{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NMNULTSFWFJVCTGUNP4PDSZXFL","short_pith_number":"pith:NMNULTSF","schema_version":"1.0","canonical_sha256":"6b1b45ce45b153514cd46bf8f1cb372ad2651c31d29ec89abea833297d2f9b1d","source":{"kind":"arxiv","id":"2505.18379","version":1},"attestation_state":"computed","paper":{"title":"Convergence of Proximal Policy Gradient Method for Problems with Control Dependent Diffusion Coefficients","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ashley Davey, Harry Zheng","submitted_at":"2025-05-23T21:13:13Z","abstract_excerpt":"We prove convergence of the proximal policy gradient method for a class of constrained stochastic control problems with control in both the drift and diffusion of the state process. The problem requires either the running or terminal cost to be strongly convex, but other terms may be non-convex. The inclusion of control-dependent diffusion introduces additional complexity in regularity analysis of the associated backward stochastic differential equation. We provide sufficient conditions under which the control iterates converge linearly to the optimal control, by deriving representations and e"},"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":"2505.18379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-05-23T21:13:13Z","cross_cats_sorted":[],"title_canon_sha256":"3341fb327a7b40ffb1afdea79789f9c274231f0561f34490ed18d7859d29f817","abstract_canon_sha256":"95ba6890d0873f379d6303b712ed165a92843418f1d085707cf5288ee479f76f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:45.535455Z","signature_b64":"B30MHZdkZFaylnan6guYoVZXqKXDbPBQ8SCLXjb8cIOu/486JamXBRUYewT/SeXpKwf79B/vBxuSjvfb2wIqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b1b45ce45b153514cd46bf8f1cb372ad2651c31d29ec89abea833297d2f9b1d","last_reissued_at":"2026-07-05T11:08:45.534952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:45.534952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Proximal Policy Gradient Method for Problems with Control Dependent Diffusion Coefficients","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ashley Davey, Harry Zheng","submitted_at":"2025-05-23T21:13:13Z","abstract_excerpt":"We prove convergence of the proximal policy gradient method for a class of constrained stochastic control problems with control in both the drift and diffusion of the state process. The problem requires either the running or terminal cost to be strongly convex, but other terms may be non-convex. The inclusion of control-dependent diffusion introduces additional complexity in regularity analysis of the associated backward stochastic differential equation. We provide sufficient conditions under which the control iterates converge linearly to the optimal control, by deriving representations and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18379","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/2505.18379/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":"2505.18379","created_at":"2026-07-05T11:08:45.535017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18379v1","created_at":"2026-07-05T11:08:45.535017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18379","created_at":"2026-07-05T11:08:45.535017+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMNULTSFWFJV","created_at":"2026-07-05T11:08:45.535017+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMNULTSFWFJVCTGU","created_at":"2026-07-05T11:08:45.535017+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMNULTSF","created_at":"2026-07-05T11:08:45.535017+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/NMNULTSFWFJVCTGUNP4PDSZXFL","json":"https://pith.science/pith/NMNULTSFWFJVCTGUNP4PDSZXFL.json","graph_json":"https://pith.science/api/pith-number/NMNULTSFWFJVCTGUNP4PDSZXFL/graph.json","events_json":"https://pith.science/api/pith-number/NMNULTSFWFJVCTGUNP4PDSZXFL/events.json","paper":"https://pith.science/paper/NMNULTSF"},"agent_actions":{"view_html":"https://pith.science/pith/NMNULTSFWFJVCTGUNP4PDSZXFL","download_json":"https://pith.science/pith/NMNULTSFWFJVCTGUNP4PDSZXFL.json","view_paper":"https://pith.science/paper/NMNULTSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18379&json=true","fetch_graph":"https://pith.science/api/pith-number/NMNULTSFWFJVCTGUNP4PDSZXFL/graph.json","fetch_events":"https://pith.science/api/pith-number/NMNULTSFWFJVCTGUNP4PDSZXFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMNULTSFWFJVCTGUNP4PDSZXFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMNULTSFWFJVCTGUNP4PDSZXFL/action/storage_attestation","attest_author":"https://pith.science/pith/NMNULTSFWFJVCTGUNP4PDSZXFL/action/author_attestation","sign_citation":"https://pith.science/pith/NMNULTSFWFJVCTGUNP4PDSZXFL/action/citation_signature","submit_replication":"https://pith.science/pith/NMNULTSFWFJVCTGUNP4PDSZXFL/action/replication_record"}},"created_at":"2026-07-05T11:08:45.535017+00:00","updated_at":"2026-07-05T11:08:45.535017+00:00"}