{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HIBIX5WLTADDWGTONSH7SVZRN4","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":"2491ae125ab938223a14ee1884c83213688ad8b434b04b31c2b1f4a88a480a88","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-19T16:51:51Z","title_canon_sha256":"5170e4d2ac398e8b824fc8fe1b566b24859006eef51139539df87e916a831170"},"schema_version":"1.0","source":{"id":"2003.08839","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.08839","created_at":"2026-07-05T01:36:29Z"},{"alias_kind":"arxiv_version","alias_value":"2003.08839v2","created_at":"2026-07-05T01:36:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08839","created_at":"2026-07-05T01:36:29Z"},{"alias_kind":"pith_short_12","alias_value":"HIBIX5WLTADD","created_at":"2026-07-05T01:36:29Z"},{"alias_kind":"pith_short_16","alias_value":"HIBIX5WLTADDWGTO","created_at":"2026-07-05T01:36:29Z"},{"alias_kind":"pith_short_8","alias_value":"HIBIX5WL","created_at":"2026-07-05T01:36:29Z"}],"graph_snapshots":[{"event_id":"sha256:dcda15f89a6dc2fc1adaf7bcf8f771121f9887f5b57280bbef1e3c5817609431","target":"graph","created_at":"2026-07-05T01:36:29Z","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/2003.08839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many real-world settings, a team of agents must coordinate its behaviour while acting in a decentralised fashion. At the same time, it is often possible to train the agents in a centralised fashion 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 policies in a centralised end-to-end","authors_text":"Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Mikayel Samvelyan, Shimon Whiteson, Tabish Rashid","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-19T16:51:51Z","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08839","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":"sha256:85a74ac58ce0a5c9eae773b11c172270830e40a228bff9c0dee996ca5428b122","target":"record","created_at":"2026-07-05T01:36:29Z","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":"2491ae125ab938223a14ee1884c83213688ad8b434b04b31c2b1f4a88a480a88","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-19T16:51:51Z","title_canon_sha256":"5170e4d2ac398e8b824fc8fe1b566b24859006eef51139539df87e916a831170"},"schema_version":"1.0","source":{"id":"2003.08839","kind":"arxiv","version":2}},"canonical_sha256":"3a028bf6cb98063b1a6e6c8ff957316f367df0fb8545f377b6ea5c6131c8e3af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a028bf6cb98063b1a6e6c8ff957316f367df0fb8545f377b6ea5c6131c8e3af","first_computed_at":"2026-07-05T01:36:29.033912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:29.033912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j0BUCak4UEUbMPe2q8FKDqem4skz016fkFR7VkJnXa46CGjh2mMb1MYErM7Q/nYW8WjWXmI3pLytlptdwqL6Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:29.034364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.08839","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85a74ac58ce0a5c9eae773b11c172270830e40a228bff9c0dee996ca5428b122","sha256:dcda15f89a6dc2fc1adaf7bcf8f771121f9887f5b57280bbef1e3c5817609431"],"state_sha256":"7075913ee3e4e120433c311d67eff8c81b5f5892a390c382a432a1eaf093891f"}