{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QJQSIB7XUE7QQVGEGERADWM7HL","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":"a258d3c7f3a09f1b68177d13916be5f7b479deba4b63740d37a08c9ce8e3563b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-01-10T05:07:42Z","title_canon_sha256":"e1023f0a3710b60ee154dfa071fd29791acfdcf9097f95842626d70d35133541"},"schema_version":"1.0","source":{"id":"2401.04934","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04934","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04934v1","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04934","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"pith_short_12","alias_value":"QJQSIB7XUE7Q","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"pith_short_16","alias_value":"QJQSIB7XUE7QQVGE","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"pith_short_8","alias_value":"QJQSIB7X","created_at":"2026-07-05T07:32:00Z"}],"graph_snapshots":[{"event_id":"sha256:7fae2f217d955f3d1c9c210e85fd1c6512148ec7f115230ebfb71185fc1d548b","target":"graph","created_at":"2026-07-05T07:32:00Z","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/2401.04934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative multi-agent reinforcement learning is a powerful tool to solve many real-world cooperative tasks, but restrictions of real-world applications may require training the agents in a fully decentralized manner. Due to the lack of information about other agents, it is challenging to derive algorithms that can converge to the optimal joint policy in a fully decentralized setting. Thus, this research area has not been thoroughly studied. In this paper, we seek to systematically review the fully decentralized methods in two settings: maximizing a shared reward of all agents and maximizing ","authors_text":"Jiechuan Jiang, Kefan Su, Zongqing Lu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-01-10T05:07:42Z","title":"Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04934","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:a06050fdfbd08e66bba8b7aecfb139276fdb91d96504c41d7880664c174864d1","target":"record","created_at":"2026-07-05T07:32:00Z","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":"a258d3c7f3a09f1b68177d13916be5f7b479deba4b63740d37a08c9ce8e3563b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-01-10T05:07:42Z","title_canon_sha256":"e1023f0a3710b60ee154dfa071fd29791acfdcf9097f95842626d70d35133541"},"schema_version":"1.0","source":{"id":"2401.04934","kind":"arxiv","version":1}},"canonical_sha256":"82612407f7a13f0854c4312201d99f3ac7ef37d536a1a1cab1e1ae8f9a7806ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82612407f7a13f0854c4312201d99f3ac7ef37d536a1a1cab1e1ae8f9a7806ce","first_computed_at":"2026-07-05T07:32:00.672880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:00.672880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VBvBEe5nvmuKdBLQ6U9JwpaoFOh2BZf9zTxpvrpZR/q5G9nMXW+ZI6Om+tXpX+J8wai9jUwZwkC5vUSDpDmaAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:00.673449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.04934","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a06050fdfbd08e66bba8b7aecfb139276fdb91d96504c41d7880664c174864d1","sha256:7fae2f217d955f3d1c9c210e85fd1c6512148ec7f115230ebfb71185fc1d548b"],"state_sha256":"e14112b3ec3d4d94f85b1e3c5f44f39621841684c57d80bd462f13f613e8115c"}