{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:L2OHHSHXVCQT55AAICV6XGCTSO","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":"05577c5e91d094c7b8aeefd73976f1f050fba3b6e445009ff7c7844f002783d4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T13:01:33Z","title_canon_sha256":"b56dd4d2c8d233f344ce3dc09e4a0d3f7b369fb28197beff8de0b1a5588c6fad"},"schema_version":"1.0","source":{"id":"2006.09118","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.09118","created_at":"2026-07-05T02:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"2006.09118v2","created_at":"2026-07-05T02:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09118","created_at":"2026-07-05T02:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"L2OHHSHXVCQT","created_at":"2026-07-05T02:17:25Z"},{"alias_kind":"pith_short_16","alias_value":"L2OHHSHXVCQT55AA","created_at":"2026-07-05T02:17:25Z"},{"alias_kind":"pith_short_8","alias_value":"L2OHHSHX","created_at":"2026-07-05T02:17:25Z"}],"graph_snapshots":[{"event_id":"sha256:35e6156d07bede241459b5f62b4b4a80bcf7dfb1908f43380f2a43b3960d6142","target":"graph","created_at":"2026-07-05T02:17:25Z","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/2006.09118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents the first non-asymptotic result showing that a model-free algorithm can achieve a logarithmic cumulative regret for episodic tabular reinforcement learning if there exists a strictly positive sub-optimality gap in the optimal $Q$-function. We prove that the optimistic $Q$-learning studied in [Jin et al. 2018] enjoys a ${\\mathcal{O}}\\left(\\frac{SA\\cdot \\mathrm{poly}\\left(H\\right)}{\\Delta_{\\min}}\\log\\left(SAT\\right)\\right)$ cumulative regret bound, where $S$ is the number of states, $A$ is the number of actions, $H$ is the planning horizon, $T$ is the total number of steps, a","authors_text":"Kunhe Yang, Lin F. Yang, Simon S. Du","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T13:01:33Z","title":"$Q$-learning with Logarithmic Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09118","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:fa41b04fd4014e9abe9831272fac2ac8f0ee2249d69b809ff613484fc0aada55","target":"record","created_at":"2026-07-05T02:17:25Z","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":"05577c5e91d094c7b8aeefd73976f1f050fba3b6e445009ff7c7844f002783d4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T13:01:33Z","title_canon_sha256":"b56dd4d2c8d233f344ce3dc09e4a0d3f7b369fb28197beff8de0b1a5588c6fad"},"schema_version":"1.0","source":{"id":"2006.09118","kind":"arxiv","version":2}},"canonical_sha256":"5e9c73c8f7a8a13ef40040abeb9853938f9df9a777766ddc8c8ff509c9c780e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e9c73c8f7a8a13ef40040abeb9853938f9df9a777766ddc8c8ff509c9c780e2","first_computed_at":"2026-07-05T02:17:25.798137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:17:25.798137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZvebpKVH/BVDIiOjc2cGHFG7LcsbiA9i6m8nP7ctxhlbSFGQ5yuS1/CaiFQDSXAdEo4jHJMXGQYYWuWgpYZ0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T02:17:25.798649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.09118","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa41b04fd4014e9abe9831272fac2ac8f0ee2249d69b809ff613484fc0aada55","sha256:35e6156d07bede241459b5f62b4b4a80bcf7dfb1908f43380f2a43b3960d6142"],"state_sha256":"c5beb87392ca4fd6b2e99314406fc7de44f5f915cf641507fa7c7d9f022c67d6"}