{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XSJ47OKATDOFMQ7S7CCBGMVVSB","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":"6c6eaf8d9b6098eb640692cf77d45adaed9983cb82a5ce00e0033a12bc2c479b","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T15:34:44Z","title_canon_sha256":"31697437e76b47f80fbd88cd2d621d116243ff0444154add1a9bfda33ec289dd"},"schema_version":"1.0","source":{"id":"2311.13469","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13469","created_at":"2026-07-05T07:58:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13469v2","created_at":"2026-07-05T07:58:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13469","created_at":"2026-07-05T07:58:25Z"},{"alias_kind":"pith_short_12","alias_value":"XSJ47OKATDOF","created_at":"2026-07-05T07:58:25Z"},{"alias_kind":"pith_short_16","alias_value":"XSJ47OKATDOFMQ7S","created_at":"2026-07-05T07:58:25Z"},{"alias_kind":"pith_short_8","alias_value":"XSJ47OKA","created_at":"2026-07-05T07:58:25Z"}],"graph_snapshots":[{"event_id":"sha256:cabec14980da403700343ecff4ec508bafa81b2b63f105cd907e489b5567311e","target":"graph","created_at":"2026-07-05T07:58:25Z","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/2311.13469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the sample complexity of learning an $\\varepsilon$-optimal policy in an average-reward Markov decision process (MDP) under a generative model. We establish the complexity bound $\\widetilde{O}\\left(SA\\frac{H}{\\varepsilon^2} \\right)$, where $H$ is the span of the bias function of the optimal policy and $SA$ is the cardinality of the state-action space. Our result is the first that is minimax optimal (up to log factors) in all parameters $S,A,H$ and $\\varepsilon$, improving on existing work that either assumes uniformly bounded mixing times for all policies or has suboptimal dependence o","authors_text":"Matthew Zurek, Yudong Chen","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T15:34:44Z","title":"Span-Based Optimal Sample Complexity for Average Reward MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13469","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":"sha256:93b4aa04173b2318a08f6986350a411afe224d78e0eecd149f803df6e3abce2a","target":"record","created_at":"2026-07-05T07:58:25Z","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":"6c6eaf8d9b6098eb640692cf77d45adaed9983cb82a5ce00e0033a12bc2c479b","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T15:34:44Z","title_canon_sha256":"31697437e76b47f80fbd88cd2d621d116243ff0444154add1a9bfda33ec289dd"},"schema_version":"1.0","source":{"id":"2311.13469","kind":"arxiv","version":2}},"canonical_sha256":"bc93cfb94098dc5643f2f8841332b5907ab18bca1ed35411f01ffe1e7da3869d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc93cfb94098dc5643f2f8841332b5907ab18bca1ed35411f01ffe1e7da3869d","first_computed_at":"2026-07-05T07:58:25.067417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:25.067417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NPBzTWxZZbprEAatzIzlKj6kWEFouxd7D7Z2zfOuSTzTdcnl6wZUundRG/9jXaRODoQDTFZEZcjxQNJ9/ogXBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:25.067818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13469","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93b4aa04173b2318a08f6986350a411afe224d78e0eecd149f803df6e3abce2a","sha256:cabec14980da403700343ecff4ec508bafa81b2b63f105cd907e489b5567311e"],"state_sha256":"4a0f751b4b61b2119d5fd9098cd62e22a81f09c90da30b30a58081d5871b36b1"}