{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T02:53:32Z","timestamp":1768877612281,"version":"3.49.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 107-2221-E-194-043"],"award-info":[{"award-number":["MOST 107-2221-E-194-043"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1109\/tcds.2019.2926477","type":"journal-article","created":{"date-parts":[[2019,10,3]],"date-time":"2019-10-03T18:18:47Z","timestamp":1570126727000},"page":"474-485","source":"Crossref","is-referenced-by-count":5,"title":["Policy Sharing Using Aggregation Trees for ${Q}$ -Learning in a Continuous State and Action Spaces"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0288-0796","authenticated-orcid":false,"given":"Yu-Jen","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4432-8801","authenticated-orcid":false,"given":"Wei-Cheng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6765-6598","authenticated-orcid":false,"given":"Ming-Yi","family":"Ju","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9234-4836","authenticated-orcid":false,"given":"Kao-Shing","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","first-page":"815","article-title":"Split selection methods for classification trees","volume":"7","author":"loh","year":"1997","journal-title":"Statistica Sinica"},{"key":"ref31","first-page":"70","article-title":"Decision tree function approximation in reinforcement learning","author":"pyeatt","year":"2001","journal-title":"Proc 3rd Int Symp Adapt Syst Evol Comput Probab Graph Models"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CLADE.2005.1520907"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2787738"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref12","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","author":"sutton","year":"1996","journal-title":"Proc Adv Neural Inf Process Syst 8"},{"key":"ref13","first-page":"1","article-title":"Q-learning in multi-agent cooperation","author":"hwang","year":"2008","journal-title":"Proc IEEE Int Workshop Adv Robot Social Impacts (ARSO)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.416"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2011.02.017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90056-Q"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2003.811112"},{"key":"ref18","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents","author":"tan","year":"1993","journal-title":"Proc 10th Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2418321"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.881047"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2012.2227719"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2008.921543"},{"key":"ref6","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.45.4.560"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790981"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-585-33656-5_4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.921000"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2570255"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCID.2008.179"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1163\/156855301317198142"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.883264"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/3477.979961"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2013.01.008"},{"key":"ref23","first-page":"56","article-title":"Bat Q-learning algorithm","volume":"3","author":"abed-alguni","year":"2017","journal-title":"Jordanian J Comput Inf Technol"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(02)00381-0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281990"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/9188029\/08755270.pdf?arnumber=8755270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T12:35:49Z","timestamp":1651062949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8755270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":32,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2019.2926477","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9]]}}}