{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:59:05Z","timestamp":1764784745035,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561001","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"8104-8110","source":"Crossref","is-referenced-by-count":4,"title":["Data-based Control of Partially-Observed Robotic Systems"],"prefix":"10.1109","author":[{"given":"Ran","family":"Wang","sequence":"first","affiliation":[{"name":"Texas A&M University,Department of Aerospace Engineering,Texas,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raman","family":"Goyal","sequence":"additional","affiliation":[{"name":"Texas A&M University,Department of Aerospace Engineering,Texas,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suman","family":"Chakravorty","sequence":"additional","affiliation":[{"name":"Texas A&M University,Department of Aerospace Engineering,Texas,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert E.","family":"Skelton","sequence":"additional","affiliation":[{"name":"Texas A&M University,Department of Aerospace Engineering,Texas,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"john","key":"ref10"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref12","article-title":"Decoupled data based approach for learning to control nonlinear dynamical systems","author":"wang","year":"2019","journal-title":"arXiv also IEEE Transactions on Automatic Control (to appear)"},{"key":"ref13","volume":"734","author":"box","year":"2011","journal-title":"Time Series Analysis Forecasting and Control"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1108\/15265940610712678"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/0020718508961129"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/0020718508961129"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/9.867047"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690390308"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264294"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref4"},{"key":"ref3","volume":"2","author":"bertsekas","year":"2012","journal-title":"Dynamic Programming and Optimal Control"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref6"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","year":"2017","author":"yuhuai","key":"ref8"},{"key":"ref7","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"journal-title":"Robust Adaptive Control","year":"2012","author":"ioannou","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974263"},{"article-title":"Trust region policy optimization","year":"2017","author":"john","key":"ref9"},{"journal-title":"Applied Optimal Control Optimization Estimation and Control","year":"1975","author":"bryson","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979891"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561001.pdf?arnumber=9561001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:49:19Z","timestamp":1673563759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561001","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}