{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EWP23T2S5XTXLEVMVJM335SGDC","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":"b7217c9122148d601bed2ba8e262c83b303a9ed46bb93eef33c048db263bda28","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T11:35:07Z","title_canon_sha256":"0ed0d06292a7183377d3649c4023762accf750b20ca80b5b5667a4072cdb06d5"},"schema_version":"1.0","source":{"id":"2210.00832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.00832","created_at":"2026-07-05T06:56:30Z"},{"alias_kind":"arxiv_version","alias_value":"2210.00832v2","created_at":"2026-07-05T06:56:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00832","created_at":"2026-07-05T06:56:30Z"},{"alias_kind":"pith_short_12","alias_value":"EWP23T2S5XTX","created_at":"2026-07-05T06:56:30Z"},{"alias_kind":"pith_short_16","alias_value":"EWP23T2S5XTXLEVM","created_at":"2026-07-05T06:56:30Z"},{"alias_kind":"pith_short_8","alias_value":"EWP23T2S","created_at":"2026-07-05T06:56:30Z"}],"graph_snapshots":[{"event_id":"sha256:6b313524ba1257ce7fc221bcfa41c9bb73f331cf75ef77f2cd1bd5c441c68516","target":"graph","created_at":"2026-07-05T06:56:30Z","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/2210.00832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reinforcement learning for continuous-time Markov decision processes (MDPs) in the finite-horizon episodic setting. In contrast to discrete-time MDPs, the inter-transition times of a continuous-time MDP are exponentially distributed with rate parameters depending on the state--action pair at each transition. We present a learning algorithm based on the methods of value iteration and upper confidence bound. We derive an upper bound on the worst-case expected regret for the proposed algorithm, and establish a worst-case lower bound, both bounds are of the order of square-root on the num","authors_text":"Xuefeng Gao, Xun Yu Zhou","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T11:35:07Z","title":"Square-root regret bounds for continuous-time episodic Markov decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00832","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":"sha256:3266298a45ef2ad062531d24e516976b3f6121df133401e18310f827099b8637","target":"record","created_at":"2026-07-05T06:56:30Z","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":"b7217c9122148d601bed2ba8e262c83b303a9ed46bb93eef33c048db263bda28","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T11:35:07Z","title_canon_sha256":"0ed0d06292a7183377d3649c4023762accf750b20ca80b5b5667a4072cdb06d5"},"schema_version":"1.0","source":{"id":"2210.00832","kind":"arxiv","version":2}},"canonical_sha256":"259fadcf52ede77592acaa59bdf64618932aa125f1b3a0ff9cb679ee836e8ec7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"259fadcf52ede77592acaa59bdf64618932aa125f1b3a0ff9cb679ee836e8ec7","first_computed_at":"2026-07-05T06:56:30.026663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:30.026663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IQcctF8zA3QvbR5sAattqQVvtgBYeJDW6uzjpznj3rqdtBO8mgsP7RpcI8AL7ekEq4NagB8CId5hLJNOOkAPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:30.027124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.00832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3266298a45ef2ad062531d24e516976b3f6121df133401e18310f827099b8637","sha256:6b313524ba1257ce7fc221bcfa41c9bb73f331cf75ef77f2cd1bd5c441c68516"],"state_sha256":"4c9e97d8257f066153659984085b31427070a39798ae9bb15e711744a4bf8f2a"}