{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:09:58Z","timestamp":1740100198379,"version":"3.37.3"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1702300,2018AAA0101502"],"award-info":[{"award-number":["2018YFB1702300,2018AAA0101502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073321,61873300"],"award-info":[{"award-number":["62073321,61873300"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533395","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Policy Iteration Algorithm for Constrained Cost Optimal Control of Discrete-Time Nonlinear System"],"prefix":"10.1109","author":[{"given":"Tao","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory for Management and Control of Complex Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinglai","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory for Management and Control of Complex Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,The State Key Laboratory for Management and Control of Complex Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruizhuo","family":"Song","sequence":"additional","affiliation":[{"name":"School of Automation, University of Science and Technology Beijing,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2940663"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2611613"},{"key":"ref12","first-page":"2794","article-title":"Policy approximation in policy iteration approximate dynamic programming for discrete-time nonlinear systems","volume":"29","author":"guo","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2907991"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2905715"},{"journal-title":"Constrained Markov Decision Processes","year":"1999","author":"altman","key":"ref15"},{"key":"ref16","article-title":"A lyapunov-based approach to safe reinforcement learning","volume":"31","author":"chow","year":"0","journal-title":"Proceeding Of Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2492242"},{"journal-title":"Dynamic Programming","year":"1957","author":"bellman","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2417510"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2869462"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2586082"},{"key":"ref2","first-page":"67","article-title":"A menu of designs for reinforcement learning over time","author":"werbos","year":"1991","journal-title":"Neural Networks for Control"},{"key":"ref1","first-page":"25","article-title":"Advanced forecasting methods for global crisis warning and models of intelligence","volume":"22","author":"werbos","year":"1977","journal-title":"General Syst Yearbook"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2018.2866823"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533395.pdf?arnumber=9533395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:33:27Z","timestamp":1659483207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533395","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}