{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:V4IFOFT4IJZLPFJ5GAJEPIIXFZ","short_pith_number":"pith:V4IFOFT4","schema_version":"1.0","canonical_sha256":"af1057167c4272b7953d301247a1172e74c330aa8f9c4fff9699687cff59ab28","source":{"kind":"arxiv","id":"1806.02450","version":2},"attestation_state":"computed","paper":{"title":"A Finite Time Analysis of Temporal Difference Learning With Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Russo, Jalaj Bhandari, Raghav Singal","submitted_at":"2018-06-06T22:57:08Z","abstract_excerpt":"Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement learning, its theoretical analysis has proved challenging and few guarantees on its statistical efficiency are available. In this work, we provide a simple and explicit finite time analysis of temporal difference learning with linear function approximation. Except for a few key insights, our analysis mirrors standard techniques for analyzing stochastic gradient d"},"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":"1806.02450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T22:57:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"04d54da77a160dcb06d23a23a11a2461a7c9fcf2288f16501e04697378eebef0","abstract_canon_sha256":"94971ea2bbf5f16bffe73acd9b50e558768d16cf78d2d17d734a5cf5e6fed890"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:29.366929Z","signature_b64":"W3l+UcE7dIHTQMTJm1g0+xRUlIa527pMemktdOthP9NHBcjN+GGGLubA0Z+BXgGsSOwnSvwMSaalnyaUervECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af1057167c4272b7953d301247a1172e74c330aa8f9c4fff9699687cff59ab28","last_reissued_at":"2026-05-18T00:01:29.366470Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:29.366470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Finite Time Analysis of Temporal Difference Learning With Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Russo, Jalaj Bhandari, Raghav Singal","submitted_at":"2018-06-06T22:57:08Z","abstract_excerpt":"Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement learning, its theoretical analysis has proved challenging and few guarantees on its statistical efficiency are available. In this work, we provide a simple and explicit finite time analysis of temporal difference learning with linear function approximation. Except for a few key insights, our analysis mirrors standard techniques for analyzing stochastic gradient d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02450","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":"1806.02450","created_at":"2026-05-18T00:01:29.366552+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02450v2","created_at":"2026-05-18T00:01:29.366552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02450","created_at":"2026-05-18T00:01:29.366552+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4IFOFT4IJZL","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4IFOFT4IJZLPFJ5","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4IFOFT4","created_at":"2026-05-18T12:32:56.356000+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/V4IFOFT4IJZLPFJ5GAJEPIIXFZ","json":"https://pith.science/pith/V4IFOFT4IJZLPFJ5GAJEPIIXFZ.json","graph_json":"https://pith.science/api/pith-number/V4IFOFT4IJZLPFJ5GAJEPIIXFZ/graph.json","events_json":"https://pith.science/api/pith-number/V4IFOFT4IJZLPFJ5GAJEPIIXFZ/events.json","paper":"https://pith.science/paper/V4IFOFT4"},"agent_actions":{"view_html":"https://pith.science/pith/V4IFOFT4IJZLPFJ5GAJEPIIXFZ","download_json":"https://pith.science/pith/V4IFOFT4IJZLPFJ5GAJEPIIXFZ.json","view_paper":"https://pith.science/paper/V4IFOFT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02450&json=true","fetch_graph":"https://pith.science/api/pith-number/V4IFOFT4IJZLPFJ5GAJEPIIXFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/V4IFOFT4IJZLPFJ5GAJEPIIXFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4IFOFT4IJZLPFJ5GAJEPIIXFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4IFOFT4IJZLPFJ5GAJEPIIXFZ/action/storage_attestation","attest_author":"https://pith.science/pith/V4IFOFT4IJZLPFJ5GAJEPIIXFZ/action/author_attestation","sign_citation":"https://pith.science/pith/V4IFOFT4IJZLPFJ5GAJEPIIXFZ/action/citation_signature","submit_replication":"https://pith.science/pith/V4IFOFT4IJZLPFJ5GAJEPIIXFZ/action/replication_record"}},"created_at":"2026-05-18T00:01:29.366552+00:00","updated_at":"2026-05-18T00:01:29.366552+00:00"}