{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MM3A6FHELIMWCBUOSTHWIIGUJC","short_pith_number":"pith:MM3A6FHE","schema_version":"1.0","canonical_sha256":"63360f14e45a1961068e94cf6420d448a8f4837122eaaa526611a268f06dc93e","source":{"kind":"arxiv","id":"1905.12425","version":2},"attestation_state":"computed","paper":{"title":"Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aristide Tossou, Christos Dimitrakakis, Debabrota Basu","submitted_at":"2019-05-27T20:15:54Z","abstract_excerpt":"We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves the optimal regret $\\tilde{\\mathcal{O}}(\\sqrt{DSAT})$ up to logarithmic factors, and so our work closes a gap with the lower bound without additional assumptions on the MDP. We perform experiments in a variety of environments that validates the theoretical bounds as well as prove UCRL-V to be better than the state-of-the-art algorithms."},"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":"1905.12425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T20:15:54Z","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"title_canon_sha256":"80b2385c7ce7d1c6b5d63551783968f24e159e4a2d3ee9350120270cbe37d3d3","abstract_canon_sha256":"3eb81f6df6f05f2207cd4eb05724a5733413d6887f03766962f37acceb4ca401"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:26.855667Z","signature_b64":"xyShLIPNXGq5xHMq0sX09BgEn3yLsBOcVxAdPJn9ubU7wVuRVWXGMjS1G5OMtJzZtYquYP8YK10d0OBsDpa/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63360f14e45a1961068e94cf6420d448a8f4837122eaaa526611a268f06dc93e","last_reissued_at":"2026-07-05T00:25:26.855153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:26.855153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aristide Tossou, Christos Dimitrakakis, Debabrota Basu","submitted_at":"2019-05-27T20:15:54Z","abstract_excerpt":"We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves the optimal regret $\\tilde{\\mathcal{O}}(\\sqrt{DSAT})$ up to logarithmic factors, and so our work closes a gap with the lower bound without additional assumptions on the MDP. We perform experiments in a variety of environments that validates the theoretical bounds as well as prove UCRL-V to be better than the state-of-the-art algorithms."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12425","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/1905.12425/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":"1905.12425","created_at":"2026-07-05T00:25:26.855213+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12425v2","created_at":"2026-07-05T00:25:26.855213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12425","created_at":"2026-07-05T00:25:26.855213+00:00"},{"alias_kind":"pith_short_12","alias_value":"MM3A6FHELIMW","created_at":"2026-07-05T00:25:26.855213+00:00"},{"alias_kind":"pith_short_16","alias_value":"MM3A6FHELIMWCBUO","created_at":"2026-07-05T00:25:26.855213+00:00"},{"alias_kind":"pith_short_8","alias_value":"MM3A6FHE","created_at":"2026-07-05T00:25:26.855213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1906.09114","citing_title":"Near-optimal Bayesian Solution For Unknown Discrete Markov Decision Process","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC","json":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC.json","graph_json":"https://pith.science/api/pith-number/MM3A6FHELIMWCBUOSTHWIIGUJC/graph.json","events_json":"https://pith.science/api/pith-number/MM3A6FHELIMWCBUOSTHWIIGUJC/events.json","paper":"https://pith.science/paper/MM3A6FHE"},"agent_actions":{"view_html":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC","download_json":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC.json","view_paper":"https://pith.science/paper/MM3A6FHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12425&json=true","fetch_graph":"https://pith.science/api/pith-number/MM3A6FHELIMWCBUOSTHWIIGUJC/graph.json","fetch_events":"https://pith.science/api/pith-number/MM3A6FHELIMWCBUOSTHWIIGUJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/action/storage_attestation","attest_author":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/action/author_attestation","sign_citation":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/action/citation_signature","submit_replication":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/action/replication_record"}},"created_at":"2026-07-05T00:25:26.855213+00:00","updated_at":"2026-07-05T00:25:26.855213+00:00"}