{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:7GL7625FVLQCXHQ5THOZ64S4T5","short_pith_number":"pith:7GL7625F","schema_version":"1.0","canonical_sha256":"f997ff6ba5aae02b9e1d99dd9f725c9f450618c131690734215da4923eb89e73","source":{"kind":"arxiv","id":"1008.0530","version":1},"attestation_state":"computed","paper":{"title":"Strategy iteration is strongly polynomial for 2-player turn-based stochastic games with a constant discount factor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Peter Bro Miltersen, Thomas Dueholm Hansen, Uri Zwick","submitted_at":"2010-08-03T12:11:27Z","abstract_excerpt":"Ye showed recently that the simplex method with Dantzig pivoting rule, as well as Howard's policy iteration algorithm, solve discounted Markov decision processes (MDPs), with a constant discount factor, in strongly polynomial time. More precisely, Ye showed that both algorithms terminate after at most $O(\\frac{mn}{1-\\gamma}\\log(\\frac{n}{1-\\gamma}))$ iterations, where $n$ is the number of states, $m$ is the total number of actions in the MDP, and $0<\\gamma<1$ is the discount factor. We improve Ye's analysis in two respects. First, we improve the bound given by Ye and show that Howard's policy 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":"1008.0530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2010-08-03T12:11:27Z","cross_cats_sorted":[],"title_canon_sha256":"f500ba50b8ad2bd016628ffdb98aaa8cfa01006ea11279ba2867bc57d8ba9dcc","abstract_canon_sha256":"d43e5e190709f8f622e7008761f23582ab4b314ebefbcce636e5c467d2dcd480"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:42:42.809955Z","signature_b64":"t3fbRFd/z6tSSKdgU7WBx2uI1NhQ6Vpe+icNx9GO+ORs1nwscbDFfJO+zEtndfUgpXfcp0jeIsIqxBq48I/gDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f997ff6ba5aae02b9e1d99dd9f725c9f450618c131690734215da4923eb89e73","last_reissued_at":"2026-05-18T04:42:42.809543Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:42:42.809543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strategy iteration is strongly polynomial for 2-player turn-based stochastic games with a constant discount factor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Peter Bro Miltersen, Thomas Dueholm Hansen, Uri Zwick","submitted_at":"2010-08-03T12:11:27Z","abstract_excerpt":"Ye showed recently that the simplex method with Dantzig pivoting rule, as well as Howard's policy iteration algorithm, solve discounted Markov decision processes (MDPs), with a constant discount factor, in strongly polynomial time. More precisely, Ye showed that both algorithms terminate after at most $O(\\frac{mn}{1-\\gamma}\\log(\\frac{n}{1-\\gamma}))$ iterations, where $n$ is the number of states, $m$ is the total number of actions in the MDP, and $0<\\gamma<1$ is the discount factor. We improve Ye's analysis in two respects. First, we improve the bound given by Ye and show that Howard's policy i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1008.0530","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":"1008.0530","created_at":"2026-05-18T04:42:42.809603+00:00"},{"alias_kind":"arxiv_version","alias_value":"1008.0530v1","created_at":"2026-05-18T04:42:42.809603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1008.0530","created_at":"2026-05-18T04:42:42.809603+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GL7625FVLQC","created_at":"2026-05-18T12:26:04.259169+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GL7625FVLQCXHQ5","created_at":"2026-05-18T12:26:04.259169+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GL7625F","created_at":"2026-05-18T12:26:04.259169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19695","citing_title":"Planning in entropy-regularized Markov decision processes and games","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GL7625FVLQCXHQ5THOZ64S4T5","json":"https://pith.science/pith/7GL7625FVLQCXHQ5THOZ64S4T5.json","graph_json":"https://pith.science/api/pith-number/7GL7625FVLQCXHQ5THOZ64S4T5/graph.json","events_json":"https://pith.science/api/pith-number/7GL7625FVLQCXHQ5THOZ64S4T5/events.json","paper":"https://pith.science/paper/7GL7625F"},"agent_actions":{"view_html":"https://pith.science/pith/7GL7625FVLQCXHQ5THOZ64S4T5","download_json":"https://pith.science/pith/7GL7625FVLQCXHQ5THOZ64S4T5.json","view_paper":"https://pith.science/paper/7GL7625F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1008.0530&json=true","fetch_graph":"https://pith.science/api/pith-number/7GL7625FVLQCXHQ5THOZ64S4T5/graph.json","fetch_events":"https://pith.science/api/pith-number/7GL7625FVLQCXHQ5THOZ64S4T5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GL7625FVLQCXHQ5THOZ64S4T5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GL7625FVLQCXHQ5THOZ64S4T5/action/storage_attestation","attest_author":"https://pith.science/pith/7GL7625FVLQCXHQ5THOZ64S4T5/action/author_attestation","sign_citation":"https://pith.science/pith/7GL7625FVLQCXHQ5THOZ64S4T5/action/citation_signature","submit_replication":"https://pith.science/pith/7GL7625FVLQCXHQ5THOZ64S4T5/action/replication_record"}},"created_at":"2026-05-18T04:42:42.809603+00:00","updated_at":"2026-05-18T04:42:42.809603+00:00"}