{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UKREFO7UWMNZGYG5GNW5R4KCCA","short_pith_number":"pith:UKREFO7U","schema_version":"1.0","canonical_sha256":"a2a242bbf4b31b9360dd336dd8f142103e6606630b10c62faa86c4635b5775f5","source":{"kind":"arxiv","id":"2106.03780","version":1},"attestation_state":"computed","paper":{"title":"Learning Stochastic Optimal Policies via Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Atsushi Yamashita, Hajime Asama, Jinkyoo Park, Michael Poli, Stefano Massaroli, Stefano Peluchetti","submitted_at":"2021-06-07T16:43:07Z","abstract_excerpt":"We systematically develop a learning-based treatment of stochastic optimal control (SOC), relying on direct optimization of parametric control policies. We propose a derivation of adjoint sensitivity results for stochastic differential equations through direct application of variational calculus. Then, given an objective function for a predetermined task specifying the desiderata for the controller, we optimize their parameters via iterative gradient descent methods. In doing so, we extend the range of applicability of classical SOC techniques, often requiring strict assumptions on the functio"},"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":"2106.03780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T16:43:07Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"c3825229799bbdeabe6ace9354393bc49f1b9dbfa3028fc9ca556827866eda57","abstract_canon_sha256":"50b839f364f6fc494904668f521b6b262c172643f823f8364be453e577b6b0cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:55.349397Z","signature_b64":"l+9A0iwqnU+SC0D5tT+gQapWZza4gwblCJLirhet/paa0LvsPCmvjclfzQh54PkLDqJy+kaKXCgklgMPxKQ4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2a242bbf4b31b9360dd336dd8f142103e6606630b10c62faa86c4635b5775f5","last_reissued_at":"2026-07-05T02:46:55.348699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:55.348699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Stochastic Optimal Policies via Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Atsushi Yamashita, Hajime Asama, Jinkyoo Park, Michael Poli, Stefano Massaroli, Stefano Peluchetti","submitted_at":"2021-06-07T16:43:07Z","abstract_excerpt":"We systematically develop a learning-based treatment of stochastic optimal control (SOC), relying on direct optimization of parametric control policies. We propose a derivation of adjoint sensitivity results for stochastic differential equations through direct application of variational calculus. Then, given an objective function for a predetermined task specifying the desiderata for the controller, we optimize their parameters via iterative gradient descent methods. In doing so, we extend the range of applicability of classical SOC techniques, often requiring strict assumptions on the functio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03780","kind":"arxiv","version":1},"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/2106.03780/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":"2106.03780","created_at":"2026-07-05T02:46:55.348771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03780v1","created_at":"2026-07-05T02:46:55.348771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03780","created_at":"2026-07-05T02:46:55.348771+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKREFO7UWMNZ","created_at":"2026-07-05T02:46:55.348771+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKREFO7UWMNZGYG5","created_at":"2026-07-05T02:46:55.348771+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKREFO7U","created_at":"2026-07-05T02:46:55.348771+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/UKREFO7UWMNZGYG5GNW5R4KCCA","json":"https://pith.science/pith/UKREFO7UWMNZGYG5GNW5R4KCCA.json","graph_json":"https://pith.science/api/pith-number/UKREFO7UWMNZGYG5GNW5R4KCCA/graph.json","events_json":"https://pith.science/api/pith-number/UKREFO7UWMNZGYG5GNW5R4KCCA/events.json","paper":"https://pith.science/paper/UKREFO7U"},"agent_actions":{"view_html":"https://pith.science/pith/UKREFO7UWMNZGYG5GNW5R4KCCA","download_json":"https://pith.science/pith/UKREFO7UWMNZGYG5GNW5R4KCCA.json","view_paper":"https://pith.science/paper/UKREFO7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03780&json=true","fetch_graph":"https://pith.science/api/pith-number/UKREFO7UWMNZGYG5GNW5R4KCCA/graph.json","fetch_events":"https://pith.science/api/pith-number/UKREFO7UWMNZGYG5GNW5R4KCCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKREFO7UWMNZGYG5GNW5R4KCCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKREFO7UWMNZGYG5GNW5R4KCCA/action/storage_attestation","attest_author":"https://pith.science/pith/UKREFO7UWMNZGYG5GNW5R4KCCA/action/author_attestation","sign_citation":"https://pith.science/pith/UKREFO7UWMNZGYG5GNW5R4KCCA/action/citation_signature","submit_replication":"https://pith.science/pith/UKREFO7UWMNZGYG5GNW5R4KCCA/action/replication_record"}},"created_at":"2026-07-05T02:46:55.348771+00:00","updated_at":"2026-07-05T02:46:55.348771+00:00"}