{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:JRC3KCHH3VEDBXI3HRN5FEUENG","short_pith_number":"pith:JRC3KCHH","schema_version":"1.0","canonical_sha256":"4c45b508e7dd4830dd1b3c5bd292846998a13cdab4480ed55580bf38907ff9cb","source":{"kind":"arxiv","id":"1401.0843","version":1},"attestation_state":"computed","paper":{"title":"Least Squares Policy Iteration with Instrumental Variables vs. Direct Policy Search: Comparison Against Optimal Benchmarks Using Energy Storage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Somayeh Moazehi, Warren B. Powell, Warren R. Scott","submitted_at":"2014-01-04T19:57:26Z","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"},"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":"1401.0843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2014-01-04T19:57:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"defdda68f8af4ca1d982ffff9f2e0dd981ed32adf1f730605b5f201acdbccbd4","abstract_canon_sha256":"23849be6fc0b0c6403a13ce55aaa1c0dfc0f5a22150ff8d7be9b12241ce991ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:03:11.807856Z","signature_b64":"w6pN/p4QRy/5wRouIntbg6Oe3zeMtKS5D7hour1N1Lfghrfc3UOSIsceXjLOcxrJLDa1MpScANCWzQVDqALWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c45b508e7dd4830dd1b3c5bd292846998a13cdab4480ed55580bf38907ff9cb","last_reissued_at":"2026-05-18T03:03:11.806878Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:03:11.806878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Least Squares Policy Iteration with Instrumental Variables vs. Direct Policy Search: Comparison Against Optimal Benchmarks Using Energy Storage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Somayeh Moazehi, Warren B. Powell, Warren R. Scott","submitted_at":"2014-01-04T19:57:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.0843","kind":"arxiv","version":1},"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":"1401.0843","created_at":"2026-05-18T03:03:11.807034+00:00"},{"alias_kind":"arxiv_version","alias_value":"1401.0843v1","created_at":"2026-05-18T03:03:11.807034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.0843","created_at":"2026-05-18T03:03:11.807034+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRC3KCHH3VED","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRC3KCHH3VEDBXI3","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRC3KCHH","created_at":"2026-05-18T12:28:35.611951+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/JRC3KCHH3VEDBXI3HRN5FEUENG","json":"https://pith.science/pith/JRC3KCHH3VEDBXI3HRN5FEUENG.json","graph_json":"https://pith.science/api/pith-number/JRC3KCHH3VEDBXI3HRN5FEUENG/graph.json","events_json":"https://pith.science/api/pith-number/JRC3KCHH3VEDBXI3HRN5FEUENG/events.json","paper":"https://pith.science/paper/JRC3KCHH"},"agent_actions":{"view_html":"https://pith.science/pith/JRC3KCHH3VEDBXI3HRN5FEUENG","download_json":"https://pith.science/pith/JRC3KCHH3VEDBXI3HRN5FEUENG.json","view_paper":"https://pith.science/paper/JRC3KCHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1401.0843&json=true","fetch_graph":"https://pith.science/api/pith-number/JRC3KCHH3VEDBXI3HRN5FEUENG/graph.json","fetch_events":"https://pith.science/api/pith-number/JRC3KCHH3VEDBXI3HRN5FEUENG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRC3KCHH3VEDBXI3HRN5FEUENG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRC3KCHH3VEDBXI3HRN5FEUENG/action/storage_attestation","attest_author":"https://pith.science/pith/JRC3KCHH3VEDBXI3HRN5FEUENG/action/author_attestation","sign_citation":"https://pith.science/pith/JRC3KCHH3VEDBXI3HRN5FEUENG/action/citation_signature","submit_replication":"https://pith.science/pith/JRC3KCHH3VEDBXI3HRN5FEUENG/action/replication_record"}},"created_at":"2026-05-18T03:03:11.807034+00:00","updated_at":"2026-05-18T03:03:11.807034+00:00"}