{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GCUAS54O6DWSIGQA6AZA64ICIX","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":"cebd15dc262ebaf7681af402664b26891115b6ae12cceb00d87947f8259f41d2","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T18:14:34Z","title_canon_sha256":"cabf746a53d5f191b3d301689d0570ae83e7312852f48aba800be527c6d5c6b4"},"schema_version":"1.0","source":{"id":"2209.14344","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14344","created_at":"2026-07-05T07:00:56Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14344v3","created_at":"2026-07-05T07:00:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14344","created_at":"2026-07-05T07:00:56Z"},{"alias_kind":"pith_short_12","alias_value":"GCUAS54O6DWS","created_at":"2026-07-05T07:00:56Z"},{"alias_kind":"pith_short_16","alias_value":"GCUAS54O6DWSIGQA","created_at":"2026-07-05T07:00:56Z"},{"alias_kind":"pith_short_8","alias_value":"GCUAS54O","created_at":"2026-07-05T07:00:56Z"}],"graph_snapshots":[{"event_id":"sha256:7f66cc3fde1a9832ed2f4663e3138bcdeceedaa899ae398afd3ae1db4cbee426","target":"graph","created_at":"2026-07-05T07:00:56Z","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/2209.14344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work focuses on equilibrium selection in no-conflict multi-agent games, where we specifically study the problem of selecting a Pareto-optimal Nash equilibrium among several existing equilibria. It has been shown that many state-of-the-art multi-agent reinforcement learning (MARL) algorithms are prone to converging to Pareto-dominated equilibria due to the uncertainty each agent has about the policy of the other agents during training. To address sub-optimal equilibrium selection, we propose Pareto Actor-Critic (Pareto-AC), which is an actor-critic algorithm that utilises a simple property","authors_text":"Filippos Christianos, Georgios Papoudakis, Stefano V. Albrecht","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T18:14:34Z","title":"Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14344","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:ea683019e54c91c823c3dfe0ffd86e380222a85b1d6592652b259b937ea499dc","target":"record","created_at":"2026-07-05T07:00:56Z","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":"cebd15dc262ebaf7681af402664b26891115b6ae12cceb00d87947f8259f41d2","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T18:14:34Z","title_canon_sha256":"cabf746a53d5f191b3d301689d0570ae83e7312852f48aba800be527c6d5c6b4"},"schema_version":"1.0","source":{"id":"2209.14344","kind":"arxiv","version":3}},"canonical_sha256":"30a809778ef0ed241a00f0320f710245fd9aef6ebb27855f19bc7f19c615c8e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30a809778ef0ed241a00f0320f710245fd9aef6ebb27855f19bc7f19c615c8e7","first_computed_at":"2026-07-05T07:00:56.612060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:56.612060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qTlLlrkU56rORnRKbKsuggTPUwJghXgD5mLL0eY9NRwHDqD+5rsYLGY1/IFolKcs2sUm5oCgzKqia9MFFZuYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:56.612493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14344","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea683019e54c91c823c3dfe0ffd86e380222a85b1d6592652b259b937ea499dc","sha256:7f66cc3fde1a9832ed2f4663e3138bcdeceedaa899ae398afd3ae1db4cbee426"],"state_sha256":"37c73eb614a2ef495861ce56e5a0a173b2ecefe9ce875401a19beaa9e500367f"}