{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4EFJ5B5EHTX3IVKCOKFCJJ2NDA","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":"de7f5c8e8555c8d85b1dfc3e239fea5282493663d8906f21c7c16a0c700024e1","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-14T16:50:26Z","title_canon_sha256":"dbd2f15c24f696eca1f93d5c533eaf979e139c67fea5724c2564e2c98ea7b398"},"schema_version":"1.0","source":{"id":"1907.06246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.06246","created_at":"2026-05-17T23:40:38Z"},{"alias_kind":"arxiv_version","alias_value":"1907.06246v1","created_at":"2026-05-17T23:40:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.06246","created_at":"2026-05-17T23:40:38Z"},{"alias_kind":"pith_short_12","alias_value":"4EFJ5B5EHTX3","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4EFJ5B5EHTX3IVKC","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4EFJ5B5E","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:0f9f289052e49b3e96d2c336e47d732c5bf6b5776dcb4ba055563e80021e2f58","target":"graph","created_at":"2026-05-17T23:40:38Z","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"},"paper":{"abstract_excerpt":"Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence is known to be fragile. To understand the instability of actor-critic, we focus on its application to linear quadratic regulators, a simple yet fundamental setting of reinforcement learning. We establish a nonasymptotic convergence analysis of actor-critic in this setting. In particular, we prove that actor-critic finds a globally optimal pair of actor (polic","authors_text":"Mingyi Hong, Yongxin Chen, Zhaoran Wang, Zhuoran Yang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-14T16:50:26Z","title":"On the Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.06246","kind":"arxiv","version":1},"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":"sha256:3ebbd5cc02c7fb39fbb16192587f2163e7fd63b43427ce3c8cf04bbf739cf814","target":"record","created_at":"2026-05-17T23:40:38Z","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":"de7f5c8e8555c8d85b1dfc3e239fea5282493663d8906f21c7c16a0c700024e1","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-14T16:50:26Z","title_canon_sha256":"dbd2f15c24f696eca1f93d5c533eaf979e139c67fea5724c2564e2c98ea7b398"},"schema_version":"1.0","source":{"id":"1907.06246","kind":"arxiv","version":1}},"canonical_sha256":"e10a9e87a43cefb45542728a24a74d18181a2ff69c40c460511449ebcc517d7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e10a9e87a43cefb45542728a24a74d18181a2ff69c40c460511449ebcc517d7f","first_computed_at":"2026-05-17T23:40:38.133423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:38.133423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/pHpQpaMccyekzfiZ713++2R3wjtDLi896OQSsvJzTweWV0/yvWvxO0MyAe+MzNaaY0pJfcY4ufxvxHDE6q6AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:38.133941Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.06246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ebbd5cc02c7fb39fbb16192587f2163e7fd63b43427ce3c8cf04bbf739cf814","sha256:0f9f289052e49b3e96d2c336e47d732c5bf6b5776dcb4ba055563e80021e2f58"],"state_sha256":"57e319b5a48eb7bf69ba4fa46c52c2717fcc5a0902cf6a9d9d2d1572668b95b3"}