{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:W4XSS5IG3A5YYE6QH372RGY7LQ","short_pith_number":"pith:W4XSS5IG","schema_version":"1.0","canonical_sha256":"b72f297506d83b8c13d03effa89b1f5c26604e1acc33f1cb91f7eb5d5771a7e9","source":{"kind":"arxiv","id":"1803.11485","version":2},"attestation_state":"computed","paper":{"title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Mikayel Samvelyan, Shimon Whiteson, Tabish Rashid","submitted_at":"2018-03-30T14:23:39Z","abstract_excerpt":"In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised "},"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":"1803.11485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T14:23:39Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"b8966e267a018f4e59cafaff8614422d9e8aa88bbdd8f08bde3069ea0db27d1c","abstract_canon_sha256":"aa91bb62c75081d4a3636e5b253fb5be334bd57d3e6461768db0f002745f4aef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.143704Z","signature_b64":"0mR2O6P0+oMp+5//ihEYSqzV0i5w5CN+gYqGRlMIIqAPsUJrcWsaEQV+rwKLZYYBgP34S6oteyyGqvsldhn7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b72f297506d83b8c13d03effa89b1f5c26604e1acc33f1cb91f7eb5d5771a7e9","last_reissued_at":"2026-05-18T00:14:06.142938Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.142938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Mikayel Samvelyan, Shimon Whiteson, Tabish Rashid","submitted_at":"2018-03-30T14:23:39Z","abstract_excerpt":"In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11485","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1803.11485","created_at":"2026-05-18T00:14:06.143049+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.11485v2","created_at":"2026-05-18T00:14:06.143049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11485","created_at":"2026-05-18T00:14:06.143049+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4XSS5IG3A5Y","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4XSS5IG3A5YYE6Q","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4XSS5IG","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.12266","citing_title":"Growing Action Spaces","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00318","citing_title":"Multiple Landmark Detection using Multi-Agent Reinforcement Learning","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2511.14135","citing_title":"AdaFair-MARL: Enforcing Adaptive Fairness Constraints in Multi-Agent Reinforcement Learning","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12555","citing_title":"DelAC: A Multi-agent Reinforcement Learning of Team-Symmetric Stochastic Games","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ","json":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ.json","graph_json":"https://pith.science/api/pith-number/W4XSS5IG3A5YYE6QH372RGY7LQ/graph.json","events_json":"https://pith.science/api/pith-number/W4XSS5IG3A5YYE6QH372RGY7LQ/events.json","paper":"https://pith.science/paper/W4XSS5IG"},"agent_actions":{"view_html":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ","download_json":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ.json","view_paper":"https://pith.science/paper/W4XSS5IG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.11485&json=true","fetch_graph":"https://pith.science/api/pith-number/W4XSS5IG3A5YYE6QH372RGY7LQ/graph.json","fetch_events":"https://pith.science/api/pith-number/W4XSS5IG3A5YYE6QH372RGY7LQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/action/storage_attestation","attest_author":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/action/author_attestation","sign_citation":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/action/citation_signature","submit_replication":"https://pith.science/pith/W4XSS5IG3A5YYE6QH372RGY7LQ/action/replication_record"}},"created_at":"2026-05-18T00:14:06.143049+00:00","updated_at":"2026-05-18T00:14:06.143049+00:00"}