{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T14:01:43Z","timestamp":1760623303367,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"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":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161189","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"10247-10253","source":"Crossref","is-referenced-by-count":8,"title":["A Continuous Off-Policy Reinforcement Learning Scheme for Optimal Motion Planning in Simply-Connected Workspaces"],"prefix":"10.1109","author":[{"given":"Panagiotis","family":"Rousseas","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Control Systems Laboratory, National Technical University of Athens,Greece"}]},{"given":"Charalampos P.","family":"Bechlioulis","sequence":"additional","affiliation":[{"name":"University of Patras,Department of Electrical and Computer Engineering"}]},{"given":"Kostas J.","family":"Kyriakopoulos","sequence":"additional","affiliation":[{"name":"Center of AI & Robotics (CAIR), New York University,Abu Dhabi"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1991.131683"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206505"},{"key":"ref34","first-page":"779","volume":"41","author":"abu-khalaf","year":"2005","journal-title":"Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460695"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6161438"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"journal-title":"Reinforcement Learning and Optimal Adaptive Control","first-page":"461","year":"2012","key":"ref30"},{"journal-title":"Long-range indoor navigation with prm-rl","year":"2020","author":"francis","key":"ref11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/S1570-579X(06)80010-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.2973327"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2421338"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/70.163777"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(90)90017-S"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143308"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2970640"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/70.563653"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060711"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341148"},{"key":"ref26","first-page":"102","article-title":"Contributions to the theory of optimal control","volume":"5","author":"kalman","year":"1960","journal-title":"de la Sociedad MatematicaMexicana"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3178788"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRoM.2015.7367873"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01867-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2000.870304"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2008.4738955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2987397"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2016.071114"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-061920-093753"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161103"},{"key":"ref3","first-page":"24","article-title":"A comparative study of a-star algorithms for search and rescue in perfect maze","author":"liu","year":"0","journal-title":"International Conference on Electric Information and Control Engineering"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161189.pdf?arnumber=10161189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:30:16Z","timestamp":1690219816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161189","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}