{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z44YQVWMTPR4T5B7LVMJV7L2A4","short_pith_number":"pith:Z44YQVWM","schema_version":"1.0","canonical_sha256":"cf398856cc9be3c9f43f5d589afd7a071f665e3ac3a34c0b48403c3a4cb468fc","source":{"kind":"arxiv","id":"2607.19854","version":1},"attestation_state":"computed","paper":{"title":"Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Maryam Fazel, Runlong Zhou, Simon S. Du, Zihan Zhang","submitted_at":"2026-07-22T07:42:19Z","abstract_excerpt":"We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.\n  We propose a new algorithm and prove a regret upper bound \\[\\tilde O(\\sqrt{SAK}+S^8A^3)\\] with failure probability $\\delta$, where $K$ is the number of episodes and $\\tilde O(\\cdot)$ hides $\\mathsf{poly}\\log(S,A,K,1/\\delta)$.\n  Thus, the regret is $H$-free and asymptotically optimal, matching the contextual-bandit lower bound $\\Omega(\\sqrt{SAK})$ up to logarithmic factors. This completely rem"},"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":"2607.19854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T07:42:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9240af97622163e9f6368136aee63c16ac45d63038fc9def3f281023af826c02","abstract_canon_sha256":"cf2d1fb02421060f9b90a75677cb9b841c532a4fce483da2f6c56217df4d9e1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:24:03.766672Z","signature_b64":"EPcLy4zDCoSfPfjdynNtBupmRXQHqsk+QwhY7+ya+BsFQPf9VOLkRMc9W8Q64aoa/Hh3UOsIcPla1LC5NBm+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf398856cc9be3c9f43f5d589afd7a071f665e3ac3a34c0b48403c3a4cb468fc","last_reissued_at":"2026-07-23T01:24:03.765830Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:24:03.765830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Maryam Fazel, Runlong Zhou, Simon S. Du, Zihan Zhang","submitted_at":"2026-07-22T07:42:19Z","abstract_excerpt":"We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.\n  We propose a new algorithm and prove a regret upper bound \\[\\tilde O(\\sqrt{SAK}+S^8A^3)\\] with failure probability $\\delta$, where $K$ is the number of episodes and $\\tilde O(\\cdot)$ hides $\\mathsf{poly}\\log(S,A,K,1/\\delta)$.\n  Thus, the regret is $H$-free and asymptotically optimal, matching the contextual-bandit lower bound $\\Omega(\\sqrt{SAK})$ up to logarithmic factors. This completely rem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19854","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/2607.19854/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":"2607.19854","created_at":"2026-07-23T01:24:03.766259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19854v1","created_at":"2026-07-23T01:24:03.766259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19854","created_at":"2026-07-23T01:24:03.766259+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z44YQVWMTPR4","created_at":"2026-07-23T01:24:03.766259+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z44YQVWMTPR4T5B7","created_at":"2026-07-23T01:24:03.766259+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z44YQVWM","created_at":"2026-07-23T01:24:03.766259+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/Z44YQVWMTPR4T5B7LVMJV7L2A4","json":"https://pith.science/pith/Z44YQVWMTPR4T5B7LVMJV7L2A4.json","graph_json":"https://pith.science/api/pith-number/Z44YQVWMTPR4T5B7LVMJV7L2A4/graph.json","events_json":"https://pith.science/api/pith-number/Z44YQVWMTPR4T5B7LVMJV7L2A4/events.json","paper":"https://pith.science/paper/Z44YQVWM"},"agent_actions":{"view_html":"https://pith.science/pith/Z44YQVWMTPR4T5B7LVMJV7L2A4","download_json":"https://pith.science/pith/Z44YQVWMTPR4T5B7LVMJV7L2A4.json","view_paper":"https://pith.science/paper/Z44YQVWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19854&json=true","fetch_graph":"https://pith.science/api/pith-number/Z44YQVWMTPR4T5B7LVMJV7L2A4/graph.json","fetch_events":"https://pith.science/api/pith-number/Z44YQVWMTPR4T5B7LVMJV7L2A4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z44YQVWMTPR4T5B7LVMJV7L2A4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z44YQVWMTPR4T5B7LVMJV7L2A4/action/storage_attestation","attest_author":"https://pith.science/pith/Z44YQVWMTPR4T5B7LVMJV7L2A4/action/author_attestation","sign_citation":"https://pith.science/pith/Z44YQVWMTPR4T5B7LVMJV7L2A4/action/citation_signature","submit_replication":"https://pith.science/pith/Z44YQVWMTPR4T5B7LVMJV7L2A4/action/replication_record"}},"created_at":"2026-07-23T01:24:03.766259+00:00","updated_at":"2026-07-23T01:24:03.766259+00:00"}