{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MM3A6FHELIMWCBUOSTHWIIGUJC","short_pith_number":"pith:MM3A6FHE","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"},"canonical_sha256":"63360f14e45a1961068e94cf6420d448a8f4837122eaaa526611a268f06dc93e","source":{"kind":"arxiv","id":"1905.12425","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MM3A6FHELIMWCBUOSTHWIIGUJC","target":"record","payload":{"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"},"canonical_sha256":"63360f14e45a1961068e94cf6420d448a8f4837122eaaa526611a268f06dc93e","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"},"source_kind":"arxiv","source_id":"1905.12425","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:25:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2I/wbyYGIBaugmZWf4hl3ygkMAat7T+Bxm0RvrUk5YeD1r3au8e5BCQa2No3v1j/bk08cscegWstRXP+/vu/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:52:17.289788Z"},"content_sha256":"d4a6103372406ee041a937b7357eebfee94f5a86e6ef12cf0650e631575326db","schema_version":"1.0","event_id":"sha256:d4a6103372406ee041a937b7357eebfee94f5a86e6ef12cf0650e631575326db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MM3A6FHELIMWCBUOSTHWIIGUJC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:25:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/vM4JbZ7qUvWB8RAyMBWZIsEgs3DBQS8L1lo/vj9YBYhPwq0WyCClKVmjBdl4fC0f6R+qFrd2oY+bayoUB1NDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:52:17.290450Z"},"content_sha256":"2f826cd74c1a8267c5a9643d0905dfbfa2248f300f4999396c382727d7d94b10","schema_version":"1.0","event_id":"sha256:2f826cd74c1a8267c5a9643d0905dfbfa2248f300f4999396c382727d7d94b10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/bundle.json","state_url":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T14:52:17Z","links":{"resolver":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC","bundle":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/bundle.json","state":"https://pith.science/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MM3A6FHELIMWCBUOSTHWIIGUJC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bv4zQCj2tlrvH+zUAuVrGivGxzIF+jY8xBC18ojfeMEQ7LM9aWCr25jftEK7SUba1LzinhRJUew2Y5viM27vBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:52:17.297341Z","bundle_sha256":"6eb5c21d54bf5256dd85d1984242d6c2113af8299db4d0a60f0e49c1c799740e"}}