{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QPK7FTAV3PJCPFGUKXCHY64P64","short_pith_number":"pith:QPK7FTAV","schema_version":"1.0","canonical_sha256":"83d5f2cc15dbd22794d455c47c7b8ff72793f181e6965d5b25ee4004d6dac76c","source":{"kind":"arxiv","id":"2410.07616","version":2},"attestation_state":"computed","paper":{"title":"The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthew Zurek, Yudong Chen","submitted_at":"2024-10-10T05:08:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.07616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T05:08:14Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"b11dffadcebc9fb6bd75302ed4743afd1131b662203145967ba0a70071ba1e87","abstract_canon_sha256":"7985d4d8a1d7b4084cf12b1cbce6484691ab5816693e5e6b70b5bb6df9bad76b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:21.050182Z","signature_b64":"AEfG6gNLMx34sRYxh6OdRMsFLYHWKgOTsVRqvtjo/qox3DHCeWI4TFlPNlZoV5xpjpUPkzXdCvjZP03uw48oAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83d5f2cc15dbd22794d455c47c7b8ff72793f181e6965d5b25ee4004d6dac76c","last_reissued_at":"2026-07-05T10:12:21.049610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:21.049610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthew Zurek, Yudong Chen","submitted_at":"2024-10-10T05:08:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07616","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.07616/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.07616","created_at":"2026-07-05T10:12:21.049677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07616v2","created_at":"2026-07-05T10:12:21.049677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07616","created_at":"2026-07-05T10:12:21.049677+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPK7FTAV3PJC","created_at":"2026-07-05T10:12:21.049677+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPK7FTAV3PJCPFGU","created_at":"2026-07-05T10:12:21.049677+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPK7FTAV","created_at":"2026-07-05T10:12:21.049677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14444","citing_title":"Statistical and Algorithmic Foundations of Reinforcement Learning","ref_index":161,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPK7FTAV3PJCPFGUKXCHY64P64","json":"https://pith.science/pith/QPK7FTAV3PJCPFGUKXCHY64P64.json","graph_json":"https://pith.science/api/pith-number/QPK7FTAV3PJCPFGUKXCHY64P64/graph.json","events_json":"https://pith.science/api/pith-number/QPK7FTAV3PJCPFGUKXCHY64P64/events.json","paper":"https://pith.science/paper/QPK7FTAV"},"agent_actions":{"view_html":"https://pith.science/pith/QPK7FTAV3PJCPFGUKXCHY64P64","download_json":"https://pith.science/pith/QPK7FTAV3PJCPFGUKXCHY64P64.json","view_paper":"https://pith.science/paper/QPK7FTAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07616&json=true","fetch_graph":"https://pith.science/api/pith-number/QPK7FTAV3PJCPFGUKXCHY64P64/graph.json","fetch_events":"https://pith.science/api/pith-number/QPK7FTAV3PJCPFGUKXCHY64P64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPK7FTAV3PJCPFGUKXCHY64P64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPK7FTAV3PJCPFGUKXCHY64P64/action/storage_attestation","attest_author":"https://pith.science/pith/QPK7FTAV3PJCPFGUKXCHY64P64/action/author_attestation","sign_citation":"https://pith.science/pith/QPK7FTAV3PJCPFGUKXCHY64P64/action/citation_signature","submit_replication":"https://pith.science/pith/QPK7FTAV3PJCPFGUKXCHY64P64/action/replication_record"}},"created_at":"2026-07-05T10:12:21.049677+00:00","updated_at":"2026-07-05T10:12:21.049677+00:00"}