{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WKUF75MJJY6QKM7QVUKOGAK4EO","short_pith_number":"pith:WKUF75MJ","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"},"canonical_sha256":"b2a85ff5894e3d0533f0ad14e3015c23924cb14db1842e1917f0e471a49807c2","source":{"kind":"arxiv","id":"2209.07059","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07059","created_at":"2026-05-18T03:10:13Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07059v5","created_at":"2026-05-18T03:10:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07059","created_at":"2026-05-18T03:10:13Z"},{"alias_kind":"pith_short_12","alias_value":"WKUF75MJJY6Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WKUF75MJJY6QKM7Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WKUF75MJ","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WKUF75MJJY6QKM7QVUKOGAK4EO","target":"record","payload":{"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"},"canonical_sha256":"b2a85ff5894e3d0533f0ad14e3015c23924cb14db1842e1917f0e471a49807c2","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"},"source_kind":"arxiv","source_id":"2209.07059","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4c7X6UfhfvtmWjT/KkyjifICdHbefei2GVbbnkhnlGswXhq3K/Uv5Klq8uAkALy83JoZw3B1fjrZzsnxtWycBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T00:54:11.205221Z"},"content_sha256":"ca7503130e2bc6f37fd7ad43f2fb3a7fdf98ede3f581ef555bfa3931d2280331","schema_version":"1.0","event_id":"sha256:ca7503130e2bc6f37fd7ad43f2fb3a7fdf98ede3f581ef555bfa3931d2280331"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WKUF75MJJY6QKM7QVUKOGAK4EO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rNesBb6BjrfjIzlrDOwAyurroBfuiKCOccK2vzjcsiq75HkCdkwJB7PfBaeZe2V9ZU6S5xOEyH9pSxk8mlM0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T00:54:11.205596Z"},"content_sha256":"e2635baaece60744d890996ebba9f2b06371dcb580dca365ba870d092ce563bd","schema_version":"1.0","event_id":"sha256:e2635baaece60744d890996ebba9f2b06371dcb580dca365ba870d092ce563bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/bundle.json","state_url":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-20T00:54:11Z","links":{"resolver":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO","bundle":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/bundle.json","state":"https://pith.science/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKUF75MJJY6QKM7QVUKOGAK4EO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WKUF75MJJY6QKM7QVUKOGAK4EO","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":"fb10c572bb7b593d9ccc97b509979eddb36eafdae22bcd024a8222c8f1a2264c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-09-15T05:46:35Z","title_canon_sha256":"e19cdd9c4249932b9b93db5a0a617ff25f6857e2fa010e39912b2c9e2ce60ac6"},"schema_version":"1.0","source":{"id":"2209.07059","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07059","created_at":"2026-05-18T03:10:13Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07059v5","created_at":"2026-05-18T03:10:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07059","created_at":"2026-05-18T03:10:13Z"},{"alias_kind":"pith_short_12","alias_value":"WKUF75MJJY6Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WKUF75MJJY6QKM7Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WKUF75MJ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:e2635baaece60744d890996ebba9f2b06371dcb580dca365ba870d092ce563bd","target":"graph","created_at":"2026-05-18T03:10:13Z","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":"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","authors_text":"Yu-Jui Huang, Zhenhua Wang, Zhou Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-09-15T05:46:35Z","title":"Convergence of Policy Iteration for Entropy-Regularized Stochastic Control Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07059","kind":"arxiv","version":5},"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:ca7503130e2bc6f37fd7ad43f2fb3a7fdf98ede3f581ef555bfa3931d2280331","target":"record","created_at":"2026-05-18T03:10:13Z","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":"fb10c572bb7b593d9ccc97b509979eddb36eafdae22bcd024a8222c8f1a2264c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-09-15T05:46:35Z","title_canon_sha256":"e19cdd9c4249932b9b93db5a0a617ff25f6857e2fa010e39912b2c9e2ce60ac6"},"schema_version":"1.0","source":{"id":"2209.07059","kind":"arxiv","version":5}},"canonical_sha256":"b2a85ff5894e3d0533f0ad14e3015c23924cb14db1842e1917f0e471a49807c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2a85ff5894e3d0533f0ad14e3015c23924cb14db1842e1917f0e471a49807c2","first_computed_at":"2026-05-18T03:10:13.316534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:13.316534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HWfoKSNU/49fJICLIMCtqK9qfiUpCC4DdsSaHx700H1g5EwldmkI++bgcmZCkSH2visbdyD7IPenc4OCqL/aAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:13.317172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.07059","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca7503130e2bc6f37fd7ad43f2fb3a7fdf98ede3f581ef555bfa3931d2280331","sha256:e2635baaece60744d890996ebba9f2b06371dcb580dca365ba870d092ce563bd"],"state_sha256":"9af04d4c16cb3a9f099e097c24e99d2da00dd625bfaa404ad60fe3406c58d0e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lU9A/L8/9BY2DnWgGTgAFrg5/lJqrIcLo7Lp+aL23srxbqQkQMwvGvMeoi3aw5ehsd6/EzWrFu9F3SoSBy6uBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T00:54:11.207596Z","bundle_sha256":"271c914b44c33b70595c262e1cf85de542a1138b9cd38f387d78b3d8d750da8c"}}