{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IVF6V2KMDHJ736Y7XZPNCN5SF3","short_pith_number":"pith:IVF6V2KM","schema_version":"1.0","canonical_sha256":"454beae94c19d3fdfb1fbe5ed137b22ec99296cf47af8e173ed51356f0275c99","source":{"kind":"arxiv","id":"2506.22203","version":2},"attestation_state":"computed","paper":{"title":"A Reinforcement Learning Framework for Some Singular Stochastic Control Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Xiang Yu, Xiaodong Luo, Zongxia Liang","submitted_at":"2025-06-27T13:16:31Z","abstract_excerpt":"We develop a continuous-time reinforcement learning framework for a class of singular stochastic control problems without entropy regularization. The optimal singular control is characterized as the optimal singular control law, which is a pair of regions of time and the augmented states. The goal of learning is to identify such an optimal region via the trial-and-error procedure. In this context, we generalize the existing policy evaluation theories with regular controls to learn our optimal singular control law and develop a policy improvement theorem via the region iteration. To facilitate "},"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":"2506.22203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-27T13:16:31Z","cross_cats_sorted":[],"title_canon_sha256":"1afd10eef5cc68e7a92d7a1f670fcb911f2233b3b4dc9346fdc3115a004dff36","abstract_canon_sha256":"c773ae35f8173df2da98ec9dac229a5ceedc690e5f7239fe4d7d9ebb8634ee58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:35.333090Z","signature_b64":"TfXFejl6PFAVpEPLHgABmDdZwJ/qGuHRZpk9/HWdYwSnKgrzaSixxxQyOsr/wXmQYZadrK4po+cRMu2qbOVTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"454beae94c19d3fdfb1fbe5ed137b22ec99296cf47af8e173ed51356f0275c99","last_reissued_at":"2026-05-18T03:09:35.332414Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:35.332414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reinforcement Learning Framework for Some Singular Stochastic Control Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Xiang Yu, Xiaodong Luo, Zongxia Liang","submitted_at":"2025-06-27T13:16:31Z","abstract_excerpt":"We develop a continuous-time reinforcement learning framework for a class of singular stochastic control problems without entropy regularization. The optimal singular control is characterized as the optimal singular control law, which is a pair of regions of time and the augmented states. The goal of learning is to identify such an optimal region via the trial-and-error procedure. In this context, we generalize the existing policy evaluation theories with regular controls to learn our optimal singular control law and develop a policy improvement theorem via the region iteration. To facilitate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22203","kind":"arxiv","version":2},"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":"2506.22203","created_at":"2026-05-18T03:09:35.332516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22203v2","created_at":"2026-05-18T03:09:35.332516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22203","created_at":"2026-05-18T03:09:35.332516+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVF6V2KMDHJ7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVF6V2KMDHJ736Y7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVF6V2KM","created_at":"2026-05-18T12:33:37.589309+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/IVF6V2KMDHJ736Y7XZPNCN5SF3","json":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3.json","graph_json":"https://pith.science/api/pith-number/IVF6V2KMDHJ736Y7XZPNCN5SF3/graph.json","events_json":"https://pith.science/api/pith-number/IVF6V2KMDHJ736Y7XZPNCN5SF3/events.json","paper":"https://pith.science/paper/IVF6V2KM"},"agent_actions":{"view_html":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3","download_json":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3.json","view_paper":"https://pith.science/paper/IVF6V2KM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22203&json=true","fetch_graph":"https://pith.science/api/pith-number/IVF6V2KMDHJ736Y7XZPNCN5SF3/graph.json","fetch_events":"https://pith.science/api/pith-number/IVF6V2KMDHJ736Y7XZPNCN5SF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/action/storage_attestation","attest_author":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/action/author_attestation","sign_citation":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/action/citation_signature","submit_replication":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/action/replication_record"}},"created_at":"2026-05-18T03:09:35.332516+00:00","updated_at":"2026-05-18T03:09:35.332516+00:00"}