{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7WVAH5BRE4OHCJB3WRFIDMRKOE","short_pith_number":"pith:7WVAH5BR","canonical_record":{"source":{"id":"2407.17226","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-24T12:26:21Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"c3a0d7bad43d47372947e3f3444d6bfcbbbe8cc1379e441291ebf3f51de5e71d","abstract_canon_sha256":"b9f6e681adc03f0be00c56518a4c0b3126df13cfc3ab3cb0ffdd10ec01c180af"},"schema_version":"1.0"},"canonical_sha256":"fdaa03f431271c71243bb44a81b22a71226b080132d23e936f0658575341e018","source":{"kind":"arxiv","id":"2407.17226","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17226","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17226v6","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17226","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"7WVAH5BRE4OH","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"7WVAH5BRE4OHCJB3","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"7WVAH5BR","created_at":"2026-07-05T11:42:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7WVAH5BRE4OHCJB3WRFIDMRKOE","target":"record","payload":{"canonical_record":{"source":{"id":"2407.17226","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-24T12:26:21Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"c3a0d7bad43d47372947e3f3444d6bfcbbbe8cc1379e441291ebf3f51de5e71d","abstract_canon_sha256":"b9f6e681adc03f0be00c56518a4c0b3126df13cfc3ab3cb0ffdd10ec01c180af"},"schema_version":"1.0"},"canonical_sha256":"fdaa03f431271c71243bb44a81b22a71226b080132d23e936f0658575341e018","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:22.053459Z","signature_b64":"3JPfXehLsUZtb+fyk/Uff21LS/uIJVkA8LkkzKSdb9eTRKHVqAnxTyfPinUPdcsswClRx7O0U5/CNOBoBK31Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdaa03f431271c71243bb44a81b22a71226b080132d23e936f0658575341e018","last_reissued_at":"2026-07-05T11:42:22.053017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:22.053017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.17226","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6cSALtiEU/YNLbMOQbMjFfWnfYU/DLP+vofYKsPT9KrNTvyoF6Ku8S7oN/TYIkyF8JqcJg2Q3T7nyCF6kIvgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:27:51.895477Z"},"content_sha256":"f7b43fc8fe5245e6248d65814f3859c9243cef6bb3c20697682960470befd490","schema_version":"1.0","event_id":"sha256:f7b43fc8fe5245e6248d65814f3859c9243cef6bb3c20697682960470befd490"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7WVAH5BRE4OHCJB3WRFIDMRKOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Xun Yu Zhou, Yanwei Jia, Yilie Huang","submitted_at":"2024-07-24T12:26:21Z","abstract_excerpt":"We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions, where states are scalar-valued and running control rewards are absent but volatilities of the state processes depend on both state and control variables. We apply a model-free approach that relies neither on knowledge of model parameters nor on their estimations, and devise an RL algorithm to learn the optimal policy parameter directly. Our main contributions include the introduction of an exploration schedule and a regret analysis of the proposed algorithm. We provide the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17226","kind":"arxiv","version":6},"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/2407.17226/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eU4Yq0FNq3Xh+UKcyIy1DbKD6s76SVD4xkodElRhUJ4BNf+4uGo3Qp7UFd3ykd8Jb/IRxIlZIhtCKRji9JL6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:27:51.896010Z"},"content_sha256":"acee068d738901b410215f681eea135ebbc8d8ebf3471ed3b211c12d16f8bb28","schema_version":"1.0","event_id":"sha256:acee068d738901b410215f681eea135ebbc8d8ebf3471ed3b211c12d16f8bb28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WVAH5BRE4OHCJB3WRFIDMRKOE/bundle.json","state_url":"https://pith.science/pith/7WVAH5BRE4OHCJB3WRFIDMRKOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WVAH5BRE4OHCJB3WRFIDMRKOE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T22:27:51Z","links":{"resolver":"https://pith.science/pith/7WVAH5BRE4OHCJB3WRFIDMRKOE","bundle":"https://pith.science/pith/7WVAH5BRE4OHCJB3WRFIDMRKOE/bundle.json","state":"https://pith.science/pith/7WVAH5BRE4OHCJB3WRFIDMRKOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WVAH5BRE4OHCJB3WRFIDMRKOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7WVAH5BRE4OHCJB3WRFIDMRKOE","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":"b9f6e681adc03f0be00c56518a4c0b3126df13cfc3ab3cb0ffdd10ec01c180af","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":"2024-07-24T12:26:21Z","title_canon_sha256":"c3a0d7bad43d47372947e3f3444d6bfcbbbe8cc1379e441291ebf3f51de5e71d"},"schema_version":"1.0","source":{"id":"2407.17226","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17226","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17226v6","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17226","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"7WVAH5BRE4OH","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"7WVAH5BRE4OHCJB3","created_at":"2026-07-05T11:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"7WVAH5BR","created_at":"2026-07-05T11:42:22Z"}],"graph_snapshots":[{"event_id":"sha256:acee068d738901b410215f681eea135ebbc8d8ebf3471ed3b211c12d16f8bb28","target":"graph","created_at":"2026-07-05T11:42:22Z","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/2407.17226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions, where states are scalar-valued and running control rewards are absent but volatilities of the state processes depend on both state and control variables. We apply a model-free approach that relies neither on knowledge of model parameters nor on their estimations, and devise an RL algorithm to learn the optimal policy parameter directly. Our main contributions include the introduction of an exploration schedule and a regret analysis of the proposed algorithm. We provide the","authors_text":"Xun Yu Zhou, Yanwei Jia, 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":"2024-07-24T12:26:21Z","title":"Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17226","kind":"arxiv","version":6},"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:f7b43fc8fe5245e6248d65814f3859c9243cef6bb3c20697682960470befd490","target":"record","created_at":"2026-07-05T11:42:22Z","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":"b9f6e681adc03f0be00c56518a4c0b3126df13cfc3ab3cb0ffdd10ec01c180af","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":"2024-07-24T12:26:21Z","title_canon_sha256":"c3a0d7bad43d47372947e3f3444d6bfcbbbe8cc1379e441291ebf3f51de5e71d"},"schema_version":"1.0","source":{"id":"2407.17226","kind":"arxiv","version":6}},"canonical_sha256":"fdaa03f431271c71243bb44a81b22a71226b080132d23e936f0658575341e018","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdaa03f431271c71243bb44a81b22a71226b080132d23e936f0658575341e018","first_computed_at":"2026-07-05T11:42:22.053017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:22.053017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3JPfXehLsUZtb+fyk/Uff21LS/uIJVkA8LkkzKSdb9eTRKHVqAnxTyfPinUPdcsswClRx7O0U5/CNOBoBK31Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:22.053459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17226","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7b43fc8fe5245e6248d65814f3859c9243cef6bb3c20697682960470befd490","sha256:acee068d738901b410215f681eea135ebbc8d8ebf3471ed3b211c12d16f8bb28"],"state_sha256":"4845e832cb5278460e4b20c12e5a94f677447444e643507cb0b26a717082fe0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mzVe/2xVFLnFdl0JeCYmj3u3gPqGxUhWw1BNlQ3O+47CdVFzUJnRHgDOA+3idwL6GhJ68NhgRLAsuBTUG9KlCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:27:51.900811Z","bundle_sha256":"f64a60e54785781ecee94aa53c83ef6aa43865791489c2fd6a9334283ae9e0f4"}}