{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MM3A6FHELIMWCBUOSTHWIIGUJC","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":"3eb81f6df6f05f2207cd4eb05724a5733413d6887f03766962f37acceb4ca401","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T20:15:54Z","title_canon_sha256":"80b2385c7ce7d1c6b5d63551783968f24e159e4a2d3ee9350120270cbe37d3d3"},"schema_version":"1.0","source":{"id":"1905.12425","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12425","created_at":"2026-07-05T00:25:26Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12425v2","created_at":"2026-07-05T00:25:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12425","created_at":"2026-07-05T00:25:26Z"},{"alias_kind":"pith_short_12","alias_value":"MM3A6FHELIMW","created_at":"2026-07-05T00:25:26Z"},{"alias_kind":"pith_short_16","alias_value":"MM3A6FHELIMWCBUO","created_at":"2026-07-05T00:25:26Z"},{"alias_kind":"pith_short_8","alias_value":"MM3A6FHE","created_at":"2026-07-05T00:25:26Z"}],"graph_snapshots":[{"event_id":"sha256:2f826cd74c1a8267c5a9643d0905dfbfa2248f300f4999396c382727d7d94b10","target":"graph","created_at":"2026-07-05T00:25:26Z","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/1905.12425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Aristide Tossou, Christos Dimitrakakis, Debabrota Basu","cross_cats":["cs.AI","cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T20:15:54Z","title":"Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12425","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:d4a6103372406ee041a937b7357eebfee94f5a86e6ef12cf0650e631575326db","target":"record","created_at":"2026-07-05T00:25:26Z","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":"3eb81f6df6f05f2207cd4eb05724a5733413d6887f03766962f37acceb4ca401","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T20:15:54Z","title_canon_sha256":"80b2385c7ce7d1c6b5d63551783968f24e159e4a2d3ee9350120270cbe37d3d3"},"schema_version":"1.0","source":{"id":"1905.12425","kind":"arxiv","version":2}},"canonical_sha256":"63360f14e45a1961068e94cf6420d448a8f4837122eaaa526611a268f06dc93e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63360f14e45a1961068e94cf6420d448a8f4837122eaaa526611a268f06dc93e","first_computed_at":"2026-07-05T00:25:26.855153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:25:26.855153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xyShLIPNXGq5xHMq0sX09BgEn3yLsBOcVxAdPJn9ubU7wVuRVWXGMjS1G5OMtJzZtYquYP8YK10d0OBsDpa/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:25:26.855667Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12425","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4a6103372406ee041a937b7357eebfee94f5a86e6ef12cf0650e631575326db","sha256:2f826cd74c1a8267c5a9643d0905dfbfa2248f300f4999396c382727d7d94b10"],"state_sha256":"474b590c0d6567983a1dbe1c3aec6e532b0958e36332ef7e3f0d7d7a6d3f334e"}