{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:LGKWV5JU6TF7IC6UQ265B3R2UN","short_pith_number":"pith:LGKWV5JU","schema_version":"1.0","canonical_sha256":"59956af534f4cbf40bd486bdd0ee3aa35fdd15e97df21ebcfbd7ff78e4c7c5e7","source":{"kind":"arxiv","id":"1004.2027","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Policy Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hilbert J. Kappen, Mohammad Gheshlaghi Azar, Vicenc Gomez","submitted_at":"2010-04-12T19:09:43Z","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"},"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":"1004.2027","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-04-12T19:09:43Z","cross_cats_sorted":["cs.AI","cs.SY","math.OC","stat.ML"],"title_canon_sha256":"2bfa631950ff0eb37653e70c904a9039501b38f855df87489f7011eb7cd729b4","abstract_canon_sha256":"7562d9b5932921ee34fa73497d5facc63a7d06a2f4609937ff4388bc97e6646e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:13:55.319270Z","signature_b64":"PPZ8JBNjN0XE/qKmlqPsXL4pbINHgAAFsoplKGxerTPZ/bmlTFVfx7Tj2eYfJU2qFg5vl9VDd11A7NrsNMR5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59956af534f4cbf40bd486bdd0ee3aa35fdd15e97df21ebcfbd7ff78e4c7c5e7","last_reissued_at":"2026-05-18T04:13:55.318814Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:13:55.318814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Policy Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hilbert J. Kappen, Mohammad Gheshlaghi Azar, Vicenc Gomez","submitted_at":"2010-04-12T19:09:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1004.2027","kind":"arxiv","version":2},"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":"1004.2027","created_at":"2026-05-18T04:13:55.318881+00:00"},{"alias_kind":"arxiv_version","alias_value":"1004.2027v2","created_at":"2026-05-18T04:13:55.318881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1004.2027","created_at":"2026-05-18T04:13:55.318881+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGKWV5JU6TF7","created_at":"2026-05-18T12:26:10.704358+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGKWV5JU6TF7IC6U","created_at":"2026-05-18T12:26:10.704358+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGKWV5JU","created_at":"2026-05-18T12:26:10.704358+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/LGKWV5JU6TF7IC6UQ265B3R2UN","json":"https://pith.science/pith/LGKWV5JU6TF7IC6UQ265B3R2UN.json","graph_json":"https://pith.science/api/pith-number/LGKWV5JU6TF7IC6UQ265B3R2UN/graph.json","events_json":"https://pith.science/api/pith-number/LGKWV5JU6TF7IC6UQ265B3R2UN/events.json","paper":"https://pith.science/paper/LGKWV5JU"},"agent_actions":{"view_html":"https://pith.science/pith/LGKWV5JU6TF7IC6UQ265B3R2UN","download_json":"https://pith.science/pith/LGKWV5JU6TF7IC6UQ265B3R2UN.json","view_paper":"https://pith.science/paper/LGKWV5JU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1004.2027&json=true","fetch_graph":"https://pith.science/api/pith-number/LGKWV5JU6TF7IC6UQ265B3R2UN/graph.json","fetch_events":"https://pith.science/api/pith-number/LGKWV5JU6TF7IC6UQ265B3R2UN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGKWV5JU6TF7IC6UQ265B3R2UN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGKWV5JU6TF7IC6UQ265B3R2UN/action/storage_attestation","attest_author":"https://pith.science/pith/LGKWV5JU6TF7IC6UQ265B3R2UN/action/author_attestation","sign_citation":"https://pith.science/pith/LGKWV5JU6TF7IC6UQ265B3R2UN/action/citation_signature","submit_replication":"https://pith.science/pith/LGKWV5JU6TF7IC6UQ265B3R2UN/action/replication_record"}},"created_at":"2026-05-18T04:13:55.318881+00:00","updated_at":"2026-05-18T04:13:55.318881+00:00"}