{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:16:10Z","timestamp":1783106170999,"version":"3.54.6"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:00:00Z","timestamp":1777939200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100025294","name":"Research Ireland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100025294","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001602","name":"Taighde \u00c9ireann - Research Ireland","doi-asserted-by":"publisher","award":["18\/CRT\/6223"],"award-info":[{"award-number":["18\/CRT\/6223"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers and Electrical Engineering"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.compeleceng.2026.111217","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T22:19:44Z","timestamp":1778019584000},"page":"111217","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Effective cross-building transfer learning for HVAC control using deep reinforcement learning and joint action dynamics"],"prefix":"10.1016","volume":"136","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9478-5675","authenticated-orcid":false,"given":"Kevlyn","family":"Kadamala","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Des","family":"Chambers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9876-8717","authenticated-orcid":false,"given":"Enda","family":"Barrett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compeleceng.2026.111217_b1","doi-asserted-by":"crossref","unstructured":"Chen B, Cai Z, Berg\u00e9s M. Gnu-rl: A precocial reinforcement learning solution for building hvac control using a differentiable mpc policy. In: Proceedings of the 6th ACM international conference on systems for energy-efficient buildings, cities, and transportation. 2019, p. 316\u201325.","DOI":"10.1145\/3360322.3360849"},{"key":"10.1016\/j.compeleceng.2026.111217_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2021.117164","article-title":"Experimental evaluation of model-free reinforcement learning algorithms for continuous HVAC control","volume":"298","author":"Biemann","year":"2021","journal-title":"Appl Energy"},{"key":"10.1016\/j.compeleceng.2026.111217_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.egyai.2020.100043","article-title":"Deep reinforcement learning for home energy management system control","volume":"3","author":"Lissa","year":"2021","journal-title":"Energy AI"},{"key":"10.1016\/j.compeleceng.2026.111217_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2022.120598","article-title":"Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings","volume":"333","author":"Coraci","year":"2023","journal-title":"Appl Energy"},{"key":"10.1016\/j.compeleceng.2026.111217_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.egyai.2023.100255","article-title":"Reinforcement learning building control approach harnessing imitation learning","volume":"14","author":"Dey","year":"2023","journal-title":"Energy AI"},{"key":"10.1016\/j.compeleceng.2026.111217_b6","series-title":"Joint European conference on machine learning and knowledge discovery in databases","first-page":"256","article-title":"Enhancing HVAC control efficiency: A hybrid approach using imitation and reinforcement learning","author":"Kadamala","year":"2024"},{"key":"10.1016\/j.compeleceng.2026.111217_b7","series-title":"Building simulation","first-page":"1","article-title":"An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems","author":"Coraci","year":"2024"},{"key":"10.1016\/j.compeleceng.2026.111217_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2024.114696","article-title":"Multi-source transfer learning method for enhancing the deployment of deep reinforcement learning in multi-zone building HVAC control","volume":"322","author":"Hou","year":"2024","journal-title":"Energy Build"},{"key":"10.1016\/j.compeleceng.2026.111217_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.segy.2024.100131","article-title":"Enhancing HVAC control systems through transfer learning with deep reinforcement learning agents","author":"Kadamala","year":"2024","journal-title":"Smart Energy"},{"key":"10.1016\/j.compeleceng.2026.111217_b10","doi-asserted-by":"crossref","unstructured":"Xu S, Wang Y, Wang Y, O\u2019Neill Z, Zhu Q. One for many: Transfer learning for building hvac control. In: Proceedings of the 7th ACM international conference on systems for energy-efficient buildings, cities, and transportation. 2020, p. 230\u20139.","DOI":"10.1145\/3408308.3427617"},{"key":"10.1016\/j.compeleceng.2026.111217_b11","series-title":"2015 international joint conference on neural networks","first-page":"1","article-title":"Faster reinforcement learning after pretraining deep networks to predict state dynamics","author":"Anderson","year":"2015"},{"issue":"19","key":"10.1016\/j.compeleceng.2026.111217_b12","doi-asserted-by":"crossref","first-page":"19160","DOI":"10.1109\/JIOT.2022.3164023","article-title":"MBRL-MC: An HVAC control approach via combining model-based deep reinforcement learning and model predictive control","volume":"9","author":"Chen","year":"2022","journal-title":"IEEE Internet Things J"},{"key":"10.1016\/j.compeleceng.2026.111217_b13","article-title":"A safe and data-efficient model-based reinforcement learning system for HVAC control","author":"Ding","year":"2025","journal-title":"IEEE Internet Things J"},{"key":"10.1016\/j.compeleceng.2026.111217_b14","first-page":"12686","article-title":"Pretraining representations for data-efficient reinforcement learning","volume":"34","author":"Schwarzer","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.compeleceng.2026.111217_b15","series-title":"International conference on machine learning","first-page":"19561","article-title":"Reinforcement learning with action-free pre-training from videos","author":"Seo","year":"2022"},{"key":"10.1016\/j.compeleceng.2026.111217_b16","doi-asserted-by":"crossref","unstructured":"Zhang C, Kuppannagari SR, Kannan R, Prasanna VK. Building HVAC scheduling using reinforcement learning via neural network based model approximation. In: Proceedings of the 6th ACM international conference on systems for energy-efficient buildings, cities, and transportation. 2019, p. 287\u201396.","DOI":"10.1145\/3360322.3360861"},{"key":"10.1016\/j.compeleceng.2026.111217_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.egyai.2025.100531","article-title":"Improving HVAC control with transfer learning: Using padding techniques for cross-building pre-training and fine-tuning","volume":"21","author":"Kadamala","year":"2025","journal-title":"Energy AI","ISSN":"https:\/\/id.crossref.org\/issn\/2666-5468","issn-type":"print"},{"key":"10.1016\/j.compeleceng.2026.111217_b18","series-title":"Machine learning and knowledge discovery in databases: European conference, ECML pKDD 2015, porto, Portugal, September 7-11, 2015, proceedings, part III 15","first-page":"3","article-title":"Autonomous hvac control, a reinforcement learning approach","author":"Barrett","year":"2015"},{"key":"10.1016\/j.compeleceng.2026.111217_b19","series-title":"2015 IEEE international conference on automation science and engineering","first-page":"444","article-title":"A multi-grid reinforcement learning method for energy conservation and comfort of HVAC in buildings","author":"Li","year":"2015"},{"key":"10.1016\/j.compeleceng.2026.111217_b20","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.compeleceng.2019.07.019","article-title":"A review of reinforcement learning for autonomous building energy management","volume":"78","author":"Mason","year":"2019","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.compeleceng.2026.111217_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2020.110225","article-title":"Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings","volume":"224","author":"Brandi","year":"2020","journal-title":"Energy Build"},{"key":"10.1016\/j.compeleceng.2026.111217_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2021.118346","article-title":"Reinforced model predictive control (RL-MPC) for building energy management","volume":"309","author":"Arroyo","year":"2022","journal-title":"Appl Energy"},{"key":"10.1016\/j.compeleceng.2026.111217_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2024.114065","article-title":"Modelling building HVAC control strategies using a deep reinforcement learning approach","volume":"310","author":"Nguyen","year":"2024","journal-title":"Energy Build"},{"issue":"7","key":"10.1016\/j.compeleceng.2026.111217_b24","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/s10462-024-10819-x","article-title":"An experimental evaluation of deep reinforcement learning algorithms for HVAC control","volume":"57","author":"Manjavacas","year":"2024","journal-title":"Artif Intell Rev"},{"key":"10.1016\/j.compeleceng.2026.111217_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2024.115075","article-title":"Sinergym\u2013A virtual testbed for building energy optimization with reinforcement learning","volume":"327","author":"Campoy-Nieves","year":"2025","journal-title":"Energy Build"},{"issue":"11","key":"10.1016\/j.compeleceng.2026.111217_b26","doi-asserted-by":"crossref","first-page":"13344","DOI":"10.1109\/TPAMI.2023.3292075","article-title":"Transfer learning in deep reinforcement learning: A survey","volume":"45","author":"Zhu","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"10.1016\/j.compeleceng.2026.111217_b27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s42979-020-00146-7","article-title":"Transfer learning applied to reinforcement learning-based hvac control","volume":"1","author":"Lissa","year":"2020","journal-title":"SN Comput Sci"},{"key":"10.1016\/j.compeleceng.2026.111217_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.buildenv.2019.106535","article-title":"Towards optimal control of air handling units using deep reinforcement learning and recurrent neural network","volume":"168","author":"Zou","year":"2020","journal-title":"Build Environ"},{"key":"10.1016\/j.compeleceng.2026.111217_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.enconman.2023.117303","article-title":"Effective pre-training of a deep reinforcement learning agent by means of long short-term memory models for thermal energy management in buildings","volume":"291","author":"Coraci","year":"2023","journal-title":"Energy Convers Manage"},{"key":"10.1016\/j.compeleceng.2026.111217_b30","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.compeleceng.2026.111217_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2025.115511","article-title":"Practical deployment of reinforcement learning for building controls using an imitation learning approach","volume":"335","author":"Silvestri","year":"2025","journal-title":"Energy Build"},{"key":"10.1016\/j.compeleceng.2026.111217_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2024.115254","article-title":"A scalable approach for real-world implementation of deep reinforcement learning controllers in buildings based on online transfer learning: The hilo case study","volume":"329","author":"Coraci","year":"2025","journal-title":"Energy Build"},{"key":"10.1016\/j.compeleceng.2026.111217_b33","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.jobe.2017.06.013","article-title":"NEST HiLo: Investigating lightweight construction and adaptive energy systems","volume":"12","author":"Block","year":"2017","journal-title":"J Build Eng"},{"key":"10.1016\/j.compeleceng.2026.111217_b34","doi-asserted-by":"crossref","unstructured":"Zhang X, Jin X, Tripp C, Biagioni DJ, Graf P, Jiang H. Transferable reinforcement learning for smart homes. In: Proceedings of the 1st international workshop on reinforcement learning for energy management in buildings & cities. 2020, p. 43\u20137.","DOI":"10.1145\/3427773.3427865"},{"key":"10.1016\/j.compeleceng.2026.111217_b35","doi-asserted-by":"crossref","first-page":"66953","DOI":"10.52202\/075280-2925","article-title":"Inverse dynamics pretraining learns good representations for multitask imitation","volume":"36","author":"Brandfonbrener","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.compeleceng.2026.111217_b36","series-title":"Finetuning offline world models in the real world","author":"Feng","year":"2023"},{"key":"10.1016\/j.compeleceng.2026.111217_b37","series-title":"European conference on computer vision","first-page":"185","article-title":"PreLAR: World model pre-training with learnable action representation","author":"Zhang","year":"2024"},{"issue":"4","key":"10.1016\/j.compeleceng.2026.111217_b38","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1561\/2200000056","article-title":"An introduction to variational autoencoders","volume":"12","author":"Kingma","year":"2019","journal-title":"Found Trends\u00ae Mach Learn"},{"key":"10.1016\/j.compeleceng.2026.111217_b39","doi-asserted-by":"crossref","unstructured":"Ramrakhya R, Batra D, Wijmans E, Das A. Pirlnav: Pretraining with imitation and rl finetuning for objectnav. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023, p. 17896\u2013906.","DOI":"10.1109\/CVPR52729.2023.01716"},{"issue":"1","key":"10.1016\/j.compeleceng.2026.111217_b40","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1080\/1350486042000271638","article-title":"Stochastic modelling of temperature variations with a view towards weather derivatives","volume":"12","author":"Benth","year":"2005","journal-title":"Appl Math Finance"},{"key":"10.1016\/j.compeleceng.2026.111217_b41","series-title":"International conference on machine learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.compeleceng.2026.111217_b42","series-title":"International conference on machine learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"issue":"274","key":"10.1016\/j.compeleceng.2026.111217_b43","first-page":"1","article-title":"Cleanrl: High-quality single-file implementations of deep reinforcement learning algorithms","volume":"23","author":"Huang","year":"2022","journal-title":"J Mach Learn Res"},{"issue":"7","key":"10.1016\/j.compeleceng.2026.111217_b44","article-title":"Transfer learning for reinforcement learning domains: A survey.","volume":"10","author":"Taylor","year":"2009","journal-title":"J Mach Learn Res"}],"container-title":["Computers and Electrical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0045790626002892?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0045790626002892?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:20:28Z","timestamp":1783102828000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0045790626002892"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":44,"alternative-id":["S0045790626002892"],"URL":"https:\/\/doi.org\/10.1016\/j.compeleceng.2026.111217","relation":{},"ISSN":["0045-7906"],"issn-type":[{"value":"0045-7906","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Effective cross-building transfer learning for HVAC control using deep reinforcement learning and joint action dynamics","name":"articletitle","label":"Article Title"},{"value":"Computers and Electrical Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compeleceng.2026.111217","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"111217"}}