{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:BKDYTHAO4ORIAXH7IJKD26GVGW","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":"4696ab5ef839beed3be386aca836fa80164a04dadd921e9333f4723281c948f9","cross_cats_sorted":["cs.LG","cs.SY","math.OC","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2011-02-12T10:03:21Z","title_canon_sha256":"809cfa211461f01705559159b68f697b6e56578e350edf217527d7f1c6739664"},"schema_version":"1.0","source":{"id":"1102.2490","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1102.2490","created_at":"2026-05-18T03:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"1102.2490v5","created_at":"2026-05-18T03:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1102.2490","created_at":"2026-05-18T03:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"BKDYTHAO4ORI","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"BKDYTHAO4ORIAXH7","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"BKDYTHAO","created_at":"2026-05-18T12:26:24Z"}],"graph_snapshots":[{"event_id":"sha256:de4047590365c2ebec28edd076443acd87df53c323e618ed943b4226bba09b0b","target":"graph","created_at":"2026-05-18T03:14:41Z","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"},"paper":{"abstract_excerpt":"This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free index policy for stochastic bandit problems. We prove two distinct results: first, for arbitrary bounded rewards, the KL-UCB algorithm satisfies a uniformly better regret bound than UCB or UCB2; second, in the special case of Bernoulli rewards, it reaches the lower bound of Lai and Robbins. Furthermore, we show that simple adaptations of the KL-UCB algorithm are also optimal for specific classes of (possibly unbounded) rewards, including those generated from exponential families of distributions. A larg","authors_text":"Aur\\'elien Garivier, Olivier Capp\\'e","cross_cats":["cs.LG","cs.SY","math.OC","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2011-02-12T10:03:21Z","title":"The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1102.2490","kind":"arxiv","version":5},"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":"sha256:800e8f7cffaff9a7c1c71d50f6c63053676cabc383bb007ab361561d9c05c7fc","target":"record","created_at":"2026-05-18T03:14:41Z","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":"4696ab5ef839beed3be386aca836fa80164a04dadd921e9333f4723281c948f9","cross_cats_sorted":["cs.LG","cs.SY","math.OC","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2011-02-12T10:03:21Z","title_canon_sha256":"809cfa211461f01705559159b68f697b6e56578e350edf217527d7f1c6739664"},"schema_version":"1.0","source":{"id":"1102.2490","kind":"arxiv","version":5}},"canonical_sha256":"0a87899c0ee3a2805cff42543d78d5358b4aa8a87d24e2a5baaf7eb8989e007c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a87899c0ee3a2805cff42543d78d5358b4aa8a87d24e2a5baaf7eb8989e007c","first_computed_at":"2026-05-18T03:14:41.232336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:14:41.232336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zBzgnCKmvh2+sZDbCerYEwsJbCiBn1CCTZDj8mrMN3NRVLYYsh4kWvV7BbU3oknzSSIEyTCnJKOP3qgF40VfDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:14:41.233065Z","signed_message":"canonical_sha256_bytes"},"source_id":"1102.2490","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:800e8f7cffaff9a7c1c71d50f6c63053676cabc383bb007ab361561d9c05c7fc","sha256:de4047590365c2ebec28edd076443acd87df53c323e618ed943b4226bba09b0b"],"state_sha256":"5c380fb0dfc80386d0a59d5f07ab9db5c0d4d4d3d6835276033e7636c364865f"}