{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QPK7FTAV3PJCPFGUKXCHY64P64","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":"7985d4d8a1d7b4084cf12b1cbce6484691ab5816693e5e6b70b5bb6df9bad76b","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":"2024-10-10T05:08:14Z","title_canon_sha256":"b11dffadcebc9fb6bd75302ed4743afd1131b662203145967ba0a70071ba1e87"},"schema_version":"1.0","source":{"id":"2410.07616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07616","created_at":"2026-07-05T10:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07616v2","created_at":"2026-07-05T10:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07616","created_at":"2026-07-05T10:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"QPK7FTAV3PJC","created_at":"2026-07-05T10:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"QPK7FTAV3PJCPFGU","created_at":"2026-07-05T10:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"QPK7FTAV","created_at":"2026-07-05T10:12:21Z"}],"graph_snapshots":[{"event_id":"sha256:7af09043625ea968ed38f586dc281ac4ca9459cefae6ab2756f5168ac0bb07c1","target":"graph","created_at":"2026-07-05T10:12:21Z","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/2410.07616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the sample complexity of the plug-in approach for learning $\\varepsilon$-optimal policies in average-reward Markov decision processes (MDPs) with a generative model. The plug-in approach constructs a model estimate then computes an average-reward optimal policy in the estimated model. Despite representing arguably the simplest algorithm for this problem, the plug-in approach has never been theoretically analyzed. Unlike the more well-studied discounted MDP reduction method, the plug-in approach requires no prior problem information or parameter tuning. Our results fill this gap and ad","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":"2024-10-10T05:08:14Z","title":"The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07616","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:d082b5661d55be322e46216b50aac744e8fa44841ecc30c6c5ab16c657c8e2c9","target":"record","created_at":"2026-07-05T10:12:21Z","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":"7985d4d8a1d7b4084cf12b1cbce6484691ab5816693e5e6b70b5bb6df9bad76b","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":"2024-10-10T05:08:14Z","title_canon_sha256":"b11dffadcebc9fb6bd75302ed4743afd1131b662203145967ba0a70071ba1e87"},"schema_version":"1.0","source":{"id":"2410.07616","kind":"arxiv","version":2}},"canonical_sha256":"83d5f2cc15dbd22794d455c47c7b8ff72793f181e6965d5b25ee4004d6dac76c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83d5f2cc15dbd22794d455c47c7b8ff72793f181e6965d5b25ee4004d6dac76c","first_computed_at":"2026-07-05T10:12:21.049610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:21.049610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AEfG6gNLMx34sRYxh6OdRMsFLYHWKgOTsVRqvtjo/qox3DHCeWI4TFlPNlZoV5xpjpUPkzXdCvjZP03uw48oAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:21.050182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d082b5661d55be322e46216b50aac744e8fa44841ecc30c6c5ab16c657c8e2c9","sha256:7af09043625ea968ed38f586dc281ac4ca9459cefae6ab2756f5168ac0bb07c1"],"state_sha256":"2d206e281b440b3ff438398045ba55443d33af5db2959430af9b4486e749e3e8"}