{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7XONRNLCHUDPPEWD77FYVS2ZIF","short_pith_number":"pith:7XONRNLC","schema_version":"1.0","canonical_sha256":"fddcd8b5623d06f792c3ffcb8acb59415164c42955212f8d50b1a38acb4afc59","source":{"kind":"arxiv","id":"1704.01869","version":3},"attestation_state":"computed","paper":{"title":"Randomized Linear Programming Solves the Discounted Markov Decision Problem In Nearly-Linear (Sometimes Sublinear) Running Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"math.OC","authors_text":"Mengdi Wang","submitted_at":"2017-04-06T14:45:40Z","abstract_excerpt":"We propose a novel randomized linear programming algorithm for approximating the optimal policy of the discounted Markov decision problem. By leveraging the value-policy duality and binary-tree data structures, the algorithm adaptively samples state-action-state transitions and makes exponentiated primal-dual updates. We show that it finds an $\\epsilon$-optimal policy using nearly-linear run time in the worst case. When the Markov decision process is ergodic and specified in some special data formats, the algorithm finds an $\\epsilon$-optimal policy using run time linear in the total number of"},"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":"1704.01869","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-04-06T14:45:40Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"4a91c3b99ef9c0436b8ab7a1e9a7e3f6030058ffaba5904559eec539338ab871","abstract_canon_sha256":"3ad53f26ab79e47d572ea9e8807a2cbe0479f8e73377e5bc464584bf9ce54181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:33.076395Z","signature_b64":"OdYQJ0bbvqTfZJagOAVsE0Xx7jDagumUEo96tqsZiuxpRMyC2Y0iAVmY97/OYsmqNFNny3K94rvEUA2NJI2FDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fddcd8b5623d06f792c3ffcb8acb59415164c42955212f8d50b1a38acb4afc59","last_reissued_at":"2026-05-17T23:44:33.075840Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:33.075840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Linear Programming Solves the Discounted Markov Decision Problem In Nearly-Linear (Sometimes Sublinear) Running Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"math.OC","authors_text":"Mengdi Wang","submitted_at":"2017-04-06T14:45:40Z","abstract_excerpt":"We propose a novel randomized linear programming algorithm for approximating the optimal policy of the discounted Markov decision problem. By leveraging the value-policy duality and binary-tree data structures, the algorithm adaptively samples state-action-state transitions and makes exponentiated primal-dual updates. We show that it finds an $\\epsilon$-optimal policy using nearly-linear run time in the worst case. When the Markov decision process is ergodic and specified in some special data formats, the algorithm finds an $\\epsilon$-optimal policy using run time linear in the total number of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01869","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":"1704.01869","created_at":"2026-05-17T23:44:33.075924+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.01869v3","created_at":"2026-05-17T23:44:33.075924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01869","created_at":"2026-05-17T23:44:33.075924+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XONRNLCHUDP","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XONRNLCHUDPPEWD","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XONRNLC","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16111","citing_title":"Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XONRNLCHUDPPEWD77FYVS2ZIF","json":"https://pith.science/pith/7XONRNLCHUDPPEWD77FYVS2ZIF.json","graph_json":"https://pith.science/api/pith-number/7XONRNLCHUDPPEWD77FYVS2ZIF/graph.json","events_json":"https://pith.science/api/pith-number/7XONRNLCHUDPPEWD77FYVS2ZIF/events.json","paper":"https://pith.science/paper/7XONRNLC"},"agent_actions":{"view_html":"https://pith.science/pith/7XONRNLCHUDPPEWD77FYVS2ZIF","download_json":"https://pith.science/pith/7XONRNLCHUDPPEWD77FYVS2ZIF.json","view_paper":"https://pith.science/paper/7XONRNLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.01869&json=true","fetch_graph":"https://pith.science/api/pith-number/7XONRNLCHUDPPEWD77FYVS2ZIF/graph.json","fetch_events":"https://pith.science/api/pith-number/7XONRNLCHUDPPEWD77FYVS2ZIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XONRNLCHUDPPEWD77FYVS2ZIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XONRNLCHUDPPEWD77FYVS2ZIF/action/storage_attestation","attest_author":"https://pith.science/pith/7XONRNLCHUDPPEWD77FYVS2ZIF/action/author_attestation","sign_citation":"https://pith.science/pith/7XONRNLCHUDPPEWD77FYVS2ZIF/action/citation_signature","submit_replication":"https://pith.science/pith/7XONRNLCHUDPPEWD77FYVS2ZIF/action/replication_record"}},"created_at":"2026-05-17T23:44:33.075924+00:00","updated_at":"2026-05-17T23:44:33.075924+00:00"}