{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GCUAS54O6DWSIGQA6AZA64ICIX","short_pith_number":"pith:GCUAS54O","schema_version":"1.0","canonical_sha256":"30a809778ef0ed241a00f0320f710245fd9aef6ebb27855f19bc7f19c615c8e7","source":{"kind":"arxiv","id":"2209.14344","version":3},"attestation_state":"computed","paper":{"title":"Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Filippos Christianos, Georgios Papoudakis, Stefano V. Albrecht","submitted_at":"2022-09-28T18:14:34Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.14344","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T18:14:34Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"cabf746a53d5f191b3d301689d0570ae83e7312852f48aba800be527c6d5c6b4","abstract_canon_sha256":"cebd15dc262ebaf7681af402664b26891115b6ae12cceb00d87947f8259f41d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:56.612493Z","signature_b64":"qTlLlrkU56rORnRKbKsuggTPUwJghXgD5mLL0eY9NRwHDqD+5rsYLGY1/IFolKcs2sUm5oCgzKqia9MFFZuYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30a809778ef0ed241a00f0320f710245fd9aef6ebb27855f19bc7f19c615c8e7","last_reissued_at":"2026-07-05T07:00:56.612060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:56.612060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Filippos Christianos, Georgios Papoudakis, Stefano V. Albrecht","submitted_at":"2022-09-28T18:14:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14344","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.14344/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.14344","created_at":"2026-07-05T07:00:56.612125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.14344v3","created_at":"2026-07-05T07:00:56.612125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14344","created_at":"2026-07-05T07:00:56.612125+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCUAS54O6DWS","created_at":"2026-07-05T07:00:56.612125+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCUAS54O6DWSIGQA","created_at":"2026-07-05T07:00:56.612125+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCUAS54O","created_at":"2026-07-05T07:00:56.612125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04750","citing_title":"Fog of Love: Engineering Virtuous Agent Behavior with Affinity-based Reinforcement Learning in a Game Environment","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01049","citing_title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCUAS54O6DWSIGQA6AZA64ICIX","json":"https://pith.science/pith/GCUAS54O6DWSIGQA6AZA64ICIX.json","graph_json":"https://pith.science/api/pith-number/GCUAS54O6DWSIGQA6AZA64ICIX/graph.json","events_json":"https://pith.science/api/pith-number/GCUAS54O6DWSIGQA6AZA64ICIX/events.json","paper":"https://pith.science/paper/GCUAS54O"},"agent_actions":{"view_html":"https://pith.science/pith/GCUAS54O6DWSIGQA6AZA64ICIX","download_json":"https://pith.science/pith/GCUAS54O6DWSIGQA6AZA64ICIX.json","view_paper":"https://pith.science/paper/GCUAS54O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.14344&json=true","fetch_graph":"https://pith.science/api/pith-number/GCUAS54O6DWSIGQA6AZA64ICIX/graph.json","fetch_events":"https://pith.science/api/pith-number/GCUAS54O6DWSIGQA6AZA64ICIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCUAS54O6DWSIGQA6AZA64ICIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCUAS54O6DWSIGQA6AZA64ICIX/action/storage_attestation","attest_author":"https://pith.science/pith/GCUAS54O6DWSIGQA6AZA64ICIX/action/author_attestation","sign_citation":"https://pith.science/pith/GCUAS54O6DWSIGQA6AZA64ICIX/action/citation_signature","submit_replication":"https://pith.science/pith/GCUAS54O6DWSIGQA6AZA64ICIX/action/replication_record"}},"created_at":"2026-07-05T07:00:56.612125+00:00","updated_at":"2026-07-05T07:00:56.612125+00:00"}