{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NYCSAKK34JDWZLNXOO36C35HET","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":"d7b2cd5ae3d6ed6078c3a864805fc4d4a89329c5aec5d82ab1baa1da7b9a4567","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-09-08T17:10:50Z","title_canon_sha256":"7af1d16ce40ad646749ab71035d69c893a3b019a2779c43e474a3d4171b654be"},"schema_version":"1.0","source":{"id":"1909.03510","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.03510","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"arxiv_version","alias_value":"1909.03510v3","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03510","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"pith_short_12","alias_value":"NYCSAKK34JDW","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"pith_short_16","alias_value":"NYCSAKK34JDWZLNX","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"pith_short_8","alias_value":"NYCSAKK3","created_at":"2026-07-05T00:52:36Z"}],"graph_snapshots":[{"event_id":"sha256:960742d498440b18f6797e3f04b00c2ed09847f8c8df8cb3b02169d4751db0bb","target":"graph","created_at":"2026-07-05T00:52:36Z","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/1909.03510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haifeng Zhang, Jun Wang, Minne Li, Weinan Zhang, Weizhe Chen, Yaodong Yang, Zeren Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-09-08T17:10:50Z","title":"Bi-level Actor-Critic for Multi-agent Coordination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03510","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:d40bb1914a598a5b07f598e2f32321c6fb67033c318977ddbd2a5ad782b78da3","target":"record","created_at":"2026-07-05T00:52:36Z","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":"d7b2cd5ae3d6ed6078c3a864805fc4d4a89329c5aec5d82ab1baa1da7b9a4567","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-09-08T17:10:50Z","title_canon_sha256":"7af1d16ce40ad646749ab71035d69c893a3b019a2779c43e474a3d4171b654be"},"schema_version":"1.0","source":{"id":"1909.03510","kind":"arxiv","version":3}},"canonical_sha256":"6e0520295be2476cadb773b7e16fa724e656dbdf0a97989121897df1b7b782b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e0520295be2476cadb773b7e16fa724e656dbdf0a97989121897df1b7b782b2","first_computed_at":"2026-07-05T00:52:36.314444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:36.314444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XBm6xp3l8034s3GBoHdHelwcTc9BYHHPaXy4/nDFbyts/2vO+7kLvm8RmHQ2Ltee/wTaTkeTf+CbDMHRtv3fDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:36.314929Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.03510","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d40bb1914a598a5b07f598e2f32321c6fb67033c318977ddbd2a5ad782b78da3","sha256:960742d498440b18f6797e3f04b00c2ed09847f8c8df8cb3b02169d4751db0bb"],"state_sha256":"f2cc4c548b1e626b2d08efa8e423aaba0df87d6b1c126fc5f87555e2e3c344b1"}