{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:65TWRS5DMK7KJEEV36FTJCZL5T","short_pith_number":"pith:65TWRS5D","schema_version":"1.0","canonical_sha256":"f76768cba362bea49095df8b348b2becd9f937df3ae120633e98cfad3dfdc33e","source":{"kind":"arxiv","id":"1411.3224","version":2},"attestation_state":"computed","paper":{"title":"On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"L.A. Prashanth, Nathaniel Korda","submitted_at":"2014-11-12T16:22:28Z","abstract_excerpt":"We provide non-asymptotic bounds for the well-known temporal difference learning algorithm TD(0) with linear function approximators. These include high-probability bounds as well as bounds in expectation. Our analysis suggests that a step-size inversely proportional to the number of iterations cannot guarantee optimal rate of convergence unless we assume (partial) knowledge of the stationary distribution for the Markov chain underlying the policy considered. We also provide bounds for the iterate averaged TD(0) variant, which gets rid of the step-size dependency while exhibiting the optimal ra"},"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":"1411.3224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-12T16:22:28Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"2241670e32391165ab3d31bdbad59266617aff52e7e4551bcb67209a7ebff8b2","abstract_canon_sha256":"43a4b4ba6951838448c55df882cfeb03ec0f46ea989196a7c5a1a04771e7cb15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:34:25.354787Z","signature_b64":"8pQsQlvdoQiY1s/mzNUms9BMy0vZiXlVlTrWVVaspMfOLBMVa/Y3V80KzaGjWxED3QVM4hXxY1d8KOSCwRz2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f76768cba362bea49095df8b348b2becd9f937df3ae120633e98cfad3dfdc33e","last_reissued_at":"2026-05-18T01:34:25.354100Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:34:25.354100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"L.A. Prashanth, Nathaniel Korda","submitted_at":"2014-11-12T16:22:28Z","abstract_excerpt":"We provide non-asymptotic bounds for the well-known temporal difference learning algorithm TD(0) with linear function approximators. These include high-probability bounds as well as bounds in expectation. Our analysis suggests that a step-size inversely proportional to the number of iterations cannot guarantee optimal rate of convergence unless we assume (partial) knowledge of the stationary distribution for the Markov chain underlying the policy considered. We also provide bounds for the iterate averaged TD(0) variant, which gets rid of the step-size dependency while exhibiting the optimal ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.3224","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":""},"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":"1411.3224","created_at":"2026-05-18T01:34:25.354194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1411.3224v2","created_at":"2026-05-18T01:34:25.354194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.3224","created_at":"2026-05-18T01:34:25.354194+00:00"},{"alias_kind":"pith_short_12","alias_value":"65TWRS5DMK7K","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"65TWRS5DMK7KJEEV","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"65TWRS5D","created_at":"2026-05-18T12:28:16.859392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65TWRS5DMK7KJEEV36FTJCZL5T","json":"https://pith.science/pith/65TWRS5DMK7KJEEV36FTJCZL5T.json","graph_json":"https://pith.science/api/pith-number/65TWRS5DMK7KJEEV36FTJCZL5T/graph.json","events_json":"https://pith.science/api/pith-number/65TWRS5DMK7KJEEV36FTJCZL5T/events.json","paper":"https://pith.science/paper/65TWRS5D"},"agent_actions":{"view_html":"https://pith.science/pith/65TWRS5DMK7KJEEV36FTJCZL5T","download_json":"https://pith.science/pith/65TWRS5DMK7KJEEV36FTJCZL5T.json","view_paper":"https://pith.science/paper/65TWRS5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1411.3224&json=true","fetch_graph":"https://pith.science/api/pith-number/65TWRS5DMK7KJEEV36FTJCZL5T/graph.json","fetch_events":"https://pith.science/api/pith-number/65TWRS5DMK7KJEEV36FTJCZL5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65TWRS5DMK7KJEEV36FTJCZL5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65TWRS5DMK7KJEEV36FTJCZL5T/action/storage_attestation","attest_author":"https://pith.science/pith/65TWRS5DMK7KJEEV36FTJCZL5T/action/author_attestation","sign_citation":"https://pith.science/pith/65TWRS5DMK7KJEEV36FTJCZL5T/action/citation_signature","submit_replication":"https://pith.science/pith/65TWRS5DMK7KJEEV36FTJCZL5T/action/replication_record"}},"created_at":"2026-05-18T01:34:25.354194+00:00","updated_at":"2026-05-18T01:34:25.354194+00:00"}