{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T03:00:41Z","timestamp":1783479641743,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100011535","name":"Missouri University of Science and Technology Intelligent Systems Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011535","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Mary K. Finley Missouri Endowment"},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Lifelong Learning Machines program from DARPA\/Microsystems Technology Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory (ARL)","doi-asserted-by":"crossref","award":["W911NF-18-2-0260"],"award-info":[{"award-number":["W911NF-18-2-0260"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Basra Oil Company (BOC), Iraq"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/tnnls.2019.2919614","type":"journal-article","created":{"date-parts":[[2019,6,25]],"date-time":"2019-06-25T20:16:05Z","timestamp":1561493765000},"page":"1255-1269","source":"Crossref","is-referenced-by-count":30,"title":["Online Model-Free <i>n<\/i>-Step HDP With Stability Analysis"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5200-7587","authenticated-orcid":false,"given":"Seaar","family":"Al-Dabooni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9726-9051","authenticated-orcid":false,"given":"Donald C.","family":"Wunsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"2038","DOI":"10.1109\/TNNLS.2013.2271454","article-title":"Goal representation heuristic dynamic programming on maze navigation","volume":"24","author":"ni","year":"2013","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.06.001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2875870"},{"key":"ref30","first-page":"692","article-title":"True online TD (\n$\\lambda$\n)","author":"seijen","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/9781118025604"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2015.2505327"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2009.5178812"},{"key":"ref27","first-page":"1847","article-title":"Ramp metering based on on-line ADHDP (\n$\\lambda$\n) controller","author":"bai","year":"2008","journal-title":"Proc IEEE Int Joint Con Neural Netw (IJCNN)"},{"key":"ref29","first-page":"1","article-title":"An emphatic approach to the problem of off-policy temporal-difference learning","volume":"73","author":"sutton","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2490698"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966204"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2019.2912349"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927521"},{"key":"ref23","author":"sutton","year":"2018","journal-title":"Reinforcement Learning&#x2014;An Introduction"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref25","first-page":"4535","article-title":"Heuristic dynamic programming strategy with eligibility traces","author":"li","year":"2008","journal-title":"Proc IEEE Amer Control Conf"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2003.809438"},{"key":"ref11","first-page":"248","article-title":"A comparison of dual heuristic programming (DHP) and neural network based stochastic optimization approach on collective robotic search problem","volume":"1","author":"zhang","year":"2003","journal-title":"Proc Int Joint Conf Neural Netw"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref12","first-page":"576","article-title":"Motion planning of wheeled mobile robots based on heuristic dynamic programming","author":"lian","year":"2014","journal-title":"Proc IEEE World Congr Intell Control Autom (WCICA)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727679"},{"key":"ref14","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref15","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"arXiv 1708 04782"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref17","first-page":"1","article-title":"True Online Temporal-Difference Learning","volume":"145","author":"seijen","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252791"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/9781118453988.ch7"},{"key":"ref4","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref3","article-title":"Approximate dynamic programming for real-time control and neural modeling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control Neural Fuzzy and Adaptive Approaches"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2424971"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.04.014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.05.031"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2329942"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2000.861284"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.1996.565374"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2016.2595580"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2000396"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3182\/20060517-3-FR-2903.00330"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(98)00051-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2283574"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1086\/209106"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9056859\/8745529-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9056859\/08745529.pdf?arnumber=8745529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:19:34Z","timestamp":1651079974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8745529\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":49,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2919614","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}