{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:24:02Z","timestamp":1730204642480,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10384307","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"1643-1648","source":"Crossref","is-referenced-by-count":0,"title":["An Optimal Solution to Infinite Horizon Nonlinear Control Problems"],"prefix":"10.1109","author":[{"given":"Mohamed Naveed","family":"Gul Mohamed","sequence":"first","affiliation":[{"name":"Texas A&M University, College Station,Department of Aerospace Engineering,TX,USA,77843"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raman","family":"Goyal","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station,Department of Aerospace Engineering,TX,USA,77843"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suman","family":"Chakravorty","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station,Department of Aerospace Engineering,TX,USA,77843"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Dynamic Programming and Optimal Control. 2nd.","volume":"I","author":"Bertsekas","year":"2000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9781139087353.004"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.4590030303"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1992.371538"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF01968501"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref7","volume-title":"Reinforcement learning and approximate dynamic programming for feedback control","volume":"17","author":"Lewis","year":"2013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/9.24227"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2015.0733"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/2200000042"},{"key":"ref11","article-title":"Finite-time bounds for fitted value iteration","volume":"9","author":"Munos","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref14","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"Sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref16","article-title":"Trust region policy optimization","volume-title":"International Conference on Machine Learning","author":"Schulman","year":"2015"},{"key":"ref17","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref18","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","volume":"abs\/1802. 09477","author":"Fujimoto","year":"2018","journal-title":"ArXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref20","article-title":"On the Search for Feedback in Reinforcement Learning","author":"Wang","year":"2022","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.128"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/s0005-1098(99)00214-9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.10.011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2013.6669584"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3182\/20120823-5-NL-3013.00063"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46024-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.08.540"},{"key":"ref28","article-title":"An Optimal Solution to Infinite Horizon Nonlinear Control Problems","author":"Mohamed","year":"2023","journal-title":"arXiv"},{"key":"ref29","article-title":"On the Optimal Feedback Law in Stochastic Optimal Nonlinear Control","author":"Mohamed","year":"2022","journal-title":"arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310229"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10384307.pdf?arnumber=10384307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:58:12Z","timestamp":1706029092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10384307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10384307","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}