{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ITCUANK4RBU6XBVKMEUQFT3EZV","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":"657e7d7aea8e8a96bf99e45a552bac7dd343a92c266ddea3fcca6b1e3ea1c739","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-05-16T14:13:06Z","title_canon_sha256":"90f1faa9e014936cf1c09c904883d866145db4b601352e198b0d0703569ff8f8"},"schema_version":"1.0","source":{"id":"2205.07704","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.07704","created_at":"2026-07-05T04:33:53Z"},{"alias_kind":"arxiv_version","alias_value":"2205.07704v2","created_at":"2026-07-05T04:33:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07704","created_at":"2026-07-05T04:33:53Z"},{"alias_kind":"pith_short_12","alias_value":"ITCUANK4RBU6","created_at":"2026-07-05T04:33:53Z"},{"alias_kind":"pith_short_16","alias_value":"ITCUANK4RBU6XBVK","created_at":"2026-07-05T04:33:53Z"},{"alias_kind":"pith_short_8","alias_value":"ITCUANK4","created_at":"2026-07-05T04:33:53Z"}],"graph_snapshots":[{"event_id":"sha256:4fb6342888381ccf48d17785280d1c34ca973fb20d02f42e2d091c35844cff5e","target":"graph","created_at":"2026-07-05T04:33:53Z","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/2205.07704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose the Bayes-UCBVI algorithm for reinforcement learning in tabular, stage-dependent, episodic Markov decision process: a natural extension of the Bayes-UCB algorithm by Kaufmann et al. (2012) for multi-armed bandits. Our method uses the quantile of a Q-value function posterior as upper confidence bound on the optimal Q-value function. For Bayes-UCBVI, we prove a regret bound of order $\\widetilde{O}(\\sqrt{H^3SAT})$ where $H$ is the length of one episode, $S$ is the number of states, $A$ the number of actions, $T$ the number of episodes, that matches the lower-bound of $\\Omega(\\sqrt{H^3S","authors_text":"Alexey Naumov, Daniil Tiapkin, Denis Belomestny, Eric Moulines, Michal Valko, Pierre Menard, Sergey Samsonov, Yunhao Tang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-05-16T14:13:06Z","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07704","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:de74df69b4abdaf5aad4f360d1d54fea7cf6ff870a91ce7caa1c5cad719b02d9","target":"record","created_at":"2026-07-05T04:33:53Z","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":"657e7d7aea8e8a96bf99e45a552bac7dd343a92c266ddea3fcca6b1e3ea1c739","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-05-16T14:13:06Z","title_canon_sha256":"90f1faa9e014936cf1c09c904883d866145db4b601352e198b0d0703569ff8f8"},"schema_version":"1.0","source":{"id":"2205.07704","kind":"arxiv","version":2}},"canonical_sha256":"44c540355c8869eb86aa612902cf64cd629c7cc521c2aec8365152760f370bcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44c540355c8869eb86aa612902cf64cd629c7cc521c2aec8365152760f370bcc","first_computed_at":"2026-07-05T04:33:53.163394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:53.163394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IVpk3B5M9mTY170KrqHihY/s+4vDpSoWaDQlv524frv0kpfRsqqmgR/NTlwRvfb4T4qXMBVcavI35TSTE1y2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:53.163796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.07704","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de74df69b4abdaf5aad4f360d1d54fea7cf6ff870a91ce7caa1c5cad719b02d9","sha256:4fb6342888381ccf48d17785280d1c34ca973fb20d02f42e2d091c35844cff5e"],"state_sha256":"7046ee859150ca9dedc5648a70c7e8d251b78a6c5b1ce1cc70ce420e62b89382"}