{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5BAJN34OXHAL4UJ52DHOZRCMVB","short_pith_number":"pith:5BAJN34O","schema_version":"1.0","canonical_sha256":"e84096ef8eb9c0be513dd0ceecc44ca85122eda56bc2ac9e492459e017012cb4","source":{"kind":"arxiv","id":"2606.31769","version":1},"attestation_state":"computed","paper":{"title":"Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions","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":"2026-06-30T14:54:34Z","abstract_excerpt":"We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees together with data-dependent regret bounds. Recent work (Dann et al., 2023; Li et al., 2026) has shown that policy optimization can adapt to both adversarial and stochastic losses with first-order, second-order, and path-length bounds, but only under known transitions, leaving open whether such data-dependent guarantees are achievable by policy optimization when the transition kernel is unknown. We resolve this by developing a new algorit"},"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":"2606.31769","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T14:54:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"48ec17545061f64651808459c4efc143c4b778423bb1214001c7b6cccdfb03f0","abstract_canon_sha256":"3a259e78527fcf5283f40d73467b2dcb795ede01b2b0f529c0294a8023bc68cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:14.238549Z","signature_b64":"9w3PlrR+yoEtczbbmeyt+gCX+HcatVfdShSek6qQsoLUMB2JfzqOd78U0uDXZaV/XOVBq4uTgRW5mo2CIzEcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e84096ef8eb9c0be513dd0ceecc44ca85122eda56bc2ac9e492459e017012cb4","last_reissued_at":"2026-07-01T01:18:14.238041Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:14.238041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions","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":"2026-06-30T14:54:34Z","abstract_excerpt":"We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees together with data-dependent regret bounds. Recent work (Dann et al., 2023; Li et al., 2026) has shown that policy optimization can adapt to both adversarial and stochastic losses with first-order, second-order, and path-length bounds, but only under known transitions, leaving open whether such data-dependent guarantees are achievable by policy optimization when the transition kernel is unknown. We resolve this by developing a new algorit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31769","kind":"arxiv","version":1},"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/2606.31769/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":"2606.31769","created_at":"2026-07-01T01:18:14.238122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31769v1","created_at":"2026-07-01T01:18:14.238122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31769","created_at":"2026-07-01T01:18:14.238122+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BAJN34OXHAL","created_at":"2026-07-01T01:18:14.238122+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BAJN34OXHAL4UJ5","created_at":"2026-07-01T01:18:14.238122+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BAJN34O","created_at":"2026-07-01T01:18:14.238122+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/5BAJN34OXHAL4UJ52DHOZRCMVB","json":"https://pith.science/pith/5BAJN34OXHAL4UJ52DHOZRCMVB.json","graph_json":"https://pith.science/api/pith-number/5BAJN34OXHAL4UJ52DHOZRCMVB/graph.json","events_json":"https://pith.science/api/pith-number/5BAJN34OXHAL4UJ52DHOZRCMVB/events.json","paper":"https://pith.science/paper/5BAJN34O"},"agent_actions":{"view_html":"https://pith.science/pith/5BAJN34OXHAL4UJ52DHOZRCMVB","download_json":"https://pith.science/pith/5BAJN34OXHAL4UJ52DHOZRCMVB.json","view_paper":"https://pith.science/paper/5BAJN34O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31769&json=true","fetch_graph":"https://pith.science/api/pith-number/5BAJN34OXHAL4UJ52DHOZRCMVB/graph.json","fetch_events":"https://pith.science/api/pith-number/5BAJN34OXHAL4UJ52DHOZRCMVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BAJN34OXHAL4UJ52DHOZRCMVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BAJN34OXHAL4UJ52DHOZRCMVB/action/storage_attestation","attest_author":"https://pith.science/pith/5BAJN34OXHAL4UJ52DHOZRCMVB/action/author_attestation","sign_citation":"https://pith.science/pith/5BAJN34OXHAL4UJ52DHOZRCMVB/action/citation_signature","submit_replication":"https://pith.science/pith/5BAJN34OXHAL4UJ52DHOZRCMVB/action/replication_record"}},"created_at":"2026-07-01T01:18:14.238122+00:00","updated_at":"2026-07-01T01:18:14.238122+00:00"}