{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A5CJZAB4Z6RLUDXXDO6DSR4LYS","short_pith_number":"pith:A5CJZAB4","schema_version":"1.0","canonical_sha256":"07449c803ccfa2ba0ef71bbc39478bc48e239535eca13bd8e380892b43fa661c","source":{"kind":"arxiv","id":"2305.19001","version":2},"attestation_state":"computed","paper":{"title":"High-probability sample complexities for policy evaluation with linear function approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alessandro Rinaldo, Cong Ma, Gen Li, Weichen Wu, Yuejie Chi, Yuting Wei","submitted_at":"2023-05-30T12:58:39Z","abstract_excerpt":"This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation error of the best linear coefficients for two widely-used policy evaluation algorithms: the temporal difference (TD) learning algorithm and the two-timescale linear TD with gradient correction (TDC) algorithm. In both the on-policy setting, where observations are generated from the target policy, and the off-policy setting, where samples are drawn from a beh"},"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":"2305.19001","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-30T12:58:39Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"title_canon_sha256":"93a8bf38a9337355132506131293702559ba0ad5842740f79c3a55e1164df554","abstract_canon_sha256":"89ac4fa4106ed3ee9d7c4dc7059c5dae8530f507f5df819adbdb6c7d1150dafa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:17.803296Z","signature_b64":"V8N5cIKIq1jdvx0bDsPidKco1LaCWkcNoU395XCRoG0k+KbLwkULEkcp2u9zIjZeJXQfh5A7FWVdgFzHSDUHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07449c803ccfa2ba0ef71bbc39478bc48e239535eca13bd8e380892b43fa661c","last_reissued_at":"2026-07-05T08:14:17.802842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:17.802842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-probability sample complexities for policy evaluation with linear function approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alessandro Rinaldo, Cong Ma, Gen Li, Weichen Wu, Yuejie Chi, Yuting Wei","submitted_at":"2023-05-30T12:58:39Z","abstract_excerpt":"This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation error of the best linear coefficients for two widely-used policy evaluation algorithms: the temporal difference (TD) learning algorithm and the two-timescale linear TD with gradient correction (TDC) algorithm. In both the on-policy setting, where observations are generated from the target policy, and the off-policy setting, where samples are drawn from a beh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19001","kind":"arxiv","version":2},"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/2305.19001/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":"2305.19001","created_at":"2026-07-05T08:14:17.802888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19001v2","created_at":"2026-07-05T08:14:17.802888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19001","created_at":"2026-07-05T08:14:17.802888+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5CJZAB4Z6RL","created_at":"2026-07-05T08:14:17.802888+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5CJZAB4Z6RLUDXX","created_at":"2026-07-05T08:14:17.802888+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5CJZAB4","created_at":"2026-07-05T08:14:17.802888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22492","citing_title":"Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS","json":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS.json","graph_json":"https://pith.science/api/pith-number/A5CJZAB4Z6RLUDXXDO6DSR4LYS/graph.json","events_json":"https://pith.science/api/pith-number/A5CJZAB4Z6RLUDXXDO6DSR4LYS/events.json","paper":"https://pith.science/paper/A5CJZAB4"},"agent_actions":{"view_html":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS","download_json":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS.json","view_paper":"https://pith.science/paper/A5CJZAB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19001&json=true","fetch_graph":"https://pith.science/api/pith-number/A5CJZAB4Z6RLUDXXDO6DSR4LYS/graph.json","fetch_events":"https://pith.science/api/pith-number/A5CJZAB4Z6RLUDXXDO6DSR4LYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/action/storage_attestation","attest_author":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/action/author_attestation","sign_citation":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/action/citation_signature","submit_replication":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/action/replication_record"}},"created_at":"2026-07-05T08:14:17.802888+00:00","updated_at":"2026-07-05T08:14:17.802888+00:00"}