{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KZBI7AVBFOTO57SUKBGTKTIGWJ","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":"9850b53716730284acd341ea366a7b6bf415f046ef2798fbfd807798b8d428c2","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T01:09:06Z","title_canon_sha256":"25c8a22426d26094619aeff0290f05ada416496d6fe12498599b4f67decb6f6d"},"schema_version":"1.0","source":{"id":"2507.00358","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00358","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00358v2","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00358","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"pith_short_12","alias_value":"KZBI7AVBFOTO","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"pith_short_16","alias_value":"KZBI7AVBFOTO57SU","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"pith_short_8","alias_value":"KZBI7AVB","created_at":"2026-07-05T11:41:43Z"}],"graph_snapshots":[{"event_id":"sha256:84493a06773f2937709f1f263ddaf4856f550b6e4d674fafe0e8df71e451144d","target":"graph","created_at":"2026-07-05T11:41:43Z","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/2507.00358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reinforcement learning (RL) for the same class of continuous-time stochastic linear--quadratic (LQ) control problems as in \\cite{huang2024sublinear}, where volatilities depend on both states and controls while states are scalar-valued and running control rewards are absent. We propose a model-free, data-driven exploration mechanism that adaptively adjusts entropy regularization by the critic and policy variance by the actor. Unlike the constant or deterministic exploration schedules employed in \\cite{huang2024sublinear}, which require extensive tuning for implementations and ignore le","authors_text":"Xun Yu Zhou, Yilie Huang","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T01:09:06Z","title":"Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00358","kind":"arxiv","version":2},"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:d8797eca88399a6e671830047a2183573aa74387dcd002a92823fd567951df15","target":"record","created_at":"2026-07-05T11:41:43Z","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":"9850b53716730284acd341ea366a7b6bf415f046ef2798fbfd807798b8d428c2","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T01:09:06Z","title_canon_sha256":"25c8a22426d26094619aeff0290f05ada416496d6fe12498599b4f67decb6f6d"},"schema_version":"1.0","source":{"id":"2507.00358","kind":"arxiv","version":2}},"canonical_sha256":"56428f82a12ba6eefe54504d354d06b2669c24a8deb0f07d0c3a46ac9fbf5c8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56428f82a12ba6eefe54504d354d06b2669c24a8deb0f07d0c3a46ac9fbf5c8c","first_computed_at":"2026-07-05T11:41:43.625688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:43.625688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iYKFPeIkX6+vCnLYyASrEcA3M6JwiajHXwdaD8FlmmsyJSV+CFCXcH3b0tBTGO8gYWq/mhUH9PSuOhExyKpACg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:43.626335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00358","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8797eca88399a6e671830047a2183573aa74387dcd002a92823fd567951df15","sha256:84493a06773f2937709f1f263ddaf4856f550b6e4d674fafe0e8df71e451144d"],"state_sha256":"53b09974bf7582ef5602ef292c4aa8e4b3da68ddcf7391d435c2cfed62fffe88"}