{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FUI2FKBTFLBKQC2ML2UHPEDL3A","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":"65e5278d91a035b6e120d9103be7ca8cafaa6cdaa2dd624d435726c4d87ba850","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-10T15:52:21Z","title_canon_sha256":"e8a8574cfd00db76186762702b5bb0395eeffd1feac338d3b58a9b827c021e71"},"schema_version":"1.0","source":{"id":"2007.05456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.05456","created_at":"2026-07-05T01:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2007.05456v1","created_at":"2026-07-05T01:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05456","created_at":"2026-07-05T01:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"FUI2FKBTFLBK","created_at":"2026-07-05T01:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"FUI2FKBTFLBKQC2M","created_at":"2026-07-05T01:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"FUI2FKBT","created_at":"2026-07-05T01:17:47Z"}],"graph_snapshots":[{"event_id":"sha256:ce03cd9cc977e17afb6845d04136d97ad1df9117fb064a86ad35713cf2eb1a2a","target":"graph","created_at":"2026-07-05T01:17:47Z","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/2007.05456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of exploration-exploitation in communicating Markov Decision Processes. We provide an analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B). For any MDP with $S$ states, $A$ actions, $\\Gamma \\leq S$ next states and diameter $D$, the regret of UCRL2B is bounded as $\\widetilde{O}(\\sqrt{D\\Gamma S A T})$.","authors_text":"Alessandro Lazaric, Matteo Pirotta, Ronan Fruit","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-10T15:52:21Z","title":"Improved Analysis of UCRL2 with Empirical Bernstein Inequality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05456","kind":"arxiv","version":1},"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:ac0f3ea47cbf11dbf86620c6e073426febe5dd468f78e17733eccdf8c4df0cc1","target":"record","created_at":"2026-07-05T01:17:47Z","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":"65e5278d91a035b6e120d9103be7ca8cafaa6cdaa2dd624d435726c4d87ba850","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-10T15:52:21Z","title_canon_sha256":"e8a8574cfd00db76186762702b5bb0395eeffd1feac338d3b58a9b827c021e71"},"schema_version":"1.0","source":{"id":"2007.05456","kind":"arxiv","version":1}},"canonical_sha256":"2d11a2a8332ac2a80b4c5ea877906bd8130054f052840ceef8118ea3b3c2d5c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d11a2a8332ac2a80b4c5ea877906bd8130054f052840ceef8118ea3b3c2d5c5","first_computed_at":"2026-07-05T01:17:47.009392Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:17:47.009392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yV1DuFIQjrVNmj3RIyZTDxE+ltVx3bgPk/V0LwBVU5oLIQ4or20HgDOrHahX8KfCl8ufjxjys66DVWeJJ8V7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:17:47.009842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.05456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac0f3ea47cbf11dbf86620c6e073426febe5dd468f78e17733eccdf8c4df0cc1","sha256:ce03cd9cc977e17afb6845d04136d97ad1df9117fb064a86ad35713cf2eb1a2a"],"state_sha256":"d021465773ee22bd5ab0ae6f38ec83fc76a42611f8d7362575052fc345fb7ba2"}