{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MJNDURVDTQDAHYI2HRDJNGQSCQ","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":"4cac72b03e22ed6c419923f1621fa6b9f7c980a206cfd71a6c0d21c96d2187be","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-24T02:21:55Z","title_canon_sha256":"77c9657552743e11ce70c752d566c1bbc0b31db5484dcc44069253d6273ece81"},"schema_version":"1.0","source":{"id":"2007.12322","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.12322","created_at":"2026-07-05T01:40:00Z"},{"alias_kind":"arxiv_version","alias_value":"2007.12322v2","created_at":"2026-07-05T01:40:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12322","created_at":"2026-07-05T01:40:00Z"},{"alias_kind":"pith_short_12","alias_value":"MJNDURVDTQDA","created_at":"2026-07-05T01:40:00Z"},{"alias_kind":"pith_short_16","alias_value":"MJNDURVDTQDAHYI2","created_at":"2026-07-05T01:40:00Z"},{"alias_kind":"pith_short_8","alias_value":"MJNDURVD","created_at":"2026-07-05T01:40:00Z"}],"graph_snapshots":[{"event_id":"sha256:5c30535ff0bd181c501bc6d0fb54a6e1336a3ee2e6aa08cf5de18faf7a209fcf","target":"graph","created_at":"2026-07-05T01:40:00Z","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/2007.12322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent policy gradient (MAPG) methods recently witness vigorous progress. However, there is a significant performance discrepancy between MAPG methods and state-of-the-art multi-agent value-based approaches. In this paper, we investigate causes that hinder the performance of MAPG algorithms and present a multi-agent decomposed policy gradient method (DOP). This method introduces the idea of value function decomposition into the multi-agent actor-critic framework. Based on this idea, DOP supports efficient off-policy learning and addresses the issue of centralized-decentralized mismatch an","authors_text":"Beining Han, Chongjie Zhang, Heng Dong, Tonghan Wang, Yihan Wang","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-24T02:21:55Z","title":"Off-Policy Multi-Agent Decomposed Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12322","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":"sha256:95446de330b244cf95974c3b8b5171661f0dd0a221463c73e5acc0dc2d8cace0","target":"record","created_at":"2026-07-05T01:40:00Z","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":"4cac72b03e22ed6c419923f1621fa6b9f7c980a206cfd71a6c0d21c96d2187be","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-24T02:21:55Z","title_canon_sha256":"77c9657552743e11ce70c752d566c1bbc0b31db5484dcc44069253d6273ece81"},"schema_version":"1.0","source":{"id":"2007.12322","kind":"arxiv","version":2}},"canonical_sha256":"625a3a46a39c0603e11a3c46969a12143f15555fac94a7485d07f2ee88cc68fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"625a3a46a39c0603e11a3c46969a12143f15555fac94a7485d07f2ee88cc68fe","first_computed_at":"2026-07-05T01:40:00.150810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:00.150810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wQsSHO97prVmG1VMPy6PwbpniSuRmBz3aGvdMscvxbpPEIx/yFq2Ztrh6roce/uVYTG2dkTn1Vyr1ZRHnR/3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:00.151194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.12322","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95446de330b244cf95974c3b8b5171661f0dd0a221463c73e5acc0dc2d8cace0","sha256:5c30535ff0bd181c501bc6d0fb54a6e1336a3ee2e6aa08cf5de18faf7a209fcf"],"state_sha256":"c740ec84e8300304521f3f15606c6362f5c530f5e8f198a7a8181d836f81c2ff"}