{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T05:53:18Z","timestamp":1769925198439,"version":"3.49.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"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. Artif. Intell."],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1109\/tai.2021.3125918","type":"journal-article","created":{"date-parts":[[2021,11,11]],"date-time":"2021-11-11T15:31:23Z","timestamp":1636644683000},"page":"581-594","source":"Crossref","is-referenced-by-count":22,"title":["Multiadvisor Reinforcement Learning for Multiagent Multiobjective Smart Home Energy Control"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3654-1952","authenticated-orcid":false,"given":"Andrew","family":"Tittaferrante","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Lakehead University, Thunder Bay, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3539-0945","authenticated-orcid":false,"given":"Abdulsalam","family":"Yassine","sequence":"additional","affiliation":[{"name":"Software Engineering Department, Lakehead University, Thunder Bay, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2017.2692098"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2016.2520639"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","article-title":"Multi-advisor reinforcement learning","author":"Laroche","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2879572"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTGRID.2010.5622078"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2396993"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2014.2388357"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2971427"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2004.1380068"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2909266"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2517211"},{"key":"ref15","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"Ernst","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2834219"},{"key":"ref17","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. 12th Int. Conf. Neural Inf. Process. Syst.","author":"Sutton","year":"1999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SMDS49396.2020.00018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23461-8_1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISGT45199.2020.9087647"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3042498"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2924030"},{"key":"ref24","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref26","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref27","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref28","article-title":"Top games awarding prize moneyEsports game rankings","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref30","article-title":"Multi-objective deep reinforcement learning","author":"Mossalam","year":"2016"},{"key":"ref31","first-page":"5392","article-title":"Hybrid reward architecture for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Seijen","year":"2017"},{"key":"ref32","first-page":"656","article-title":"Q-decomposition for reinforcement learning agents","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Russell","year":"2003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HONET.2019.8907970"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SEGE49949.2020.9181985"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2445491"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2552169"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0305-0548(91)90013-H"},{"key":"ref38","first-page":"807","article-title":"All learning is local: Multi-agent learning in global reward games","volume-title":"Proc. 16th Int. Conf. Neural Inf. Process. Syst.","author":"Chang","year":"2004"},{"key":"ref39","volume-title":"On-line Q-Learning using Connectionist Systems","volume":"37","author":"Rummery","year":"1994"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref42","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref43","first-page":"2827","article-title":"Neural episodic control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pritzel","year":"2017"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/9834985\/09612064.pdf?arnumber=9612064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:10:05Z","timestamp":1755911405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9612064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8]]},"references-count":43,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tai.2021.3125918","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8]]}}}