{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WWIKMOZM25FCRX5RHYRJURMUOJ","short_pith_number":"pith:WWIKMOZM","schema_version":"1.0","canonical_sha256":"b590a63b2cd74a28dfb13e229a4594725bd6d6f638438ec7c3de1ba3b98aa3c0","source":{"kind":"arxiv","id":"2512.04697","version":3},"attestation_state":"computed","paper":{"title":"Continuous-time reinforcement learning for optimal switching over multiple regimes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.CP"],"primary_cat":"math.OC","authors_text":"Mengge Li, Xiang Yu, Yijie Huang, Zhou Zhou","submitted_at":"2025-12-04T11:48:07Z","abstract_excerpt":"This paper studies the continuous-time reinforcement learning (RL) for optimal switching problems across multiple regimes. We consider a type of exploratory formulation under entropy regularization where the agent randomizes both the timing of switches and the selection of regimes through the generator matrix of an associated continuous-time finite-state Markov chain. We establish the well-posedness of the associated system of Hamilton-Jacobi-Bellman (HJB) equations and provide a characterization of the optimal policy. The policy improvement and the convergence of the policy iterations are rig"},"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":"2512.04697","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-12-04T11:48:07Z","cross_cats_sorted":["cs.LG","q-fin.CP"],"title_canon_sha256":"629e83184e871638facfcc3fbcf092f986987c631c7bddce0a7436fea773447a","abstract_canon_sha256":"91f14b68a9cda9253985ded9dce877478b425d8b09684c4c7692a0e2baa00db3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b590a63b2cd74a28dfb13e229a4594725bd6d6f638438ec7c3de1ba3b98aa3c0","last_reissued_at":"2026-07-31T01:08:54.841852Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:08:54.841852Z"},"graph_snapshot":{"paper":{"title":"Continuous-time reinforcement learning for optimal switching over multiple regimes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.CP"],"primary_cat":"math.OC","authors_text":"Mengge Li, Xiang Yu, Yijie Huang, Zhou Zhou","submitted_at":"2025-12-04T11:48:07Z","abstract_excerpt":"This paper studies the continuous-time reinforcement learning (RL) for optimal switching problems across multiple regimes. We consider a type of exploratory formulation under entropy regularization where the agent randomizes both the timing of switches and the selection of regimes through the generator matrix of an associated continuous-time finite-state Markov chain. We establish the well-posedness of the associated system of Hamilton-Jacobi-Bellman (HJB) equations and provide a characterization of the optimal policy. The policy improvement and the convergence of the policy iterations are rig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.04697","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.04697/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2512.04697","created_at":"2026-07-31T01:08:54.844845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.04697v3","created_at":"2026-07-31T01:08:54.844845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.04697","created_at":"2026-07-31T01:08:54.844845+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWIKMOZM25FC","created_at":"2026-07-31T01:08:54.844845+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWIKMOZM25FCRX5R","created_at":"2026-07-31T01:08:54.844845+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWIKMOZM","created_at":"2026-07-31T01:08:54.844845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2606.12875","citing_title":"Randomized Optimal Switching Problem and Related Mirror Descent Flow","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11798","citing_title":"Deterministic Policy Gradient for Learning Equilibrium in Time-Inconsistent Control Problems","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29892","citing_title":"Mean Field Competition of Optimal Switching: The Vanishing Entropy Regularization Approach","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2603.10321","citing_title":"Equilibrium under Time-Inconsistency: A New Existence Theory by Vanishing Entropy Regularization","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14363","citing_title":"Equilibrium for Time-inconsistent Mean Field Games: A Systematic Analysis by Entropy Regularization","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27378","citing_title":"Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27372","citing_title":"Continuous-time q-learning for mean-field control with common noise, part-I: Theoretical foundations","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWIKMOZM25FCRX5RHYRJURMUOJ","json":"https://pith.science/pith/WWIKMOZM25FCRX5RHYRJURMUOJ.json","graph_json":"https://pith.science/api/pith-number/WWIKMOZM25FCRX5RHYRJURMUOJ/graph.json","events_json":"https://pith.science/api/pith-number/WWIKMOZM25FCRX5RHYRJURMUOJ/events.json","paper":"https://pith.science/paper/WWIKMOZM"},"agent_actions":{"view_html":"https://pith.science/pith/WWIKMOZM25FCRX5RHYRJURMUOJ","download_json":"https://pith.science/pith/WWIKMOZM25FCRX5RHYRJURMUOJ.json","view_paper":"https://pith.science/paper/WWIKMOZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.04697&json=true","fetch_graph":"https://pith.science/api/pith-number/WWIKMOZM25FCRX5RHYRJURMUOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WWIKMOZM25FCRX5RHYRJURMUOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWIKMOZM25FCRX5RHYRJURMUOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWIKMOZM25FCRX5RHYRJURMUOJ/action/storage_attestation","attest_author":"https://pith.science/pith/WWIKMOZM25FCRX5RHYRJURMUOJ/action/author_attestation","sign_citation":"https://pith.science/pith/WWIKMOZM25FCRX5RHYRJURMUOJ/action/citation_signature","submit_replication":"https://pith.science/pith/WWIKMOZM25FCRX5RHYRJURMUOJ/action/replication_record"}},"created_at":"2026-07-31T01:08:54.844845+00:00","updated_at":"2026-07-31T01:08:54.844845+00:00"}