{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:21:06Z","timestamp":1752229266897,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61473253"],"award-info":[{"award-number":["61473253"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities of China","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Natural Science Foundation of China through Foundation for Innovative Research Groups","award":["61621002"],"award-info":[{"award-number":["61621002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1109\/tnnls.2018.2844466","type":"journal-article","created":{"date-parts":[[2018,7,2]],"date-time":"2018-07-02T23:11:44Z","timestamp":1530573104000},"page":"464-473","source":"Crossref","is-referenced-by-count":10,"title":["Hierarchical Decision and Control for Continuous Multitarget Problem: Policy Evaluation With Action Delay"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6610-721X","authenticated-orcid":false,"given":"Jiangcheng","family":"Zhu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2304-3671","authenticated-orcid":false,"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Zhepei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shan","family":"Guo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2759-6364","authenticated-orcid":false,"given":"Chao","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1609\/icaps.v26i1.13789","article-title":"Real-time stochastic optimal control for multi-agent quadrotor systems","author":"g\u00f3mez","year":"2016","journal-title":"Proc Int Conf Autom Planning Scheduling"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref10"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1109\/TNNLS.2013.2292704","article-title":"Reinforcement learning output feedback NN control using deterministic learning technique","volume":"25","author":"xu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"journal-title":"End to End Learning for Self-Driving Cars","year":"2016","author":"bojarski","key":"ref13"},{"journal-title":"End-to-end driving via conditional imitation learning","year":"2017","author":"codevilla","key":"ref14"},{"journal-title":"Reinforcement learning with unsupervised auxiliary tasks","year":"2016","author":"jaderberg","key":"ref15"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref18","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","volume":"19","author":"abbeel","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1991.131810"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/1729881417717702"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.883869"},{"key":"ref27","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"melo","year":"2001"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","article-title":"Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers","volume":"32","author":"lewis","year":"2012","journal-title":"IEEE Control Syst"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2005\/11\/P11011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref8"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref9","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2004.840124"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1063\/1.2709596","article-title":"An introduction to stochastic control theory, path integrals and reinforcement learning","volume":"887","author":"kappen","year":"2007","journal-title":"Proc AIP Conf"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980409"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.678"},{"key":"ref23","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref26","first-page":"231","article-title":"Law of large numbers for identically distributed variables","volume":"2","author":"feller","year":"1971","journal-title":"An Introduction to Probability Theory and Its Applications"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8621620\/08401524.pdf?arnumber=8401524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T13:37:46Z","timestamp":1693748266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8401524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":30,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2018.2844466","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2019,2]]}}}