{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PO6NCANF7HJKSAJC553QOH7V2G","short_pith_number":"pith:PO6NCANF","schema_version":"1.0","canonical_sha256":"7bbcd101a5f9d2a90122ef77071ff5d18c54440b29b53585b796671623b0bb84","source":{"kind":"arxiv","id":"2210.09921","version":4},"attestation_state":"computed","paper":{"title":"Finite-time analysis of single-timescale actor-critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin Zhao, Xuyang Chen","submitted_at":"2022-10-18T15:03:56Z","abstract_excerpt":"Actor-critic methods have achieved significant success in many challenging applications. However, its finite-time convergence is still poorly understood in the most practical single-timescale form. Existing works on analyzing single-timescale actor-critic have been limited to i.i.d. sampling or tabular setting for simplicity. We investigate the more practical online single-timescale actor-critic algorithm on continuous state space, where the critic assumes linear function approximation and updates with a single Markovian sample per actor step. Previous analysis has been unable to establish the"},"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":"2210.09921","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T15:03:56Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"67036df3dd9c047999c9202e5926fb1f7c803528638d0431afdfeb3be1aeb3cd","abstract_canon_sha256":"9f42a485439f5e64414eb9d0f05b77e5055f9cfe3f107b9b207a8544b35c6f32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:37.219216Z","signature_b64":"gFCwWFLLjEUlHkbpLyY12IXHYw9h4qg2T2xexwed6cMU1+zHqxMt14/BM1oN37dgiNyTa+RW77AwkV406QBcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bbcd101a5f9d2a90122ef77071ff5d18c54440b29b53585b796671623b0bb84","last_reissued_at":"2026-07-05T07:37:37.218737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:37.218737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-time analysis of single-timescale actor-critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin Zhao, Xuyang Chen","submitted_at":"2022-10-18T15:03:56Z","abstract_excerpt":"Actor-critic methods have achieved significant success in many challenging applications. However, its finite-time convergence is still poorly understood in the most practical single-timescale form. Existing works on analyzing single-timescale actor-critic have been limited to i.i.d. sampling or tabular setting for simplicity. We investigate the more practical online single-timescale actor-critic algorithm on continuous state space, where the critic assumes linear function approximation and updates with a single Markovian sample per actor step. Previous analysis has been unable to establish the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09921","kind":"arxiv","version":4},"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/2210.09921/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":"2210.09921","created_at":"2026-07-05T07:37:37.218794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09921v4","created_at":"2026-07-05T07:37:37.218794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09921","created_at":"2026-07-05T07:37:37.218794+00:00"},{"alias_kind":"pith_short_12","alias_value":"PO6NCANF7HJK","created_at":"2026-07-05T07:37:37.218794+00:00"},{"alias_kind":"pith_short_16","alias_value":"PO6NCANF7HJKSAJC","created_at":"2026-07-05T07:37:37.218794+00:00"},{"alias_kind":"pith_short_8","alias_value":"PO6NCANF","created_at":"2026-07-05T07:37:37.218794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01041","citing_title":"Global Optimality of Single-Timescale Actor-Critic under Continuous State-Action Space: A Study on Linear Quadratic Regulator","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PO6NCANF7HJKSAJC553QOH7V2G","json":"https://pith.science/pith/PO6NCANF7HJKSAJC553QOH7V2G.json","graph_json":"https://pith.science/api/pith-number/PO6NCANF7HJKSAJC553QOH7V2G/graph.json","events_json":"https://pith.science/api/pith-number/PO6NCANF7HJKSAJC553QOH7V2G/events.json","paper":"https://pith.science/paper/PO6NCANF"},"agent_actions":{"view_html":"https://pith.science/pith/PO6NCANF7HJKSAJC553QOH7V2G","download_json":"https://pith.science/pith/PO6NCANF7HJKSAJC553QOH7V2G.json","view_paper":"https://pith.science/paper/PO6NCANF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09921&json=true","fetch_graph":"https://pith.science/api/pith-number/PO6NCANF7HJKSAJC553QOH7V2G/graph.json","fetch_events":"https://pith.science/api/pith-number/PO6NCANF7HJKSAJC553QOH7V2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PO6NCANF7HJKSAJC553QOH7V2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PO6NCANF7HJKSAJC553QOH7V2G/action/storage_attestation","attest_author":"https://pith.science/pith/PO6NCANF7HJKSAJC553QOH7V2G/action/author_attestation","sign_citation":"https://pith.science/pith/PO6NCANF7HJKSAJC553QOH7V2G/action/citation_signature","submit_replication":"https://pith.science/pith/PO6NCANF7HJKSAJC553QOH7V2G/action/replication_record"}},"created_at":"2026-07-05T07:37:37.218794+00:00","updated_at":"2026-07-05T07:37:37.218794+00:00"}