{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NYCSAKK34JDWZLNXOO36C35HET","short_pith_number":"pith:NYCSAKK3","schema_version":"1.0","canonical_sha256":"6e0520295be2476cadb773b7e16fa724e656dbdf0a97989121897df1b7b782b2","source":{"kind":"arxiv","id":"1909.03510","version":3},"attestation_state":"computed","paper":{"title":"Bi-level Actor-Critic for Multi-agent Coordination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Haifeng Zhang, Jun Wang, Minne Li, Weinan Zhang, Weizhe Chen, Yaodong Yang, Zeren Huang","submitted_at":"2019-09-08T17:10:50Z","abstract_excerpt":"Coordination is one of the essential problems in multi-agent systems. Typically multi-agent reinforcement learning (MARL) methods treat agents equally and the goal is to solve the Markov game to an arbitrary Nash equilibrium (NE) when multiple equilibra exist, thus lacking a solution for NE selection. In this paper, we treat agents \\emph{unequally} and consider Stackelberg equilibrium as a potentially better convergence point than Nash equilibrium in terms of Pareto superiority, especially in cooperative environments. Under Markov games, we formally define the bi-level reinforcement learning p"},"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":"1909.03510","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-09-08T17:10:50Z","cross_cats_sorted":[],"title_canon_sha256":"7af1d16ce40ad646749ab71035d69c893a3b019a2779c43e474a3d4171b654be","abstract_canon_sha256":"d7b2cd5ae3d6ed6078c3a864805fc4d4a89329c5aec5d82ab1baa1da7b9a4567"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:36.314929Z","signature_b64":"XBm6xp3l8034s3GBoHdHelwcTc9BYHHPaXy4/nDFbyts/2vO+7kLvm8RmHQ2Ltee/wTaTkeTf+CbDMHRtv3fDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e0520295be2476cadb773b7e16fa724e656dbdf0a97989121897df1b7b782b2","last_reissued_at":"2026-07-05T00:52:36.314444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:36.314444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bi-level Actor-Critic for Multi-agent Coordination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Haifeng Zhang, Jun Wang, Minne Li, Weinan Zhang, Weizhe Chen, Yaodong Yang, Zeren Huang","submitted_at":"2019-09-08T17:10:50Z","abstract_excerpt":"Coordination is one of the essential problems in multi-agent systems. Typically multi-agent reinforcement learning (MARL) methods treat agents equally and the goal is to solve the Markov game to an arbitrary Nash equilibrium (NE) when multiple equilibra exist, thus lacking a solution for NE selection. In this paper, we treat agents \\emph{unequally} and consider Stackelberg equilibrium as a potentially better convergence point than Nash equilibrium in terms of Pareto superiority, especially in cooperative environments. Under Markov games, we formally define the bi-level reinforcement learning p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03510","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/1909.03510/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":"1909.03510","created_at":"2026-07-05T00:52:36.314533+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.03510v3","created_at":"2026-07-05T00:52:36.314533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03510","created_at":"2026-07-05T00:52:36.314533+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYCSAKK34JDW","created_at":"2026-07-05T00:52:36.314533+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYCSAKK34JDWZLNX","created_at":"2026-07-05T00:52:36.314533+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYCSAKK3","created_at":"2026-07-05T00:52:36.314533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYCSAKK34JDWZLNXOO36C35HET","json":"https://pith.science/pith/NYCSAKK34JDWZLNXOO36C35HET.json","graph_json":"https://pith.science/api/pith-number/NYCSAKK34JDWZLNXOO36C35HET/graph.json","events_json":"https://pith.science/api/pith-number/NYCSAKK34JDWZLNXOO36C35HET/events.json","paper":"https://pith.science/paper/NYCSAKK3"},"agent_actions":{"view_html":"https://pith.science/pith/NYCSAKK34JDWZLNXOO36C35HET","download_json":"https://pith.science/pith/NYCSAKK34JDWZLNXOO36C35HET.json","view_paper":"https://pith.science/paper/NYCSAKK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.03510&json=true","fetch_graph":"https://pith.science/api/pith-number/NYCSAKK34JDWZLNXOO36C35HET/graph.json","fetch_events":"https://pith.science/api/pith-number/NYCSAKK34JDWZLNXOO36C35HET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYCSAKK34JDWZLNXOO36C35HET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYCSAKK34JDWZLNXOO36C35HET/action/storage_attestation","attest_author":"https://pith.science/pith/NYCSAKK34JDWZLNXOO36C35HET/action/author_attestation","sign_citation":"https://pith.science/pith/NYCSAKK34JDWZLNXOO36C35HET/action/citation_signature","submit_replication":"https://pith.science/pith/NYCSAKK34JDWZLNXOO36C35HET/action/replication_record"}},"created_at":"2026-07-05T00:52:36.314533+00:00","updated_at":"2026-07-05T00:52:36.314533+00:00"}