{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:HBBXYMLECD3U5XIB7NKJEWPY7R","short_pith_number":"pith:HBBXYMLE","schema_version":"1.0","canonical_sha256":"38437c316410f74edd01fb549259f8fc6c6cf08cf665ef7e510dfbfe8f72d57a","source":{"kind":"arxiv","id":"1301.0583","version":1},"attestation_state":"computed","paper":{"title":"Polynomial Value Iteration Algorithms for Detrerminstic MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.AI","authors_text":"Omid Madani","submitted_at":"2012-12-12T15:57:15Z","abstract_excerpt":"Value iteration is a commonly used and empirically competitive method in solving many Markov decision process problems.  However, it is known that value iteration has only pseudo-polynomial complexity in general.  We establish a somewhat surprising polynomial bound for value iteration on deterministic Markov decision (DMDP) problems.  We show that the basic value iteration procedure converges to the highest average reward cycle on a DMDP problem in heta(n^2) iterations, or heta(mn^2) total time, where n denotes the number of states, and m the number of edges.  We give two extensions of value i"},"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":"1301.0583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-12-12T15:57:15Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"43acf54dc499d2ae9126766397d297dce3e65ba44fb1408c0ec4b176a256454b","abstract_canon_sha256":"cbd9a2f0242f8b1897000393ba2caa6924319c9daf22577c635051bba98471a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:37:18.367940Z","signature_b64":"uQtEmjTQGGa1RsYAugMSHd7YCZ0ORGAXoq7R6GksQKwJN0O8/uyFVMsi3mp4cCnjjxRL06v0P9orLKj5k7VHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38437c316410f74edd01fb549259f8fc6c6cf08cf665ef7e510dfbfe8f72d57a","last_reissued_at":"2026-05-18T03:37:18.367292Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:37:18.367292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Polynomial Value Iteration Algorithms for Detrerminstic MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.AI","authors_text":"Omid Madani","submitted_at":"2012-12-12T15:57:15Z","abstract_excerpt":"Value iteration is a commonly used and empirically competitive method in solving many Markov decision process problems.  However, it is known that value iteration has only pseudo-polynomial complexity in general.  We establish a somewhat surprising polynomial bound for value iteration on deterministic Markov decision (DMDP) problems.  We show that the basic value iteration procedure converges to the highest average reward cycle on a DMDP problem in heta(n^2) iterations, or heta(mn^2) total time, where n denotes the number of states, and m the number of edges.  We give two extensions of value i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0583","kind":"arxiv","version":1},"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":"1301.0583","created_at":"2026-05-18T03:37:18.367411+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.0583v1","created_at":"2026-05-18T03:37:18.367411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0583","created_at":"2026-05-18T03:37:18.367411+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBBXYMLECD3U","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBBXYMLECD3U5XIB","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBBXYMLE","created_at":"2026-05-18T12:27:09.501522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBBXYMLECD3U5XIB7NKJEWPY7R","json":"https://pith.science/pith/HBBXYMLECD3U5XIB7NKJEWPY7R.json","graph_json":"https://pith.science/api/pith-number/HBBXYMLECD3U5XIB7NKJEWPY7R/graph.json","events_json":"https://pith.science/api/pith-number/HBBXYMLECD3U5XIB7NKJEWPY7R/events.json","paper":"https://pith.science/paper/HBBXYMLE"},"agent_actions":{"view_html":"https://pith.science/pith/HBBXYMLECD3U5XIB7NKJEWPY7R","download_json":"https://pith.science/pith/HBBXYMLECD3U5XIB7NKJEWPY7R.json","view_paper":"https://pith.science/paper/HBBXYMLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.0583&json=true","fetch_graph":"https://pith.science/api/pith-number/HBBXYMLECD3U5XIB7NKJEWPY7R/graph.json","fetch_events":"https://pith.science/api/pith-number/HBBXYMLECD3U5XIB7NKJEWPY7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBBXYMLECD3U5XIB7NKJEWPY7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBBXYMLECD3U5XIB7NKJEWPY7R/action/storage_attestation","attest_author":"https://pith.science/pith/HBBXYMLECD3U5XIB7NKJEWPY7R/action/author_attestation","sign_citation":"https://pith.science/pith/HBBXYMLECD3U5XIB7NKJEWPY7R/action/citation_signature","submit_replication":"https://pith.science/pith/HBBXYMLECD3U5XIB7NKJEWPY7R/action/replication_record"}},"created_at":"2026-05-18T03:37:18.367411+00:00","updated_at":"2026-05-18T03:37:18.367411+00:00"}