{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:09:30Z","timestamp":1767262170250,"version":"3.37.3"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009360","name":"King\u2019s College London","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100009360","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. II"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/tcsii.2019.2947682","type":"journal-article","created":{"date-parts":[[2019,10,16]],"date-time":"2019-10-16T20:23:23Z","timestamp":1571257403000},"page":"2059-2063","source":"Crossref","is-referenced-by-count":12,"title":["Reinforcement Learning-Based Control of Nonlinear Systems Using Lyapunov Stability Concept and Fuzzy Reward Scheme"],"prefix":"10.1109","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3404-9278","authenticated-orcid":false,"given":"Ming","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6572-7265","authenticated-orcid":false,"given":"Hak Keung","family":"Lam","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4623-0576","authenticated-orcid":false,"given":"Qian","family":"Shi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9361-4340","authenticated-orcid":false,"given":"Bo","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/sym11020290"},{"key":"ref12","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2777827"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905621"},{"journal-title":"PPO-CMA Proximal Policy Optimization With Covariance Matrix Adaptation","year":"2018","author":"h\u00e4m\u00e4l\u00e4inen","key":"ref16"},{"key":"ref17","first-page":"1394","article-title":"Adaptive step-size for policy gradient methods","author":"pirotta","year":"2013","journal-title":"Advances in Neural Information Processing Systems 26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2868859"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/17512549.2017.1314832"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2019.2896591"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2018.2890654"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2417170"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref5"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"article-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665111"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2016.2554153"},{"journal-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"schulman","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2019.2907503"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2019.2938781"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2017.09.007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1049\/trit.2018.1007"}],"container-title":["IEEE Transactions on Circuits and Systems II: Express Briefs"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8920\/9204872\/08871158.pdf?arnumber=8871158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T16:53:28Z","timestamp":1651078408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8871158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":25,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsii.2019.2947682","relation":{},"ISSN":["1549-7747","1558-3791"],"issn-type":[{"type":"print","value":"1549-7747"},{"type":"electronic","value":"1558-3791"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}