{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:JRC3KCHH3VEDBXI3HRN5FEUENG","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":"23849be6fc0b0c6403a13ce55aaa1c0dfc0f5a22150ff8d7be9b12241ce991ae","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2014-01-04T19:57:26Z","title_canon_sha256":"defdda68f8af4ca1d982ffff9f2e0dd981ed32adf1f730605b5f201acdbccbd4"},"schema_version":"1.0","source":{"id":"1401.0843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.0843","created_at":"2026-05-18T03:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"1401.0843v1","created_at":"2026-05-18T03:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.0843","created_at":"2026-05-18T03:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"JRC3KCHH3VED","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"JRC3KCHH3VEDBXI3","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"JRC3KCHH","created_at":"2026-05-18T12:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:9e06b83a5e38070d8c26c2c67004ce2c2088f52ba8aacc3f143525a6752cf305","target":"graph","created_at":"2026-05-18T03:03:11Z","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":"This paper studies approximate policy iteration (API) methods which use least-squares Bellman error minimization for policy evaluation. We address several of its enhancements, namely, Bellman error minimization using instrumental variables, least-squares projected Bellman error minimization, and projected Bellman error minimization using instrumental variables. We prove that for a general discrete-time stochastic control problem, Bellman error minimization using instrumental variables is equivalent to both variants of projected Bellman error minimization. An alternative to these API methods is","authors_text":"Somayeh Moazehi, Warren B. Powell, Warren R. Scott","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2014-01-04T19:57:26Z","title":"Least Squares Policy Iteration with Instrumental Variables vs. Direct Policy Search: Comparison Against Optimal Benchmarks Using Energy Storage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.0843","kind":"arxiv","version":1},"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":"sha256:1e8e7314423190ce336539f4eef44fc509c38629166e799ec412194083e335c3","target":"record","created_at":"2026-05-18T03:03:11Z","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":"23849be6fc0b0c6403a13ce55aaa1c0dfc0f5a22150ff8d7be9b12241ce991ae","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2014-01-04T19:57:26Z","title_canon_sha256":"defdda68f8af4ca1d982ffff9f2e0dd981ed32adf1f730605b5f201acdbccbd4"},"schema_version":"1.0","source":{"id":"1401.0843","kind":"arxiv","version":1}},"canonical_sha256":"4c45b508e7dd4830dd1b3c5bd292846998a13cdab4480ed55580bf38907ff9cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c45b508e7dd4830dd1b3c5bd292846998a13cdab4480ed55580bf38907ff9cb","first_computed_at":"2026-05-18T03:03:11.806878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:03:11.806878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w6pN/p4QRy/5wRouIntbg6Oe3zeMtKS5D7hour1N1Lfghrfc3UOSIsceXjLOcxrJLDa1MpScANCWzQVDqALWDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:03:11.807856Z","signed_message":"canonical_sha256_bytes"},"source_id":"1401.0843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e8e7314423190ce336539f4eef44fc509c38629166e799ec412194083e335c3","sha256:9e06b83a5e38070d8c26c2c67004ce2c2088f52ba8aacc3f143525a6752cf305"],"state_sha256":"b63c3f3c292914a58b38539870c2c564818f2967cd69fa1fe30aed7f6de77ed4"}