{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UQY7HYO2OJA5HX6S6O45YPORVF","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":"502c1a27572fef9268623058e2112a82d3e25189d1b6ff34a95e07704093549c","cross_cats_sorted":["cs.AI","cs.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-25T20:15:55Z","title_canon_sha256":"5db60d2b6abb492b69c4406c82297d2a804210bb45235a06745517b955c88a67"},"schema_version":"1.0","source":{"id":"1702.07944","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.07944","created_at":"2026-05-18T00:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"1702.07944v2","created_at":"2026-05-18T00:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07944","created_at":"2026-05-18T00:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"UQY7HYO2OJA5","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UQY7HYO2OJA5HX6S","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UQY7HYO2","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:1807257caf72ee8471a174503cf8463397d87b421bccae7fd06090312bbde940","target":"graph","created_at":"2026-05-18T00:42:43Z","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"},"paper":{"abstract_excerpt":"Policy evaluation is a crucial step in many reinforcement-learning procedures, which estimates a value function that predicts states' long-term value under a given policy. In this paper, we focus on policy evaluation with linear function approximation over a fixed dataset. We first transform the empirical policy evaluation problem into a (quadratic) convex-concave saddle point problem, and then present a primal-dual batch gradient method, as well as two stochastic variance reduction methods for solving the problem. These algorithms scale linearly in both sample size and feature dimension. More","authors_text":"Dengyong Zhou, Jianshu Chen, Lihong Li, Lin Xiao, Simon S. Du","cross_cats":["cs.AI","cs.SY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-25T20:15:55Z","title":"Stochastic Variance Reduction Methods for Policy Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07944","kind":"arxiv","version":2},"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:d23c9ddd4dd11bda5d3b2dceaf6cd3e72bdc7ec3f3f788a4b2133674fb9cbbe6","target":"record","created_at":"2026-05-18T00:42:43Z","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":"502c1a27572fef9268623058e2112a82d3e25189d1b6ff34a95e07704093549c","cross_cats_sorted":["cs.AI","cs.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-25T20:15:55Z","title_canon_sha256":"5db60d2b6abb492b69c4406c82297d2a804210bb45235a06745517b955c88a67"},"schema_version":"1.0","source":{"id":"1702.07944","kind":"arxiv","version":2}},"canonical_sha256":"a431f3e1da7241d3dfd2f3b9dc3dd1a943d671d91d8158c5d46ae59129e6c09a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a431f3e1da7241d3dfd2f3b9dc3dd1a943d671d91d8158c5d46ae59129e6c09a","first_computed_at":"2026-05-18T00:42:43.884160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:43.884160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+rIeb6faZUfD60YR93j1v34r/bwoNNpgxHkrGTUEM3tG/lebPnU+uyw0fjH2UP8sPgBAjGdoZff7H3VUtU0fCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:43.884797Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.07944","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d23c9ddd4dd11bda5d3b2dceaf6cd3e72bdc7ec3f3f788a4b2133674fb9cbbe6","sha256:1807257caf72ee8471a174503cf8463397d87b421bccae7fd06090312bbde940"],"state_sha256":"34e74f3daa5e9c4acde6f277eed468aa8fd890b2fd0e9a9e27669fd96053ded0"}