{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2HVVSJ6PULBWRN3QJYA3KNFAGS","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":"cc3fe089ba0240d2c1d76fd3887862bc444a5cb96a16faba95914088f5a674f4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-23T10:55:33Z","title_canon_sha256":"0a01858c67f77e72c24a314f94f657257cea5729f674c48ea019e4fb955bd338"},"schema_version":"1.0","source":{"id":"2112.12458","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.12458","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2112.12458v3","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12458","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"2HVVSJ6PULBW","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"2HVVSJ6PULBWRN3Q","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"2HVVSJ6P","created_at":"2026-07-05T07:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:45c035bbf19d8c1e7918bfdd3833f64f7f0ff5401d2a0b4984fece2ee0038d1a","target":"graph","created_at":"2026-07-05T07:05:04Z","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/2112.12458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many recent successful off-policy multi-agent reinforcement learning (MARL) algorithms for cooperative partially observable environments focus on finding factorized value functions, leading to convoluted network structures. Building on the structure of independent Q-learners, our LAN algorithm takes a radically different approach, leveraging a dueling architecture to learn for each agent a decentralized best-response policies via individual advantage functions. The learning is stabilized by a centralized critic whose primary objective is to reduce the moving target problem of the individual ad","authors_text":"Ann Now\\'e, Diederik M. Roijers, Mathieu Reymond, Rapha\\\"el Avalos","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-23T10:55:33Z","title":"Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12458","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:d7ef7bc9f70509aaa22b541de79bc2019b9b997ecf5dd2ff0aa71cda9a3adc0d","target":"record","created_at":"2026-07-05T07:05:04Z","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":"cc3fe089ba0240d2c1d76fd3887862bc444a5cb96a16faba95914088f5a674f4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-23T10:55:33Z","title_canon_sha256":"0a01858c67f77e72c24a314f94f657257cea5729f674c48ea019e4fb955bd338"},"schema_version":"1.0","source":{"id":"2112.12458","kind":"arxiv","version":3}},"canonical_sha256":"d1eb5927cfa2c368b7704e01b534a034bfa66a184f95e65a7d02fc7afe094af1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1eb5927cfa2c368b7704e01b534a034bfa66a184f95e65a7d02fc7afe094af1","first_computed_at":"2026-07-05T07:05:04.127882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:04.127882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zz+ibs66hJ3PjslAm8Wv5flK74OR8uU8NnVTlLUH/uvVrCH22Ai+Vp6F2uQe3ZPY1IgIjR64k01UC6/1zlnBDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:04.128407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.12458","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7ef7bc9f70509aaa22b541de79bc2019b9b997ecf5dd2ff0aa71cda9a3adc0d","sha256:45c035bbf19d8c1e7918bfdd3833f64f7f0ff5401d2a0b4984fece2ee0038d1a"],"state_sha256":"57f87bb0c7e83246f976cfbb2db0007bf350adddb0bdfa3e85c3ca71cf86e7b4"}