{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JWKTAAMM44P3DVZQIGM4523WZL","short_pith_number":"pith:JWKTAAMM","schema_version":"1.0","canonical_sha256":"4d9530018ce71fb1d7304199ceeb76cae621c33d9e035bf5e11115468a4c62bd","source":{"kind":"arxiv","id":"2602.01903","version":2},"attestation_state":"computed","paper":{"title":"Data- and Variance-dependent Regret Bounds for Online Tabular MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kenji Yamanishi, Mingyi Li, Taira Tsuchiya","submitted_at":"2026-02-02T10:09:29Z","abstract_excerpt":"This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent regret bounds in the stochastic regime. We quantify MDP complexity using a first-order quantity and several new data-dependent measures for the adversarial regime, including a second-order quantity and a path-length measure, as well as variance-based measures for the stochastic regime. To adapt to these measures, we develop algorithms based on global optimi"},"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":"2602.01903","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T10:09:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bc908ab3554c74d7df3a2c817052193312cc2ff09c763e05f7dc58f3a982de6a","abstract_canon_sha256":"0244715691c2b8b3bcb67a522f865499e0f8e10e86808de6336226a981c989b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:09.957025Z","signature_b64":"F48Ees4tNzw1duKw47Ln7kL9MZKayNH7TPKo1qwZ+Yb5rpz1hHOpcBVdvqMv3d+YCsbOFlEv2e5a75Nm/ujZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d9530018ce71fb1d7304199ceeb76cae621c33d9e035bf5e11115468a4c62bd","last_reissued_at":"2026-06-03T01:05:09.956547Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:09.956547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data- and Variance-dependent Regret Bounds for Online Tabular MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kenji Yamanishi, Mingyi Li, Taira Tsuchiya","submitted_at":"2026-02-02T10:09:29Z","abstract_excerpt":"This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent regret bounds in the stochastic regime. We quantify MDP complexity using a first-order quantity and several new data-dependent measures for the adversarial regime, including a second-order quantity and a path-length measure, as well as variance-based measures for the stochastic regime. To adapt to these measures, we develop algorithms based on global optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01903","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/2602.01903/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":"2602.01903","created_at":"2026-06-03T01:05:09.956608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.01903v2","created_at":"2026-06-03T01:05:09.956608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01903","created_at":"2026-06-03T01:05:09.956608+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWKTAAMM44P3","created_at":"2026-06-03T01:05:09.956608+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWKTAAMM44P3DVZQ","created_at":"2026-06-03T01:05:09.956608+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWKTAAMM","created_at":"2026-06-03T01:05:09.956608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWKTAAMM44P3DVZQIGM4523WZL","json":"https://pith.science/pith/JWKTAAMM44P3DVZQIGM4523WZL.json","graph_json":"https://pith.science/api/pith-number/JWKTAAMM44P3DVZQIGM4523WZL/graph.json","events_json":"https://pith.science/api/pith-number/JWKTAAMM44P3DVZQIGM4523WZL/events.json","paper":"https://pith.science/paper/JWKTAAMM"},"agent_actions":{"view_html":"https://pith.science/pith/JWKTAAMM44P3DVZQIGM4523WZL","download_json":"https://pith.science/pith/JWKTAAMM44P3DVZQIGM4523WZL.json","view_paper":"https://pith.science/paper/JWKTAAMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.01903&json=true","fetch_graph":"https://pith.science/api/pith-number/JWKTAAMM44P3DVZQIGM4523WZL/graph.json","fetch_events":"https://pith.science/api/pith-number/JWKTAAMM44P3DVZQIGM4523WZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWKTAAMM44P3DVZQIGM4523WZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWKTAAMM44P3DVZQIGM4523WZL/action/storage_attestation","attest_author":"https://pith.science/pith/JWKTAAMM44P3DVZQIGM4523WZL/action/author_attestation","sign_citation":"https://pith.science/pith/JWKTAAMM44P3DVZQIGM4523WZL/action/citation_signature","submit_replication":"https://pith.science/pith/JWKTAAMM44P3DVZQIGM4523WZL/action/replication_record"}},"created_at":"2026-06-03T01:05:09.956608+00:00","updated_at":"2026-06-03T01:05:09.956608+00:00"}