{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BZMS5VXVMDJ3P4V4P5WBMFCMLB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d3d443372e00c4b74ddece37e1ec0832bc8b18c37911cc79750ce09d61966cf9","cross_cats_sorted":["math.OC","math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T16:28:34Z","title_canon_sha256":"6ddac41a2f6c68638d5da84b6787e022b8a84e547d87399a0c81636a531a66a6"},"schema_version":"1.0","source":{"id":"2411.01302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01302","created_at":"2026-07-05T09:30:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01302v1","created_at":"2026-07-05T09:30:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01302","created_at":"2026-07-05T09:30:28Z"},{"alias_kind":"pith_short_12","alias_value":"BZMS5VXVMDJ3","created_at":"2026-07-05T09:30:28Z"},{"alias_kind":"pith_short_16","alias_value":"BZMS5VXVMDJ3P4V4","created_at":"2026-07-05T09:30:28Z"},{"alias_kind":"pith_short_8","alias_value":"BZMS5VXV","created_at":"2026-07-05T09:30:28Z"}],"graph_snapshots":[{"event_id":"sha256:c642f8f5f1c6ab14668c7390a5e209188e28825b18312c67767df8b102ced8db","target":"graph","created_at":"2026-07-05T09:30:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.01302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the convergence of $q$-learning and related algorithms introduced by Jia and Zhou (J. Mach. Learn. Res., 24 (2023), 161) for controlled diffusion processes. Under suitable conditions on the growth and regularity of the model parameters, we provide a quantitative error and regret analysis of both the exploratory policy improvement algorithm and the $q$-learning algorithm.","authors_text":"Wenpin Tang, Xun Yu Zhou","cross_cats":["math.OC","math.PR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T16:28:34Z","title":"Regret of exploratory policy improvement and $q$-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01302","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a81fe52c1d2d795b5aedeadd366c9bf44351dd55ab459eed225b6426654fa3a6","target":"record","created_at":"2026-07-05T09:30:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d3d443372e00c4b74ddece37e1ec0832bc8b18c37911cc79750ce09d61966cf9","cross_cats_sorted":["math.OC","math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-02T16:28:34Z","title_canon_sha256":"6ddac41a2f6c68638d5da84b6787e022b8a84e547d87399a0c81636a531a66a6"},"schema_version":"1.0","source":{"id":"2411.01302","kind":"arxiv","version":1}},"canonical_sha256":"0e592ed6f560d3b7f2bc7f6c16144c584afef412ca9ae191dd97dfab8d849574","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e592ed6f560d3b7f2bc7f6c16144c584afef412ca9ae191dd97dfab8d849574","first_computed_at":"2026-07-05T09:30:28.170900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:28.170900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U0fXs3ODGHBUxpBp2M6+EKsal5UcYI2rcQamZA6WLSgoiBg4mPmFS+bHXq8SqWYK6foPmTDOBnqSkA3WSWUWDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:28.171379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a81fe52c1d2d795b5aedeadd366c9bf44351dd55ab459eed225b6426654fa3a6","sha256:c642f8f5f1c6ab14668c7390a5e209188e28825b18312c67767df8b102ced8db"],"state_sha256":"8900bfb0f935db0c2dbddd8e54c7f0bffd5ea63261cf944541c963843bdab3fb"}