{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:X72JH4KJPNYWISDSWUGEOD37KV","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":"2e91cdd2ba054061b6afbfe0d5d87f2a914127c1f46cc49db50df76925affc1f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-14T21:29:09Z","title_canon_sha256":"6505fbd71a2075d33e54525824d5636710e8db22dc2358b58261f7b885994128"},"schema_version":"1.0","source":{"id":"2003.06709","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.06709","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2003.06709v5","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06709","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"X72JH4KJPNYW","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"pith_short_16","alias_value":"X72JH4KJPNYWISDS","created_at":"2026-07-05T02:38:13Z"},{"alias_kind":"pith_short_8","alias_value":"X72JH4KJ","created_at":"2026-07-05T02:38:13Z"}],"graph_snapshots":[{"event_id":"sha256:3f8b451414392bb46572cb7e8eae533f3d521421d85637f944a8ead7c406cda9","target":"graph","created_at":"2026-07-05T02:38:13Z","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/2003.06709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose FACtored Multi-Agent Centralised policy gradients (FACMAC), a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces. Like MADDPG, a popular multi-agent actor-critic method, our approach uses deep deterministic policy gradients to learn policies. However, FACMAC learns a centralised but factored critic, which combines per-agent utilities into the joint action-value function via a non-linear monotonic function, as in QMIX, a popular multi-agent Q-learning algorithm. However, unlike QMIX, there are no inherent constraints on factori","authors_text":"Bei Peng, Christian A. Schroeder de Witt, Philip H. S. Torr, Pierre-Alexandre Kamienny, Shimon Whiteson, Tabish Rashid, Wendelin B\\\"ohmer","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-14T21:29:09Z","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06709","kind":"arxiv","version":5},"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":"sha256:8b9b0c07710d054852972a7ed991357d67dcbea5b1d95bec428811388c712184","target":"record","created_at":"2026-07-05T02:38:13Z","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":"2e91cdd2ba054061b6afbfe0d5d87f2a914127c1f46cc49db50df76925affc1f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-14T21:29:09Z","title_canon_sha256":"6505fbd71a2075d33e54525824d5636710e8db22dc2358b58261f7b885994128"},"schema_version":"1.0","source":{"id":"2003.06709","kind":"arxiv","version":5}},"canonical_sha256":"bff493f1497b71644872b50c470f7f5547e08b4d09f852470ad88d1ff1dd2094","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bff493f1497b71644872b50c470f7f5547e08b4d09f852470ad88d1ff1dd2094","first_computed_at":"2026-07-05T02:38:13.024290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:13.024290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uYzyEcvCiDxEC1F0p3/K5nF7Lhl7l6ZIy6z0ARBbYj9EIIxo7T0/kAb2aQ6o7oW8zk/7ifl2bhLkszjKkyJuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:13.024713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.06709","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b9b0c07710d054852972a7ed991357d67dcbea5b1d95bec428811388c712184","sha256:3f8b451414392bb46572cb7e8eae533f3d521421d85637f944a8ead7c406cda9"],"state_sha256":"93e11f6930b0cf947db29e3753877803ea41e32ffe81cd27b4850852bb1b4a6f"}