{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T11:15:38Z","timestamp":1784632538862,"version":"3.55.0"},"reference-count":130,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"15","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFB1312"],"award-info":[{"award-number":["2019YFB1312"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFA0702200"],"award-info":[{"award-number":["2018YFA0702200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972214"],"award-info":[{"award-number":["61972214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61822309"],"award-info":[{"award-number":["61822309"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773310"],"award-info":[{"award-number":["61773310"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Basic Research Project of Leading Technology of Jiangsu Province","award":["BK20202011"],"award-info":[{"award-number":["BK20202011"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2020M673406"],"award-info":[{"award-number":["2020M673406"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005374","name":"1311 Talent Project of Nanjing University of Posts and Telecommunications","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2021,8,1]]},"DOI":"10.1109\/jiot.2021.3078462","type":"journal-article","created":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T22:14:41Z","timestamp":1620684881000},"page":"12046-12063","source":"Crossref","is-referenced-by-count":422,"title":["A Review of Deep Reinforcement Learning for Smart Building Energy Management"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5015-0320","authenticated-orcid":false,"given":"Liang","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3621-8039","authenticated-orcid":false,"given":"Shuqi","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8482-1046","authenticated-orcid":false,"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2712560"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3014055"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref31","author":"shao","year":"2019","journal-title":"A Survey of Deep Reinforcement Learning in Video Games"},{"key":"ref30","author":"schrittwieser","year":"2020","journal-title":"Mastering atari go chess and shogi by planning with a learned model"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/s20072157"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2988367"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2765359"},{"key":"ref29","author":"l","year":"2017","journal-title":"Deep reinforcement learning An overview"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2957289"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3302505.3310069"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3011739"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2019.00920"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2834219"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2019.03.038"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2010.2083705"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.23919\/SICEISCS48470.2020.9083565"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2313736"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/89"},{"key":"ref51","author":"nagy","year":"2018","journal-title":"Deep reinforcement learning for optimal control of space heating"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.07.019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2963502"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2019.101748"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2020.03.001"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2018.00520"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref53","author":"nguyen","year":"2020","journal-title":"Deep reinforcement learning for cyber security"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2871020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216885"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2018.10.028"},{"key":"ref6","year":"2020","journal-title":"The Global Alliance for Buildings and Construction (GABC) The Global Status Report 2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/iet-esi.2019.0019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41560-018-0253-6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3396851.3397694"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2901120"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2926642"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115426"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115473"},{"key":"ref48","first-page":"1","article-title":"Energy management strategy for a hybrid electric vehicle based on deep reinforcemant learning","volume":"8","author":"hu","year":"2018","journal-title":"Appl Sci"},{"key":"ref47","author":"hu","year":"2020","journal-title":"Transforming Thermal Comfort Model and Control in the Tropics A Machine-Learning Approach"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2973193"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2966232"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3042007"},{"key":"ref127","author":"zhu","year":"2020","journal-title":"Transfer Learning in Deep Reinforcement Learning A Survey"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968092"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977661"},{"key":"ref124","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Proc NIPS"},{"key":"ref73","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc ICML"},{"key":"ref72","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"hasselt","year":"2016","journal-title":"Proc AAAI"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3427617"},{"key":"ref71","first-page":"3846","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","author":"gu","year":"2017","journal-title":"Proc NIPS"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006306"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2517211"},{"key":"ref76","first-page":"1","article-title":"Noisy networks for exploration","author":"fortunato","year":"2018","journal-title":"Proc ICLR"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/iSPEC48194.2019.8975202"},{"key":"ref77","first-page":"3215","article-title":"RainBow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proc AAAI"},{"key":"ref74","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc ICLR"},{"key":"ref75","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"Proc ICML"},{"key":"ref78","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"key":"ref79","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc NIPS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115036"},{"key":"ref62","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2991728"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.02.066"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147629"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2989696"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.11.002"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/en12010001"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2977104"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2018.07.007"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2909266"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.113788"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2016.05.067"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2019.00590"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2976771"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2017.12.019"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2978061"},{"key":"ref93","author":"latif","year":"2021","journal-title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2019.02890"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2019.07.029"},{"key":"ref105","author":"kumar","year":"2019","journal-title":"Explainable AI Reinforcement Learning Agents for Residential Cost Savings"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360849"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489210"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2019.106535"},{"key":"ref103","first-page":"1","article-title":"Transferable reinforcement learning for smart homes","author":"zhang","year":"2020","journal-title":"Proc Int Workshop Reinforcement Learn Energy Manag Build"},{"key":"ref102","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360857"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2974848"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2015.01.060"},{"key":"ref98","article-title":"Energy-efficient heating control for smart buildings with deep reinforcement learning","volume":"34","author":"gupta","year":"2021","journal-title":"J Build Eng"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2019.109420"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3024656"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/IIAI-AAI.2019.00120"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2647881"},{"key":"ref11","first-page":"269","article-title":"An IoT-based thermal model learning framework for smart buildings","volume":"4","author":"zhang","year":"2017","journal-title":"IEEE Internet of Things Journal"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2020.106535"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2020.110261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2017.2781639"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2020.109963"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM.2017.8274336"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.114208"},{"key":"ref82","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc ICML"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ISGTEurope.2019.8905731"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2993112"},{"key":"ref81","first-page":"1856","article-title":"Soft actor–critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2992117"},{"key":"ref84","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM40551.2019.8974083"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062224"},{"key":"ref83","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc ICML"},{"key":"ref114","first-page":"1","article-title":"Deep reinforcement learning solutions for energy microgrids management","author":"francois-lavet","year":"2016","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3035127"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.3390\/en12122291"},{"key":"ref80","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proc ICML"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.3390\/en13112830"},{"key":"ref120","author":"lee","year":"2020","journal-title":"Demand-Side Scheduling Based on Deep Actor–Critic Learning for Smart Grids"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3007167"},{"key":"ref121","author":"huang","year":"2021","journal-title":"Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learning"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.3182\/20120823-5-NL-3013.00069"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/2939912.2942355"},{"key":"ref85","first-page":"18","article-title":"The surprising effectiveness of MAPPO in cooperative, multi-agent games","author":"yu","year":"2017","journal-title":"Proc NIPS"},{"key":"ref86","first-page":"465","article-title":"Improving PILCO with Bayesian neural network dynamics models","author":"gal","year":"2016","journal-title":"Proc ICML Workshop Data Efficient Mach Learn"},{"key":"ref87","author":"ha","year":"2018","journal-title":"World Models"},{"key":"ref88","author":"schrittwieser","year":"2020","journal-title":"Mastering atari go chess and shogi by planning with a learned model"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9493570\/09426901.pdf?arnumber=9426901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:48Z","timestamp":1652194428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9426901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,1]]},"references-count":130,"journal-issue":{"issue":"15"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2021.3078462","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,1]]}}}