{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4IRCROHVZNILBWFTLC2AJKEAHH","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":"19e2da07c1dfb507745e225d826d9a677479f1353885896e75ecb260eff00bc4","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-24T18:52:17Z","title_canon_sha256":"129799faef3367462664e92fdcb43f80296c1bc0bbad39200aed10b2ca973a3a"},"schema_version":"1.0","source":{"id":"1705.08926","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08926","created_at":"2026-07-05T09:47:24Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08926v3","created_at":"2026-07-05T09:47:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08926","created_at":"2026-07-05T09:47:24Z"},{"alias_kind":"pith_short_12","alias_value":"4IRCROHVZNIL","created_at":"2026-07-05T09:47:24Z"},{"alias_kind":"pith_short_16","alias_value":"4IRCROHVZNILBWFT","created_at":"2026-07-05T09:47:24Z"},{"alias_kind":"pith_short_8","alias_value":"4IRCROHV","created_at":"2026-07-05T09:47:24Z"}],"graph_snapshots":[{"event_id":"sha256:29dd76da52a2e853a759c19a42ce0f0489210484fd208a26c3eb2f2af6368bf2","target":"graph","created_at":"2026-07-05T09:47:24Z","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/1705.08926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative multi-agent systems can be naturally used to model many real world problems, such as network packet routing and the coordination of autonomous vehicles. There is a great need for new reinforcement learning methods that can efficiently learn decentralised policies for such systems. To this end, we propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients. COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies. In addition, to address the challenges of multi-agent credit assignm","authors_text":"Gregory Farquhar, Jakob Foerster, Nantas Nardelli, Shimon Whiteson, Triantafyllos Afouras","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-24T18:52:17Z","title":"Counterfactual Multi-Agent Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08926","kind":"arxiv","version":3},"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:c4380e8ea2b2a5c10c49b7f86e0635bf1aa5584cea96dbd2f4cdf5fe11920edf","target":"record","created_at":"2026-07-05T09:47:24Z","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":"19e2da07c1dfb507745e225d826d9a677479f1353885896e75ecb260eff00bc4","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-24T18:52:17Z","title_canon_sha256":"129799faef3367462664e92fdcb43f80296c1bc0bbad39200aed10b2ca973a3a"},"schema_version":"1.0","source":{"id":"1705.08926","kind":"arxiv","version":3}},"canonical_sha256":"e22228b8f5cb50b0d8b358b404a88039cde86996b0ac84c316118037ead171f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e22228b8f5cb50b0d8b358b404a88039cde86996b0ac84c316118037ead171f1","first_computed_at":"2026-07-05T09:47:24.175907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:24.175907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z7EKOI6Plfm6LvLMmjg/GSyBTNU4tG/buFctl+XB0yl4/db+TIoUeT6tdQmaGHE5nuow5D9NjyUrzB71ILgzAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:24.176408Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08926","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4380e8ea2b2a5c10c49b7f86e0635bf1aa5584cea96dbd2f4cdf5fe11920edf","sha256:29dd76da52a2e853a759c19a42ce0f0489210484fd208a26c3eb2f2af6368bf2"],"state_sha256":"f31d88d04e593a068802a722b17698f5d34be52ab4acb3d2adeeddd1e576fd9b"}