{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T13:04:39Z","timestamp":1725800679012},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"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":[[2020,11,1]]},"DOI":"10.1109\/ieeeconf51394.2020.9443572","type":"proceedings-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T01:32:35Z","timestamp":1622770355000},"page":"579-583","source":"Crossref","is-referenced-by-count":2,"title":["Distributed Hybrid Kalman Temporal Differences for Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Mohammad","family":"Salimibeni","sequence":"first","affiliation":[{"name":"Concordia University,Concordia Institute for Information Systems Engineering,Montreal,QC,Canada"}]},{"given":"Parvin","family":"Malekzadeh","sequence":"additional","affiliation":[{"name":"University of Toronto,Department of Electrical and Computer Engineering,Toronto,ON,Canada"}]},{"given":"Arash","family":"Mohammadi","sequence":"additional","affiliation":[{"name":"Concordia University,Concordia Institute for Information Systems Engineering,Montreal,QC,Canada"}]},{"given":"Konstantinos N.","family":"Plataniotis","sequence":"additional","affiliation":[{"name":"University of Toronto,Department of Electrical and Computer Engineering,Toronto,ON,Canada"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2436064"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2718964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2853572"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10284"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1970.1099422"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2945402"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2724848"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CIC.2017.00017"},{"key":"ref10","article-title":"Temporal Difference Based Actor Critic Learning - Convergence and Neural Implementation","author":"castro","year":"2008","journal-title":"Neural Information Processing Systems Conference"},{"key":"ref11","first-page":"257","article-title":"Curse of Dimensionality","author":"keogh","year":"2011","journal-title":"Encyclopedia of Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"article-title":"Playing Atari with Deep Reinforcement Learning","year":"2013","author":"mnih","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2940445"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2967509"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932257"},{"article-title":"Continuous Control with Deep Reinforcement Learning","year":"2015","author":"lillicrap","key":"ref17"},{"article-title":"Addressing Function Approximation Error in Actor-critic Methods","year":"2018","author":"fujimoto","key":"ref18"},{"article-title":"Soft actor-critic: Offpolicy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","year":"2018","author":"haarnoja","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2247418"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936863"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2961174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815368"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3077"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2973169"},{"article-title":"Agnostic System Identification for Model-based Reinforcement Learning","year":"2012","author":"ross","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007951"},{"key":"ref9","first-page":"833","article-title":"Reinforcement Learning in Continuous Action Spaces Through Sequential Monte Carlo Methods","author":"lazaric","year":"2008","journal-title":"Advances in neural information processing systems"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"journal-title":"Neural Networks A Comprehensive Foundation","year":"1994","author":"haykin","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1997.616132"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/5.58338"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.08.001"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5732-z"},{"journal-title":"Algorithms and Representations for Reinforcement Learning","year":"2005","author":"engel","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-006-8134-8"}],"event":{"name":"2020 54th Asilomar Conference on Signals, Systems, and Computers","start":{"date-parts":[[2020,11,1]]},"location":"Pacific Grove, CA, USA","end":{"date-parts":[[2020,11,4]]}},"container-title":["2020 54th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9443248\/9443268\/09443572.pdf?arnumber=9443572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:58:08Z","timestamp":1659484688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9443572\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,1]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf51394.2020.9443572","relation":{},"subject":[],"published":{"date-parts":[[2020,11,1]]}}}