{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EWP23T2S5XTXLEVMVJM335SGDC","short_pith_number":"pith:EWP23T2S","schema_version":"1.0","canonical_sha256":"259fadcf52ede77592acaa59bdf64618932aa125f1b3a0ff9cb679ee836e8ec7","source":{"kind":"arxiv","id":"2210.00832","version":2},"attestation_state":"computed","paper":{"title":"Square-root regret bounds for continuous-time episodic Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Xuefeng Gao, Xun Yu Zhou","submitted_at":"2022-10-03T11:35:07Z","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"},"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":"2210.00832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T11:35:07Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"0ed0d06292a7183377d3649c4023762accf750b20ca80b5b5667a4072cdb06d5","abstract_canon_sha256":"b7217c9122148d601bed2ba8e262c83b303a9ed46bb93eef33c048db263bda28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:30.027124Z","signature_b64":"IQcctF8zA3QvbR5sAattqQVvtgBYeJDW6uzjpznj3rqdtBO8mgsP7RpcI8AL7ekEq4NagB8CId5hLJNOOkAPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"259fadcf52ede77592acaa59bdf64618932aa125f1b3a0ff9cb679ee836e8ec7","last_reissued_at":"2026-07-05T06:56:30.026663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:30.026663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Square-root regret bounds for continuous-time episodic Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Xuefeng Gao, Xun Yu Zhou","submitted_at":"2022-10-03T11:35:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00832","kind":"arxiv","version":2},"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/2210.00832/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":"2210.00832","created_at":"2026-07-05T06:56:30.026710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00832v2","created_at":"2026-07-05T06:56:30.026710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00832","created_at":"2026-07-05T06:56:30.026710+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWP23T2S5XTX","created_at":"2026-07-05T06:56:30.026710+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWP23T2S5XTXLEVM","created_at":"2026-07-05T06:56:30.026710+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWP23T2S","created_at":"2026-07-05T06:56:30.026710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.05358","citing_title":"Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWP23T2S5XTXLEVMVJM335SGDC","json":"https://pith.science/pith/EWP23T2S5XTXLEVMVJM335SGDC.json","graph_json":"https://pith.science/api/pith-number/EWP23T2S5XTXLEVMVJM335SGDC/graph.json","events_json":"https://pith.science/api/pith-number/EWP23T2S5XTXLEVMVJM335SGDC/events.json","paper":"https://pith.science/paper/EWP23T2S"},"agent_actions":{"view_html":"https://pith.science/pith/EWP23T2S5XTXLEVMVJM335SGDC","download_json":"https://pith.science/pith/EWP23T2S5XTXLEVMVJM335SGDC.json","view_paper":"https://pith.science/paper/EWP23T2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00832&json=true","fetch_graph":"https://pith.science/api/pith-number/EWP23T2S5XTXLEVMVJM335SGDC/graph.json","fetch_events":"https://pith.science/api/pith-number/EWP23T2S5XTXLEVMVJM335SGDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWP23T2S5XTXLEVMVJM335SGDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWP23T2S5XTXLEVMVJM335SGDC/action/storage_attestation","attest_author":"https://pith.science/pith/EWP23T2S5XTXLEVMVJM335SGDC/action/author_attestation","sign_citation":"https://pith.science/pith/EWP23T2S5XTXLEVMVJM335SGDC/action/citation_signature","submit_replication":"https://pith.science/pith/EWP23T2S5XTXLEVMVJM335SGDC/action/replication_record"}},"created_at":"2026-07-05T06:56:30.026710+00:00","updated_at":"2026-07-05T06:56:30.026710+00:00"}