{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MVHJLDN5T6ZFR74UIUXJIQ4GIC","short_pith_number":"pith:MVHJLDN5","schema_version":"1.0","canonical_sha256":"654e958dbd9fb258ff94452e944386409b0e4a23db834f5efd9be1b729384c60","source":{"kind":"arxiv","id":"2404.17939","version":2},"attestation_state":"computed","paper":{"title":"Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Huy\\^en Pham, Robert Denkert, Xavier Warin","submitted_at":"2024-04-27T15:41:06Z","abstract_excerpt":"We propose a comprehensive framework for policy gradient methods tailored to continuous time reinforcement learning. This is based on the connection between stochastic control problems and randomised problems, enabling applications across various classes of Markovian continuous time control problems, beyond diffusion models, including e.g. regular, impulse and optimal stopping/switching problems. By utilizing change of measure in the control randomisation technique, we derive a new policy gradient representation for these randomised problems, featuring parametrised intensity policies. We furth"},"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":"2404.17939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-04-27T15:41:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7c2af375ae1d11621a25d83c8d83faf5d76ad6d4d1532ee75211bd0c28cea9f2","abstract_canon_sha256":"533052d577e92512f4c46ebba73d78d791a2c7bbe9a440f0cd635679ebad84f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:34.279278Z","signature_b64":"dKi5C++xHaGJuaNbxRt4A2kfMYVHdQLw6ntVJVFcths18vCPLDJXzGw06QHQcSxB6z/eMV/4mLl3SIbhHUJUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"654e958dbd9fb258ff94452e944386409b0e4a23db834f5efd9be1b729384c60","last_reissued_at":"2026-07-05T08:13:34.278726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:34.278726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Huy\\^en Pham, Robert Denkert, Xavier Warin","submitted_at":"2024-04-27T15:41:06Z","abstract_excerpt":"We propose a comprehensive framework for policy gradient methods tailored to continuous time reinforcement learning. This is based on the connection between stochastic control problems and randomised problems, enabling applications across various classes of Markovian continuous time control problems, beyond diffusion models, including e.g. regular, impulse and optimal stopping/switching problems. By utilizing change of measure in the control randomisation technique, we derive a new policy gradient representation for these randomised problems, featuring parametrised intensity policies. We furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17939","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.17939/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":"2404.17939","created_at":"2026-07-05T08:13:34.278788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17939v2","created_at":"2026-07-05T08:13:34.278788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17939","created_at":"2026-07-05T08:13:34.278788+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVHJLDN5T6ZF","created_at":"2026-07-05T08:13:34.278788+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVHJLDN5T6ZFR74U","created_at":"2026-07-05T08:13:34.278788+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVHJLDN5","created_at":"2026-07-05T08:13:34.278788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16659","citing_title":"Exploratory Mean-Variance Portfolio Optimization with Regime-Switching Market Dynamics","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVHJLDN5T6ZFR74UIUXJIQ4GIC","json":"https://pith.science/pith/MVHJLDN5T6ZFR74UIUXJIQ4GIC.json","graph_json":"https://pith.science/api/pith-number/MVHJLDN5T6ZFR74UIUXJIQ4GIC/graph.json","events_json":"https://pith.science/api/pith-number/MVHJLDN5T6ZFR74UIUXJIQ4GIC/events.json","paper":"https://pith.science/paper/MVHJLDN5"},"agent_actions":{"view_html":"https://pith.science/pith/MVHJLDN5T6ZFR74UIUXJIQ4GIC","download_json":"https://pith.science/pith/MVHJLDN5T6ZFR74UIUXJIQ4GIC.json","view_paper":"https://pith.science/paper/MVHJLDN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17939&json=true","fetch_graph":"https://pith.science/api/pith-number/MVHJLDN5T6ZFR74UIUXJIQ4GIC/graph.json","fetch_events":"https://pith.science/api/pith-number/MVHJLDN5T6ZFR74UIUXJIQ4GIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVHJLDN5T6ZFR74UIUXJIQ4GIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVHJLDN5T6ZFR74UIUXJIQ4GIC/action/storage_attestation","attest_author":"https://pith.science/pith/MVHJLDN5T6ZFR74UIUXJIQ4GIC/action/author_attestation","sign_citation":"https://pith.science/pith/MVHJLDN5T6ZFR74UIUXJIQ4GIC/action/citation_signature","submit_replication":"https://pith.science/pith/MVHJLDN5T6ZFR74UIUXJIQ4GIC/action/replication_record"}},"created_at":"2026-07-05T08:13:34.278788+00:00","updated_at":"2026-07-05T08:13:34.278788+00:00"}