{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:23:20Z","timestamp":1783614200537,"version":"3.55.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"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":["IEEE Trans. Emerg. Topics Comput."],"published-print":{"date-parts":[[2021,4,1]]},"DOI":"10.1109\/tetc.2018.2890682","type":"journal-article","created":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T19:51:46Z","timestamp":1546372306000},"page":"972-982","source":"Crossref","is-referenced-by-count":11,"title":["An Experience Replay Method Based on Tree Structure for Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4432-8801","authenticated-orcid":false,"given":"WEI-CHENG","family":"JIANG","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9234-4836","authenticated-orcid":false,"given":"KAO-SHING","family":"HWANG","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JIN-LING","family":"LIN","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509181"},{"key":"ref11","first-page":"717","article-title":"Generalized model learning for reinforcement learning in factored domains","author":"hester","year":"0","journal-title":"Proc 8th Int Conf Auton Agents Multiagent Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-2598-0_49"},{"key":"ref13","first-page":"101","article-title":"Model-based reinforcement learning with an approximate, learned model","author":"kuvayev","year":"0","journal-title":"Proc 9th Yale Workshop Adapt Learn Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2011.09.008"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref16","first-page":"283","article-title":"Extended dyna-Q algorithm for path planning of mobile robots","volume":"2","author":"viet","year":"2011","journal-title":"Meas Sci Instrum"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2012.754074"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329241"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/AERO.2005.1559688"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2294155"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2012.6266001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2647993"},{"key":"ref6","first-page":"769","article-title":"Tree based discretization for continuous state space reinforcement learning","author":"uther","year":"0","journal-title":"Proc 15th Nat Conf Artif Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.06.009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2014.2316518"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_4"},{"key":"ref7","first-page":"70","article-title":"Decision tree function approximation in reinforcement learning","author":"pyeatt","year":"2001","journal-title":"Proc 3rd Int Symp Adaptive Syst Evol Comput Probabilistic Graphical Models"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2186565"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5455\/jjcit.71-1480540385"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2007.907738"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.06.016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2018.2805718"},{"key":"ref21","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc Association for the Advancement of Artificial Intelligence"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.1600317WC"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2011.02.017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"}],"container-title":["IEEE Transactions on Emerging Topics in Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245516\/9447283\/08598780.pdf?arnumber=8598780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:52Z","timestamp":1652194432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8598780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,1]]},"references-count":29,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tetc.2018.2890682","relation":{},"ISSN":["2168-6750","2376-4562"],"issn-type":[{"value":"2168-6750","type":"electronic"},{"value":"2376-4562","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,1]]}}}