"arxiv","id":"2211.03032","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QAAVI3DURFSG7BNCPH2TCT5N3A","target":"record","payload":{"canonical_record":{"source":{"id":"2211.03032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-06T05:38:23Z","cross_cats_sorted":[],"title_canon_sha256":"797ab774fb6f42cd223258fe4ac3d4ae04768ee401fb9060d7546e855f10c22f","abstract_canon_sha256":"11f619807d559040a921a1ce7d829bcc7cf4afc4fab2651f961b2233d6ac855d"},"schema_version":"1.0"},"canonical_sha256":"8001546c7489646f85a279f5314fadd8317f221a71eaea965fc5ade2d9c3a5f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:43.753621Z","signature_b64":"SIVBQfoMAN0D3zjVUSae4aha1zXthRjbgKXkUPGXSQuZh8Ub4PRCCPr9e4NOmoOQuK9foYNTwzXM7mtWL1lAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8001546c7489646f85a279f5314fadd8317f221a71eaea965fc5ade2d9c3a5f9","last_reissued_at":"2026-07-05T05:13:43.753172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:43.753172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.03032","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qfe9UlWTH8NAPVSiTcGM3Nx5NR8VoWU1DN4l1xorJpdwQm2+O7AyyLER8yjkNR5geHFpLCahXj4zpE97WSu+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:02:54.030615Z"},"content_sha256":"78c54c35d0cba77143395f4f1673ef5d7ba92beec4d805d07c7b874a080c44df","schema_version":"1.0","event_id":"sha256:78c54c35d0cba77143395f4f1673ef5d7ba92beec4d805d07c7b874a080c44df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QAAVI3DURFSG7BNCPH2TCT5N3A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decentralized Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kefan Su, Zongqing Lu","submitted_at":"2022-11-06T05:38:23Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03032","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.03032/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z8+S7SPryFxYnavZM9yeStgnvCkSflqVeqaHawdI+gkBGgK9ZguICvaL1M9SKKKATgme1eIbB4zAfrW2HK3BBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:02:54.030983Z"},"content_sha256":"048cbadec8692b64f090f84e7d0063d572478536a73056d23252071214f4beda","schema_version":"1.0","event_id":"sha256:048cbadec8692b64f090f84e7d0063d572478536a73056d23252071214f4beda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QAAVI3DURFSG7BNCPH2TCT5N3A/bundle.json","state_url":"https://pith.science/pith/QAAVI3DURFSG7BNCPH2TCT5N3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QAAVI3DURFSG7BNCPH2TCT5N3A/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T09:02:54Z","links":{"resolver":"https://pith.science/pith/QAAVI3DURFSG7BNCPH2TCT5N3A","bundle":"https://pith.science/pith/QAAVI3DURFSG7BNCPH2TCT5N3A/bundle.json","state":"https://pith.science/pith/QAAVI3DURFSG7BNCPH2TCT5N3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QAAVI3DURFSG7BNCPH2TCT5N3A/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g3z/zQHrGEV44G7Ul/HWTUi+/5g0CFWeX3Ea4Lqa5mmMsjwXUupLvwDvZ6lF8BgBqMOL5tafgfUfg0FHaO9iAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:02:54.032933Z","bundle_sha256":"8397a6bfcf475a0cb969208ff0baec8ee15b0df0b682ef7b5a05a0f495de5dd8"}}