{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AY4AKTSDLIXYEZBRAPL7QEXDXZ","short_pith_number":"pith:AY4AKTSD","schema_version":"1.0","canonical_sha256":"0638054e435a2f82643103d7f812e3be7927f2fc803fff97465d73e42ff82be0","source":{"kind":"arxiv","id":"2403.02476","version":2},"attestation_state":"computed","paper":{"title":"A Simple Finite-Time Analysis of TD Learning with Linear Function Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra","submitted_at":"2024-03-04T20:40:02Z","abstract_excerpt":"We study the finite-time convergence of TD learning with linear function approximation under Markovian sampling. Existing proofs for this setting either assume a projection step in the algorithm to simplify the analysis, or require a fairly intricate argument to ensure stability of the iterates. We ask: \\textit{Is it possible to retain the simplicity of a projection-based analysis without actually performing a projection step in the algorithm?} Our main contribution is to show this is possible via a novel two-step argument. In the first step, we use induction to prove that under a standard cho"},"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":"2403.02476","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-04T20:40:02Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"482ef87cd59580f01b6a16b3c915e3eb5b9c1c882cdc066565febc7dd2eaae31","abstract_canon_sha256":"a1d1bb15a3a1eedb224b02689c5e7b61fccb8cdf73996698befefa5c8b3ddf7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:46.280014Z","signature_b64":"fP4UWLdHOLu/z9oI3iuQSqc+vgZ7I5iC4uVQgDSIB2Ls9Os1YaRvh+GEab9/7ZYNIJtorObhGsqJ+OVT6mofCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0638054e435a2f82643103d7f812e3be7927f2fc803fff97465d73e42ff82be0","last_reissued_at":"2026-07-05T08:36:46.279535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:46.279535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Finite-Time Analysis of TD Learning with Linear Function Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra","submitted_at":"2024-03-04T20:40:02Z","abstract_excerpt":"We study the finite-time convergence of TD learning with linear function approximation under Markovian sampling. Existing proofs for this setting either assume a projection step in the algorithm to simplify the analysis, or require a fairly intricate argument to ensure stability of the iterates. We ask: \\textit{Is it possible to retain the simplicity of a projection-based analysis without actually performing a projection step in the algorithm?} Our main contribution is to show this is possible via a novel two-step argument. In the first step, we use induction to prove that under a standard cho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02476","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/2403.02476/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":"2403.02476","created_at":"2026-07-05T08:36:46.279589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02476v2","created_at":"2026-07-05T08:36:46.279589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02476","created_at":"2026-07-05T08:36:46.279589+00:00"},{"alias_kind":"pith_short_12","alias_value":"AY4AKTSDLIXY","created_at":"2026-07-05T08:36:46.279589+00:00"},{"alias_kind":"pith_short_16","alias_value":"AY4AKTSDLIXYEZBR","created_at":"2026-07-05T08:36:46.279589+00:00"},{"alias_kind":"pith_short_8","alias_value":"AY4AKTSD","created_at":"2026-07-05T08:36:46.279589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18183","citing_title":"A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AY4AKTSDLIXYEZBRAPL7QEXDXZ","json":"https://pith.science/pith/AY4AKTSDLIXYEZBRAPL7QEXDXZ.json","graph_json":"https://pith.science/api/pith-number/AY4AKTSDLIXYEZBRAPL7QEXDXZ/graph.json","events_json":"https://pith.science/api/pith-number/AY4AKTSDLIXYEZBRAPL7QEXDXZ/events.json","paper":"https://pith.science/paper/AY4AKTSD"},"agent_actions":{"view_html":"https://pith.science/pith/AY4AKTSDLIXYEZBRAPL7QEXDXZ","download_json":"https://pith.science/pith/AY4AKTSDLIXYEZBRAPL7QEXDXZ.json","view_paper":"https://pith.science/paper/AY4AKTSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02476&json=true","fetch_graph":"https://pith.science/api/pith-number/AY4AKTSDLIXYEZBRAPL7QEXDXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/AY4AKTSDLIXYEZBRAPL7QEXDXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AY4AKTSDLIXYEZBRAPL7QEXDXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AY4AKTSDLIXYEZBRAPL7QEXDXZ/action/storage_attestation","attest_author":"https://pith.science/pith/AY4AKTSDLIXYEZBRAPL7QEXDXZ/action/author_attestation","sign_citation":"https://pith.science/pith/AY4AKTSDLIXYEZBRAPL7QEXDXZ/action/citation_signature","submit_replication":"https://pith.science/pith/AY4AKTSDLIXYEZBRAPL7QEXDXZ/action/replication_record"}},"created_at":"2026-07-05T08:36:46.279589+00:00","updated_at":"2026-07-05T08:36:46.279589+00:00"}