{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IRPOU4KNJWMJHEA3EHYDGVRMMQ","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":"e9c8587cd9a32058278ebec9ec17b21571ad282abbc035470459ca47d9c416c8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-10T03:19:46Z","title_canon_sha256":"3bb2b118e2d8b34c0b76fe31707991436c1e12ece974f55aa1ca3222f613a1db"},"schema_version":"1.0","source":{"id":"2410.07574","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07574","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07574v2","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07574","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"pith_short_12","alias_value":"IRPOU4KNJWMJ","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"pith_short_16","alias_value":"IRPOU4KNJWMJHEA3","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"pith_short_8","alias_value":"IRPOU4KN","created_at":"2026-07-05T10:27:17Z"}],"graph_snapshots":[{"event_id":"sha256:962351f28eee1347668995a4da3f8a889ad6bb9f0537021ee483cbee648c0dc5","target":"graph","created_at":"2026-07-05T10:27:17Z","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/2410.07574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the gap-dependent bounds of two important algorithms for on-policy Q-learning for finite-horizon episodic tabular Markov Decision Processes (MDPs): UCB-Advantage (Zhang et al. 2020) and Q-EarlySettled-Advantage (Li et al. 2021). UCB-Advantage and Q-EarlySettled-Advantage improve upon the results based on Hoeffding-type bonuses and achieve the almost optimal $\\sqrt{T}$-type regret bound in the worst-case scenario, where $T$ is the total number of steps. However, the benign structures of the MDPs such as a strictly positive suboptimality gap can significantly improve the regret. While g","authors_text":"Haochen Zhang, Lingzhou Xue, Zhong Zheng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-10T03:19:46Z","title":"Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07574","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:fbad0e0e1d94449d6a03111e5021b84789869aa3c992793fa92ac20ec0793e9b","target":"record","created_at":"2026-07-05T10:27:17Z","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":"e9c8587cd9a32058278ebec9ec17b21571ad282abbc035470459ca47d9c416c8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-10T03:19:46Z","title_canon_sha256":"3bb2b118e2d8b34c0b76fe31707991436c1e12ece974f55aa1ca3222f613a1db"},"schema_version":"1.0","source":{"id":"2410.07574","kind":"arxiv","version":2}},"canonical_sha256":"445eea714d4d9893901b21f033562c641c9a82627b2d683e3c1f45125a2ad420","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"445eea714d4d9893901b21f033562c641c9a82627b2d683e3c1f45125a2ad420","first_computed_at":"2026-07-05T10:27:17.089518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:17.089518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rNcOlHO5fO6BCavdt89VoMbgpwxnytrAChPzgvvnqTYnV1N5evwE1bWp6cecZppc/5cDB1rVQIjR/1JqD1buDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:17.090545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07574","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbad0e0e1d94449d6a03111e5021b84789869aa3c992793fa92ac20ec0793e9b","sha256:962351f28eee1347668995a4da3f8a889ad6bb9f0537021ee483cbee648c0dc5"],"state_sha256":"be62d6e6412f4c70393cb00d9b4908a4d3eabc3ac7c1e48f477fa1983f06e31a"}