{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QJQSIB7XUE7QQVGEGERADWM7HL","short_pith_number":"pith:QJQSIB7X","schema_version":"1.0","canonical_sha256":"82612407f7a13f0854c4312201d99f3ac7ef37d536a1a1cab1e1ae8f9a7806ce","source":{"kind":"arxiv","id":"2401.04934","version":1},"attestation_state":"computed","paper":{"title":"Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Jiechuan Jiang, Kefan Su, Zongqing Lu","submitted_at":"2024-01-10T05:07:42Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.04934","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-01-10T05:07:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e1023f0a3710b60ee154dfa071fd29791acfdcf9097f95842626d70d35133541","abstract_canon_sha256":"a258d3c7f3a09f1b68177d13916be5f7b479deba4b63740d37a08c9ce8e3563b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:00.673449Z","signature_b64":"VBvBEe5nvmuKdBLQ6U9JwpaoFOh2BZf9zTxpvrpZR/q5G9nMXW+ZI6Om+tXpX+J8wai9jUwZwkC5vUSDpDmaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82612407f7a13f0854c4312201d99f3ac7ef37d536a1a1cab1e1ae8f9a7806ce","last_reissued_at":"2026-07-05T07:32:00.672880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:00.672880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Jiechuan Jiang, Kefan Su, Zongqing Lu","submitted_at":"2024-01-10T05:07:42Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04934","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/2401.04934/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.04934","created_at":"2026-07-05T07:32:00.672955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04934v1","created_at":"2026-07-05T07:32:00.672955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04934","created_at":"2026-07-05T07:32:00.672955+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJQSIB7XUE7Q","created_at":"2026-07-05T07:32:00.672955+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJQSIB7XUE7QQVGE","created_at":"2026-07-05T07:32:00.672955+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJQSIB7X","created_at":"2026-07-05T07:32:00.672955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04359","citing_title":"Learning to cooperate with emergent reputation via multi-agent reinforcement learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15519","citing_title":"Fully Decentralized Cooperative Multi-Agent Reinforcement Learning is A Context Modeling Problem","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJQSIB7XUE7QQVGEGERADWM7HL","json":"https://pith.science/pith/QJQSIB7XUE7QQVGEGERADWM7HL.json","graph_json":"https://pith.science/api/pith-number/QJQSIB7XUE7QQVGEGERADWM7HL/graph.json","events_json":"https://pith.science/api/pith-number/QJQSIB7XUE7QQVGEGERADWM7HL/events.json","paper":"https://pith.science/paper/QJQSIB7X"},"agent_actions":{"view_html":"https://pith.science/pith/QJQSIB7XUE7QQVGEGERADWM7HL","download_json":"https://pith.science/pith/QJQSIB7XUE7QQVGEGERADWM7HL.json","view_paper":"https://pith.science/paper/QJQSIB7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04934&json=true","fetch_graph":"https://pith.science/api/pith-number/QJQSIB7XUE7QQVGEGERADWM7HL/graph.json","fetch_events":"https://pith.science/api/pith-number/QJQSIB7XUE7QQVGEGERADWM7HL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJQSIB7XUE7QQVGEGERADWM7HL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJQSIB7XUE7QQVGEGERADWM7HL/action/storage_attestation","attest_author":"https://pith.science/pith/QJQSIB7XUE7QQVGEGERADWM7HL/action/author_attestation","sign_citation":"https://pith.science/pith/QJQSIB7XUE7QQVGEGERADWM7HL/action/citation_signature","submit_replication":"https://pith.science/pith/QJQSIB7XUE7QQVGEGERADWM7HL/action/replication_record"}},"created_at":"2026-07-05T07:32:00.672955+00:00","updated_at":"2026-07-05T07:32:00.672955+00:00"}