{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WKUF75MJJY6QKM7QVUKOGAK4EO","short_pith_number":"pith:WKUF75MJ","schema_version":"1.0","canonical_sha256":"b2a85ff5894e3d0533f0ad14e3015c23924cb14db1842e1917f0e471a49807c2","source":{"kind":"arxiv","id":"2209.07059","version":5},"attestation_state":"computed","paper":{"title":"Convergence of Policy Iteration for Entropy-Regularized Stochastic Control Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Yu-Jui Huang, Zhenhua Wang, Zhou Zhou","submitted_at":"2022-09-15T05:46:35Z","abstract_excerpt":"For a general entropy-regularized stochastic control problem on an infinite horizon, we prove that a policy iteration algorithm (PIA) converges to an optimal relaxed control. Contrary to the standard stochastic control literature, classical H\\\"{o}lder estimates of value functions do not ensure the convergence of the PIA, due to the added entropy-regularizing term. To circumvent this, we carry out a delicate estimation by moving back and forth between appropriate H\\\"{o}lder and Sobolev spaces. This requires new Sobolev estimates designed specifically for the purpose of policy iteration and a no"},"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":"2209.07059","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-09-15T05:46:35Z","cross_cats_sorted":[],"title_canon_sha256":"e19cdd9c4249932b9b93db5a0a617ff25f6857e2fa010e39912b2c9e2ce60ac6","abstract_canon_sha256":"fb10c572bb7b593d9ccc97b509979eddb36eafdae22bcd024a8222c8f1a2264c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:13.317172Z","signature_b64":"HWfoKSNU/49fJICLIMCtqK9qfiUpCC4DdsSaHx700H1g5EwldmkI++bgcmZCkSH2visbdyD7IPenc4OCqL/aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2a85ff5894e3d0533f0ad14e3015c23924cb14db1842e1917f0e471a49807c2","last_reissued_at":"2026-05-18T03:10:13.316534Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:13.316534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Policy Iteration for Entropy-Regularized Stochastic Control Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Yu-Jui Huang, Zhenhua Wang, Zhou Zhou","submitted_at":"2022-09-15T05:46:35Z","abstract_excerpt":"For a general entropy-regularized stochastic control problem on an infinite horizon, we prove that a policy iteration algorithm (PIA) converges to an optimal relaxed control. Contrary to the standard stochastic control literature, classical H\\\"{o}lder estimates of value functions do not ensure the convergence of the PIA, due to the added entropy-regularizing term. To circumvent this, we carry out a delicate estimation by moving back and forth between appropriate H\\\"{o}lder and Sobolev spaces. This requires new Sobolev estimates designed specifically for the purpose of policy iteration and a no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07059","kind":"arxiv","version":5},"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":"2209.07059","created_at":"2026-05-18T03:10:13.316623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07059v5","created_at":"2026-05-18T03:10:13.316623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07059","created_at":"2026-05-18T03:10:13.316623+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKUF75MJJY6Q","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKUF75MJJY6QKM7Q","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKUF75MJ","created_at":"2026-05-18T12:33:33.725879+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/WKUF75MJJY6QKM7QVUKOGAK4EO","json":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO.json","graph_json":"https://pith.science/api/pith-number/WKUF75MJJY6QKM7QVUKOGAK4EO/graph.json","events_json":"https://pith.science/api/pith-number/WKUF75MJJY6QKM7QVUKOGAK4EO/events.json","paper":"https://pith.science/paper/WKUF75MJ"},"agent_actions":{"view_html":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO","download_json":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO.json","view_paper":"https://pith.science/paper/WKUF75MJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07059&json=true","fetch_graph":"https://pith.science/api/pith-number/WKUF75MJJY6QKM7QVUKOGAK4EO/graph.json","fetch_events":"https://pith.science/api/pith-number/WKUF75MJJY6QKM7QVUKOGAK4EO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/action/storage_attestation","attest_author":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/action/author_attestation","sign_citation":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/action/citation_signature","submit_replication":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/action/replication_record"}},"created_at":"2026-05-18T03:10:13.316623+00:00","updated_at":"2026-05-18T03:10:13.316623+00:00"}