{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:VYEKZVPPEG2PYUGD6PIZC6PQMB","short_pith_number":"pith:VYEKZVPP","schema_version":"1.0","canonical_sha256":"ae08acd5ef21b4fc50c3f3d19179f060554ec9a7275750d422d2c1aecc54e129","source":{"kind":"arxiv","id":"1311.0396","version":1},"attestation_state":"computed","paper":{"title":"Data-based approximate policy iteration for nonlinear continuous-time optimal control design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.SY","authors_text":"Biao Luo, Derong Liu, Huai-Ning Wu, Tingwen Huang","submitted_at":"2013-11-02T17:37:47Z","abstract_excerpt":"This paper addresses the model-free nonlinear optimal problem with generalized cost functional, and a data-based reinforcement learning technique is developed. It is known that the nonlinear optimal control problem relies on the solution of the Hamilton-Jacobi-Bellman (HJB) equation, which is a nonlinear partial differential equation that is generally impossible to be solved analytically. Even worse, most of practical systems are too complicated to establish their accurate mathematical model. To overcome these difficulties, we propose a data-based approximate policy iteration (API) method by u"},"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":"1311.0396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2013-11-02T17:37:47Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"62f69bb314d1f1ad346ebe0ba26779b569ec7e3b6c1167b77122840b6fb87c67","abstract_canon_sha256":"880576ef2779edc99b400702ce51f99f8814645dadbeada50d660b6312bb72ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:06:44.137097Z","signature_b64":"hhowJCw5HikhXNgjpNyfcLvUoHd/tdEx/NynUdO+F89BklHEsX/tWf6QksJQoAuUgpw84zVU1SEG493+1Q9TDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae08acd5ef21b4fc50c3f3d19179f060554ec9a7275750d422d2c1aecc54e129","last_reissued_at":"2026-05-18T03:06:44.136508Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:06:44.136508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-based approximate policy iteration for nonlinear continuous-time optimal control design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.SY","authors_text":"Biao Luo, Derong Liu, Huai-Ning Wu, Tingwen Huang","submitted_at":"2013-11-02T17:37:47Z","abstract_excerpt":"This paper addresses the model-free nonlinear optimal problem with generalized cost functional, and a data-based reinforcement learning technique is developed. It is known that the nonlinear optimal control problem relies on the solution of the Hamilton-Jacobi-Bellman (HJB) equation, which is a nonlinear partial differential equation that is generally impossible to be solved analytically. Even worse, most of practical systems are too complicated to establish their accurate mathematical model. To overcome these difficulties, we propose a data-based approximate policy iteration (API) method by u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.0396","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":"1311.0396","created_at":"2026-05-18T03:06:44.136599+00:00"},{"alias_kind":"arxiv_version","alias_value":"1311.0396v1","created_at":"2026-05-18T03:06:44.136599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.0396","created_at":"2026-05-18T03:06:44.136599+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYEKZVPPEG2P","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYEKZVPPEG2PYUGD","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYEKZVPP","created_at":"2026-05-18T12:28:04.890932+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/VYEKZVPPEG2PYUGD6PIZC6PQMB","json":"https://pith.science/pith/VYEKZVPPEG2PYUGD6PIZC6PQMB.json","graph_json":"https://pith.science/api/pith-number/VYEKZVPPEG2PYUGD6PIZC6PQMB/graph.json","events_json":"https://pith.science/api/pith-number/VYEKZVPPEG2PYUGD6PIZC6PQMB/events.json","paper":"https://pith.science/paper/VYEKZVPP"},"agent_actions":{"view_html":"https://pith.science/pith/VYEKZVPPEG2PYUGD6PIZC6PQMB","download_json":"https://pith.science/pith/VYEKZVPPEG2PYUGD6PIZC6PQMB.json","view_paper":"https://pith.science/paper/VYEKZVPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1311.0396&json=true","fetch_graph":"https://pith.science/api/pith-number/VYEKZVPPEG2PYUGD6PIZC6PQMB/graph.json","fetch_events":"https://pith.science/api/pith-number/VYEKZVPPEG2PYUGD6PIZC6PQMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYEKZVPPEG2PYUGD6PIZC6PQMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYEKZVPPEG2PYUGD6PIZC6PQMB/action/storage_attestation","attest_author":"https://pith.science/pith/VYEKZVPPEG2PYUGD6PIZC6PQMB/action/author_attestation","sign_citation":"https://pith.science/pith/VYEKZVPPEG2PYUGD6PIZC6PQMB/action/citation_signature","submit_replication":"https://pith.science/pith/VYEKZVPPEG2PYUGD6PIZC6PQMB/action/replication_record"}},"created_at":"2026-05-18T03:06:44.136599+00:00","updated_at":"2026-05-18T03:06:44.136599+00:00"}