{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DVGZ33QGUVYMKUPJXC5ZELC6MV","short_pith_number":"pith:DVGZ33QG","schema_version":"1.0","canonical_sha256":"1d4d9dee06a570c551e9b8bb922c5e656e461f27f9c45ad7d1ac04f2f64b41ab","source":{"kind":"arxiv","id":"1806.01492","version":3},"attestation_state":"computed","paper":{"title":"Near-Optimal Time and Sample Complexities for Solving Discounted Markov Decision Process with a Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Aaron Sidford, Lin F. Yang, Mengdi Wang, Xian Wu, Yinyu Ye","submitted_at":"2018-06-05T04:34:54Z","abstract_excerpt":"In this paper we consider the problem of computing an $\\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any state-action pair samples from the transition function in $O(1)$ time. Given such a DMDP with states $S$, actions $A$, discount factor $\\gamma\\in(0,1)$, and rewards in range $[0, 1]$ we provide an algorithm which computes an $\\epsilon$-optimal policy with probability $1 - \\delta$ where \\emph{both} the time spent and number of sample taken are upper bounded by \\[ O\\lef"},"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":"1806.01492","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-06-05T04:34:54Z","cross_cats_sorted":[],"title_canon_sha256":"2868beb5fde9e37c85483f987687620152b4ac7203bf38f377565de60d777078","abstract_canon_sha256":"953d6e186b505d7ab56a6c0974701bb91ce5c67a58be90adb4913a68b69f0092"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.958247Z","signature_b64":"H6joWHEYGupRRcrPbn3yT6LJFYUX7B2Jfm/3sF/aqDDT9V31Lr2FSB/eNVNNZYGqybw4zVLeLxfJaBcmtSiFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d4d9dee06a570c551e9b8bb922c5e656e461f27f9c45ad7d1ac04f2f64b41ab","last_reissued_at":"2026-05-17T23:44:02.957692Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.957692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Time and Sample Complexities for Solving Discounted Markov Decision Process with a Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Aaron Sidford, Lin F. Yang, Mengdi Wang, Xian Wu, Yinyu Ye","submitted_at":"2018-06-05T04:34:54Z","abstract_excerpt":"In this paper we consider the problem of computing an $\\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any state-action pair samples from the transition function in $O(1)$ time. Given such a DMDP with states $S$, actions $A$, discount factor $\\gamma\\in(0,1)$, and rewards in range $[0, 1]$ we provide an algorithm which computes an $\\epsilon$-optimal policy with probability $1 - \\delta$ where \\emph{both} the time spent and number of sample taken are upper bounded by \\[ O\\lef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01492","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1806.01492","created_at":"2026-05-17T23:44:02.957794+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01492v3","created_at":"2026-05-17T23:44:02.957794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01492","created_at":"2026-05-17T23:44:02.957794+00:00"},{"alias_kind":"pith_short_12","alias_value":"DVGZ33QGUVYM","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DVGZ33QGUVYMKUPJ","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DVGZ33QG","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04795","citing_title":"Sample Complexity for Markov Decision Processes and Stochastic Optimal Control with Static Risk Measures","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02141","citing_title":"On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV","json":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV.json","graph_json":"https://pith.science/api/pith-number/DVGZ33QGUVYMKUPJXC5ZELC6MV/graph.json","events_json":"https://pith.science/api/pith-number/DVGZ33QGUVYMKUPJXC5ZELC6MV/events.json","paper":"https://pith.science/paper/DVGZ33QG"},"agent_actions":{"view_html":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV","download_json":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV.json","view_paper":"https://pith.science/paper/DVGZ33QG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01492&json=true","fetch_graph":"https://pith.science/api/pith-number/DVGZ33QGUVYMKUPJXC5ZELC6MV/graph.json","fetch_events":"https://pith.science/api/pith-number/DVGZ33QGUVYMKUPJXC5ZELC6MV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/action/storage_attestation","attest_author":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/action/author_attestation","sign_citation":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/action/citation_signature","submit_replication":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/action/replication_record"}},"created_at":"2026-05-17T23:44:02.957794+00:00","updated_at":"2026-05-17T23:44:02.957794+00:00"}