{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ITCUANK4RBU6XBVKMEUQFT3EZV","short_pith_number":"pith:ITCUANK4","schema_version":"1.0","canonical_sha256":"44c540355c8869eb86aa612902cf64cd629c7cc521c2aec8365152760f370bcc","source":{"kind":"arxiv","id":"2205.07704","version":2},"attestation_state":"computed","paper":{"title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexey Naumov, Daniil Tiapkin, Denis Belomestny, Eric Moulines, Michal Valko, Pierre Menard, Sergey Samsonov, Yunhao Tang","submitted_at":"2022-05-16T14:13:06Z","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"},"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":"2205.07704","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-05-16T14:13:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"90f1faa9e014936cf1c09c904883d866145db4b601352e198b0d0703569ff8f8","abstract_canon_sha256":"657e7d7aea8e8a96bf99e45a552bac7dd343a92c266ddea3fcca6b1e3ea1c739"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:53.163796Z","signature_b64":"IVpk3B5M9mTY170KrqHihY/s+4vDpSoWaDQlv524frv0kpfRsqqmgR/NTlwRvfb4T4qXMBVcavI35TSTE1y2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44c540355c8869eb86aa612902cf64cd629c7cc521c2aec8365152760f370bcc","last_reissued_at":"2026-07-05T04:33:53.163394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:53.163394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexey Naumov, Daniil Tiapkin, Denis Belomestny, Eric Moulines, Michal Valko, Pierre Menard, Sergey Samsonov, Yunhao Tang","submitted_at":"2022-05-16T14:13:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07704","kind":"arxiv","version":2},"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/2205.07704/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":"2205.07704","created_at":"2026-07-05T04:33:53.163447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.07704v2","created_at":"2026-07-05T04:33:53.163447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07704","created_at":"2026-07-05T04:33:53.163447+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITCUANK4RBU6","created_at":"2026-07-05T04:33:53.163447+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITCUANK4RBU6XBVK","created_at":"2026-07-05T04:33:53.163447+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITCUANK4","created_at":"2026-07-05T04:33:53.163447+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/ITCUANK4RBU6XBVKMEUQFT3EZV","json":"https://pith.science/pith/ITCUANK4RBU6XBVKMEUQFT3EZV.json","graph_json":"https://pith.science/api/pith-number/ITCUANK4RBU6XBVKMEUQFT3EZV/graph.json","events_json":"https://pith.science/api/pith-number/ITCUANK4RBU6XBVKMEUQFT3EZV/events.json","paper":"https://pith.science/paper/ITCUANK4"},"agent_actions":{"view_html":"https://pith.science/pith/ITCUANK4RBU6XBVKMEUQFT3EZV","download_json":"https://pith.science/pith/ITCUANK4RBU6XBVKMEUQFT3EZV.json","view_paper":"https://pith.science/paper/ITCUANK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.07704&json=true","fetch_graph":"https://pith.science/api/pith-number/ITCUANK4RBU6XBVKMEUQFT3EZV/graph.json","fetch_events":"https://pith.science/api/pith-number/ITCUANK4RBU6XBVKMEUQFT3EZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITCUANK4RBU6XBVKMEUQFT3EZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITCUANK4RBU6XBVKMEUQFT3EZV/action/storage_attestation","attest_author":"https://pith.science/pith/ITCUANK4RBU6XBVKMEUQFT3EZV/action/author_attestation","sign_citation":"https://pith.science/pith/ITCUANK4RBU6XBVKMEUQFT3EZV/action/citation_signature","submit_replication":"https://pith.science/pith/ITCUANK4RBU6XBVKMEUQFT3EZV/action/replication_record"}},"created_at":"2026-07-05T04:33:53.163447+00:00","updated_at":"2026-07-05T04:33:53.163447+00:00"}