{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PO6NCANF7HJKSAJC553QOH7V2G","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":"9f42a485439f5e64414eb9d0f05b77e5055f9cfe3f107b9b207a8544b35c6f32","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T15:03:56Z","title_canon_sha256":"67036df3dd9c047999c9202e5926fb1f7c803528638d0431afdfeb3be1aeb3cd"},"schema_version":"1.0","source":{"id":"2210.09921","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09921","created_at":"2026-07-05T07:37:37Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09921v4","created_at":"2026-07-05T07:37:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09921","created_at":"2026-07-05T07:37:37Z"},{"alias_kind":"pith_short_12","alias_value":"PO6NCANF7HJK","created_at":"2026-07-05T07:37:37Z"},{"alias_kind":"pith_short_16","alias_value":"PO6NCANF7HJKSAJC","created_at":"2026-07-05T07:37:37Z"},{"alias_kind":"pith_short_8","alias_value":"PO6NCANF","created_at":"2026-07-05T07:37:37Z"}],"graph_snapshots":[{"event_id":"sha256:882d036d877ea4511b3915230ff69ae8f8aea4c5be47146af6f1ee03be48e6c8","target":"graph","created_at":"2026-07-05T07:37:37Z","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/2210.09921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lin Zhao, Xuyang Chen","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T15:03:56Z","title":"Finite-time analysis of single-timescale actor-critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09921","kind":"arxiv","version":4},"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:bf0e71cd3ed740792c2306c6b303e9b44a25a7c053854f62e6e7bea72e0f62d4","target":"record","created_at":"2026-07-05T07:37:37Z","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":"9f42a485439f5e64414eb9d0f05b77e5055f9cfe3f107b9b207a8544b35c6f32","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T15:03:56Z","title_canon_sha256":"67036df3dd9c047999c9202e5926fb1f7c803528638d0431afdfeb3be1aeb3cd"},"schema_version":"1.0","source":{"id":"2210.09921","kind":"arxiv","version":4}},"canonical_sha256":"7bbcd101a5f9d2a90122ef77071ff5d18c54440b29b53585b796671623b0bb84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bbcd101a5f9d2a90122ef77071ff5d18c54440b29b53585b796671623b0bb84","first_computed_at":"2026-07-05T07:37:37.218737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:37.218737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gFCwWFLLjEUlHkbpLyY12IXHYw9h4qg2T2xexwed6cMU1+zHqxMt14/BM1oN37dgiNyTa+RW77AwkV406QBcAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:37.219216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.09921","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf0e71cd3ed740792c2306c6b303e9b44a25a7c053854f62e6e7bea72e0f62d4","sha256:882d036d877ea4511b3915230ff69ae8f8aea4c5be47146af6f1ee03be48e6c8"],"state_sha256":"0c332de0d1d1be476f56454a0899bdf4dec9068eb4fbc05ba8437cf3a0f0915d"}