{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IKI2OWAUFXXISALBNTFIQPUISN","short_pith_number":"pith:IKI2OWAU","schema_version":"1.0","canonical_sha256":"4291a758142dee8901616cca883e88934ceecb34e469980be48605977a6b88c1","source":{"kind":"arxiv","id":"1803.07743","version":4},"attestation_state":"computed","paper":{"title":"A Supplementary Condition for the Convergence of the Control Policy during Adaptive Dynamic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Nitin Sharma, Xuefeng Bao, Zhi-Hong Mao","submitted_at":"2018-03-21T04:16:14Z","abstract_excerpt":"Reinforcement learning based adaptive/approximate dynamic programming (ADP) is a powerful technique to determine an approximate optimal controller for a dynamical system. These methods bypass the need to analytically solve the nonlinear Hamilton-Jacobi-Bellman equation, whose solution is often to difficult to determine but is needed to determine the optimal control policy. ADP methods usually employ a policy iteration algorithm that evaluates and improves a value function at every step to find the optimal control policy. Previous works in ADP have been lacking a stronger condition that ensures"},"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":"1803.07743","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T04:16:14Z","cross_cats_sorted":[],"title_canon_sha256":"4ce349c6b4e8c3fa02991827d17c51189d7ab1b5f882054993f45b5ac0e20eff","abstract_canon_sha256":"dd80f0fc087ff25bd94965e371dd92b8047de264fe6bb00157b18505db5d886e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:09.608177Z","signature_b64":"qtq7TGHXiZok8aGiM1xHgnWTvfCVq+DUiVqxk7ty+zLHKlvEYUeOiJJ/GndSUkyvodHD1o2eXxzhh/d9dxuRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4291a758142dee8901616cca883e88934ceecb34e469980be48605977a6b88c1","last_reissued_at":"2026-05-18T00:15:09.607621Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:09.607621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Supplementary Condition for the Convergence of the Control Policy during Adaptive Dynamic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Nitin Sharma, Xuefeng Bao, Zhi-Hong Mao","submitted_at":"2018-03-21T04:16:14Z","abstract_excerpt":"Reinforcement learning based adaptive/approximate dynamic programming (ADP) is a powerful technique to determine an approximate optimal controller for a dynamical system. These methods bypass the need to analytically solve the nonlinear Hamilton-Jacobi-Bellman equation, whose solution is often to difficult to determine but is needed to determine the optimal control policy. ADP methods usually employ a policy iteration algorithm that evaluates and improves a value function at every step to find the optimal control policy. Previous works in ADP have been lacking a stronger condition that ensures"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07743","kind":"arxiv","version":4},"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":"1803.07743","created_at":"2026-05-18T00:15:09.607708+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.07743v4","created_at":"2026-05-18T00:15:09.607708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07743","created_at":"2026-05-18T00:15:09.607708+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKI2OWAUFXXI","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKI2OWAUFXXISALB","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKI2OWAU","created_at":"2026-05-18T12:32:31.084164+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/IKI2OWAUFXXISALBNTFIQPUISN","json":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN.json","graph_json":"https://pith.science/api/pith-number/IKI2OWAUFXXISALBNTFIQPUISN/graph.json","events_json":"https://pith.science/api/pith-number/IKI2OWAUFXXISALBNTFIQPUISN/events.json","paper":"https://pith.science/paper/IKI2OWAU"},"agent_actions":{"view_html":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN","download_json":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN.json","view_paper":"https://pith.science/paper/IKI2OWAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.07743&json=true","fetch_graph":"https://pith.science/api/pith-number/IKI2OWAUFXXISALBNTFIQPUISN/graph.json","fetch_events":"https://pith.science/api/pith-number/IKI2OWAUFXXISALBNTFIQPUISN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN/action/storage_attestation","attest_author":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN/action/author_attestation","sign_citation":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN/action/citation_signature","submit_replication":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN/action/replication_record"}},"created_at":"2026-05-18T00:15:09.607708+00:00","updated_at":"2026-05-18T00:15:09.607708+00:00"}