{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:LGKWV5JU6TF7IC6UQ265B3R2UN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7562d9b5932921ee34fa73497d5facc63a7d06a2f4609937ff4388bc97e6646e","cross_cats_sorted":["cs.AI","cs.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-04-12T19:09:43Z","title_canon_sha256":"2bfa631950ff0eb37653e70c904a9039501b38f855df87489f7011eb7cd729b4"},"schema_version":"1.0","source":{"id":"1004.2027","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1004.2027","created_at":"2026-05-18T04:13:55Z"},{"alias_kind":"arxiv_version","alias_value":"1004.2027v2","created_at":"2026-05-18T04:13:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1004.2027","created_at":"2026-05-18T04:13:55Z"},{"alias_kind":"pith_short_12","alias_value":"LGKWV5JU6TF7","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_16","alias_value":"LGKWV5JU6TF7IC6U","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_8","alias_value":"LGKWV5JU","created_at":"2026-05-18T12:26:10Z"}],"graph_snapshots":[{"event_id":"sha256:f6dd650ccf946a43b9922862bd420e3f3c009ee2d4affc3adcf9a614671da238","target":"graph","created_at":"2026-05-18T04:13:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\\infty-norm performance-loss bounds for DPP in the presence of approximation/estimation error. The bounds are expressed in terms of the l\\infty-norm of the average accumulated error as opposed to the l\\infty-norm of the error in the case of the standard approximate value iteration (AVI) and the approximate policy iteration (API). This suggests that DPP can achieve a bet","authors_text":"Hilbert J. Kappen, Mohammad Gheshlaghi Azar, Vicenc Gomez","cross_cats":["cs.AI","cs.SY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-04-12T19:09:43Z","title":"Dynamic Policy Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1004.2027","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fa2d7d69010f5456b6edfaf535c2e7d3d68fd6db995a2fd1ee77c65341afaff2","target":"record","created_at":"2026-05-18T04:13:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7562d9b5932921ee34fa73497d5facc63a7d06a2f4609937ff4388bc97e6646e","cross_cats_sorted":["cs.AI","cs.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-04-12T19:09:43Z","title_canon_sha256":"2bfa631950ff0eb37653e70c904a9039501b38f855df87489f7011eb7cd729b4"},"schema_version":"1.0","source":{"id":"1004.2027","kind":"arxiv","version":2}},"canonical_sha256":"59956af534f4cbf40bd486bdd0ee3aa35fdd15e97df21ebcfbd7ff78e4c7c5e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59956af534f4cbf40bd486bdd0ee3aa35fdd15e97df21ebcfbd7ff78e4c7c5e7","first_computed_at":"2026-05-18T04:13:55.318814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:13:55.318814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PPZ8JBNjN0XE/qKmlqPsXL4pbINHgAAFsoplKGxerTPZ/bmlTFVfx7Tj2eYfJU2qFg5vl9VDd11A7NrsNMR5Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T04:13:55.319270Z","signed_message":"canonical_sha256_bytes"},"source_id":"1004.2027","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa2d7d69010f5456b6edfaf535c2e7d3d68fd6db995a2fd1ee77c65341afaff2","sha256:f6dd650ccf946a43b9922862bd420e3f3c009ee2d4affc3adcf9a614671da238"],"state_sha256":"948ff5c56f9ec585f38e42f0cb34d3dc00d6666ece33a8e1af61a3ac44cbad97"}