{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M3ARRVNQ25JGFS6272T3UBADO6","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":"3adb1cd3f99964e42788ecb83fec2559bd686d20b7833a441a0155ec2ca03642","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-15T05:43:17Z","title_canon_sha256":"7c1672f6b93c8e05eea80fde89c4cea76ed28c91bef67e9060b4a069b7852903"},"schema_version":"1.0","source":{"id":"2302.07477","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.07477","created_at":"2026-07-05T06:55:52Z"},{"alias_kind":"arxiv_version","alias_value":"2302.07477v3","created_at":"2026-07-05T06:55:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07477","created_at":"2026-07-05T06:55:52Z"},{"alias_kind":"pith_short_12","alias_value":"M3ARRVNQ25JG","created_at":"2026-07-05T06:55:52Z"},{"alias_kind":"pith_short_16","alias_value":"M3ARRVNQ25JGFS62","created_at":"2026-07-05T06:55:52Z"},{"alias_kind":"pith_short_8","alias_value":"M3ARRVNQ","created_at":"2026-07-05T06:55:52Z"}],"graph_snapshots":[{"event_id":"sha256:48190f82b67e78c3434c4d151c936d26fed144a4dce2f41a44f146f6ab85fb07","target":"graph","created_at":"2026-07-05T06:55:52Z","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/2302.07477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the optimal sample complexity theory of tabular reinforcement learning (RL) for maximizing the infinite horizon discounted reward in a Markov decision process (MDP). Optimal worst-case complexity results have been developed for tabular RL problems in this setting, leading to a sample complexity dependence on $\\gamma$ and $\\epsilon$ of the form $\\tilde \\Theta((1-\\gamma)^{-3}\\epsilon^{-2})$, where $\\gamma$ denotes the discount factor and $\\epsilon$ is the solution error tolerance. However, in many applications of interest, the optimal policy (or all policies) induces mixing. We estab","authors_text":"Jose Blanchet, Peter Glynn, Shengbo Wang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-15T05:43:17Z","title":"Optimal Sample Complexity of Reinforcement Learning for Mixing Discounted Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07477","kind":"arxiv","version":3},"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:b3579e831b41c11dd0ad1bfe2385216f7eb837d0885775baf3f899aeb2bad942","target":"record","created_at":"2026-07-05T06:55:52Z","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":"3adb1cd3f99964e42788ecb83fec2559bd686d20b7833a441a0155ec2ca03642","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-15T05:43:17Z","title_canon_sha256":"7c1672f6b93c8e05eea80fde89c4cea76ed28c91bef67e9060b4a069b7852903"},"schema_version":"1.0","source":{"id":"2302.07477","kind":"arxiv","version":3}},"canonical_sha256":"66c118d5b0d75262cbdafea7ba040377b642932e65c2a0790a0c953896e90ea0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66c118d5b0d75262cbdafea7ba040377b642932e65c2a0790a0c953896e90ea0","first_computed_at":"2026-07-05T06:55:52.203559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:52.203559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YjqXh7gANdvu2Hf8PqiX0+u1tvqgDnR7qRfJv4+1wAKluOsDmh1j5pqbSIzZ7jl8bEefv0xzY5FGCqu/AKo2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:52.204027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.07477","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3579e831b41c11dd0ad1bfe2385216f7eb837d0885775baf3f899aeb2bad942","sha256:48190f82b67e78c3434c4d151c936d26fed144a4dce2f41a44f146f6ab85fb07"],"state_sha256":"ed8670261625c27f1c4d0e53edc40589976bddaf287bab86d2ff9a0618cbfce6"}