{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:29:52Z","timestamp":1759937392915,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:00:00Z","timestamp":1656374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["ALLRP 561116 - 20"],"award-info":[{"award-number":["ALLRP 561116 - 20"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,28]]},"DOI":"10.1145\/3538637.3539615","type":"proceedings-article","created":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T16:33:05Z","timestamp":1655915585000},"page":"556-564","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Diversity for transfer in learning-based control of buildings"],"prefix":"10.1145","author":[{"given":"Tianyu","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}]},{"given":"Aakash Krishna G","family":"S","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}]},{"given":"Mohammad","family":"Afshari","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}]},{"given":"Petr","family":"Musilek","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}]},{"given":"Matthew E.","family":"Taylor","sequence":"additional","affiliation":[{"name":"University of Alberta & Alberta, Edmonton, Canada"}]},{"given":"Omid","family":"Ardakanian","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}]}],"member":"320","published-online":{"date-parts":[[2022,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. Buildings: A source of enormous untapped efficiency potential. https:\/\/www.iea.org\/topics\/buildings. Accessed: 2022-04-01.  [n.d.]. Buildings: A source of enormous untapped efficiency potential. https:\/\/www.iea.org\/topics\/buildings. Accessed: 2022-04-01."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2018.09.033"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.02.003"},{"key":"e_1_3_2_1_4_1","volume-title":"Multi-agent reinforcement learning: An overview. Innovations in multi-agent systems and applications-1","author":"Bu\u015foniu Lucian","year":"2010","unstructured":"Lucian Bu\u015foniu , Robert Babu\u0161ka , and Bart De Schutter . 2010. Multi-agent reinforcement learning: An overview. Innovations in multi-agent systems and applications-1 ( 2010 ), 183--221. Lucian Bu\u015foniu, Robert Babu\u0161ka, and Bart De Schutter. 2010. Multi-agent reinforcement learning: An overview. Innovations in multi-agent systems and applications-1 (2010), 183--221."},{"key":"e_1_3_2_1_5_1","unstructured":"Jie Cai. 2015. A low cost multi-agent control approach for building energy system management. (2015).  Jie Cai. 2015. A low cost multi-agent control approach for building energy system management. (2015)."},{"volume-title":"Proceedings of the Twelfth ACM International Conference on Future Energy Systems. ACM, 199--210","author":"Bingqing","key":"e_1_3_2_1_6_1","unstructured":"Bingqing Chen et al. 2021. Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization . In Proceedings of the Twelfth ACM International Conference on Future Energy Systems. ACM, 199--210 . Bingqing Chen et al. 2021. Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization. In Proceedings of the Twelfth ACM International Conference on Future Energy Systems. ACM, 199--210."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360849"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-7788(00)00114-6"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2010.06.011"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1711518.1711598"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2020.09.001"},{"volume-title":"International Conference on Learning Representations.","author":"Benjamin","key":"e_1_3_2_1_12_1","unstructured":"Benjamin Eysenbach et al. 2019. Diversity is All You Need: Learning Skills without a Reward Function . In International Conference on Learning Representations. Benjamin Eysenbach et al. 2019. Diversity is All You Need: Learning Skills without a Reward Function. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2021.108519"},{"key":"e_1_3_2_1_14_1","volume-title":"A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy. arXiv preprint arXiv:2012.04283","author":"Fontaine Matthew","year":"2020","unstructured":"Matthew Fontaine and Stefanos Nikolaidis . 2020. A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy. arXiv preprint arXiv:2012.04283 ( 2020 ). Matthew Fontaine and Stefanos Nikolaidis. 2020. A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy. arXiv preprint arXiv:2012.04283 (2020)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.1993.348229"},{"key":"e_1_3_2_1_16_1","unstructured":"Rosenberg Goel et al. 2014. Enhancements to ASHRAE standard 90.1 prototype building models. Technical Report. Pacific Northwest National Lab.(PNNL) Richland WA (United States).  Rosenberg Goel et al. 2014. Enhancements to ASHRAE standard 90.1 prototype building models. Technical Report. Pacific Northwest National Lab.(PNNL) Richland WA (United States)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2021.110836"},{"volume-title":"2017 American Control Conference (ACC). IEEE, 37--43","author":"Xiaodong","key":"e_1_3_2_1_18_1","unstructured":"Xiaodong Hou et al. 2017. Distributed model predictive control via proximal Jacobian ADMM for building control applications . In 2017 American Control Conference (ACC). IEEE, 37--43 . Xiaodong Hou et al. 2017. Distributed model predictive control via proximal Jacobian ADMM for building control applications. In 2017 American Control Conference (ACC). IEEE, 37--43."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Max Jaderberg et al. 2019. Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science 364 6443 (2019) 859--865.  Max Jaderberg et al. 2019. Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science 364 6443 (2019) 859--865.","DOI":"10.1126\/science.aau6249"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Laura Klein et al. 2012. Coordinating occupant behavior for building energy and comfort management using multi-agent systems. Automation in construction 22 (2012) 525--536.  Laura Klein et al. 2012. Coordinating occupant behavior for building energy and comfort management using multi-agent systems. Automation in construction 22 (2012) 525--536.","DOI":"10.1016\/j.autcon.2011.11.012"},{"key":"e_1_3_2_1_21_1","unstructured":"Ksenia Konyushova et al. 2021. Active offline policy selection. Advances in Neural Information Processing Systems 34 (2021).  Ksenia Konyushova et al. 2021. Active offline policy selection. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_1_22_1","first-page":"1179","article-title":"Conservative Q-Learning for Offline Reinforcement Learning","volume":"33","author":"Aviral Kumar","year":"2020","unstructured":"Aviral Kumar et al. 2020 . Conservative Q-Learning for Offline Reinforcement Learning . Advances in Neural Information Processing Systems 33 (2020), 1179 -- 1191 . Aviral Kumar et al. 2020. Conservative Q-Learning for Offline Reinforcement Learning. Advances in Neural Information Processing Systems 33 (2020), 1179--1191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","unstructured":"Marc Lanctot et al. 2017. A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning. Advances in Neural Information Processing Systems 30 (2017).  Marc Lanctot et al. 2017. A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001606"},{"key":"e_1_3_2_1_25_1","unstructured":"Chenghao Li et al. 2021. Celebrating Diversity in Shared Multi-Agent Reinforcement Learning. Advances in Neural Information Processing Systems 34 (2021).  Chenghao Li et al. 2021. Celebrating Diversity in Shared Multi-Agent Reinforcement Learning. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/821"},{"volume-title":"2013 IEEE International Conference on Robotics and Automation. IEEE, 4545--4551","author":"Pyry","key":"e_1_3_2_1_27_1","unstructured":"Pyry Matikainen et al. 2013. Multi-armed recommendation bandits for selecting state machine policies for robotic systems . In 2013 IEEE International Conference on Robotics and Automation. IEEE, 4545--4551 . Pyry Matikainen et al. 2013. Multi-armed recommendation bandits for selecting state machine policies for robotic systems. In 2013 IEEE International Conference on Robotics and Automation. IEEE, 4545--4551."},{"key":"e_1_3_2_1_28_1","volume-title":"McKee et al","author":"Kevin","year":"2021","unstructured":"Kevin R. McKee et al . 2021 . Quantifying environment and population diversity in multi-agent reinforcement learning. ArXiv abs\/2102.08370 (2021). Kevin R. McKee et al. 2021. Quantifying environment and population diversity in multi-agent reinforcement learning. ArXiv abs\/2102.08370 (2021)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09548-8"},{"volume-title":"International Conference on Machine Learning. PMLR, 7588--7598","author":"Joe","key":"e_1_3_2_1_30_1","unstructured":"Joe Mellor et al. 2021. Neural architecture search without training . In International Conference on Machine Learning. PMLR, 7588--7598 . Joe Mellor et al. 2021. Neural architecture search without training. In International Conference on Machine Learning. PMLR, 7588--7598."},{"key":"e_1_3_2_1_31_1","volume-title":"Illuminating search spaces by mapping elites. arXiv preprint arXiv:1504.04909","author":"Mouret Jean-Baptiste","year":"2015","unstructured":"Jean-Baptiste Mouret and Jeff Clune . 2015. Illuminating search spaces by mapping elites. arXiv preprint arXiv:1504.04909 ( 2015 ). Jean-Baptiste Mouret and Jeff Clune. 2015. Illuminating search spaces by mapping elites. arXiv preprint arXiv:1504.04909 (2015)."},{"volume-title":"Proceedings of the Eleventh ACM International Conference on Future Energy Systems. 57--67","author":"Srinarayana","key":"e_1_3_2_1_32_1","unstructured":"Srinarayana Nagarathinam et al. 2020. MARCO-Multi-Agent Reinforcement learning based COntrol of building HVAC systems . In Proceedings of the Eleventh ACM International Conference on Future Energy Systems. 57--67 . Srinarayana Nagarathinam et al. 2020. MARCO-Multi-Agent Reinforcement learning based COntrol of building HVAC systems. In Proceedings of the Eleventh ACM International Conference on Future Energy Systems. 57--67."},{"key":"e_1_3_2_1_33_1","unstructured":"Jack Parker-Holder etal 2020. Effective Diversity in Population Based Reinforcement Learning. (2020). arXiv:2002.00632 [cs.LG]  Jack Parker-Holder et al. 2020. Effective Diversity in Population Based Reinforcement Learning. (2020). arXiv:2002.00632 [cs.LG]"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00040"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2007.03.007"},{"volume-title":"Autonomous Building Control Using Offline Reinforcement Learning. In International Conference on P2P, Parallel, Grid, Cloud and Internet Computing. Springer, 246--255","author":"Jorren","key":"e_1_3_2_1_36_1","unstructured":"Jorren Schepers et al. 2021 . Autonomous Building Control Using Offline Reinforcement Learning. In International Conference on P2P, Parallel, Grid, Cloud and Internet Computing. Springer, 246--255 . Jorren Schepers et al. 2021. Autonomous Building Control Using Offline Reinforcement Learning. In International Conference on P2P, Parallel, Grid, Cloud and Internet Computing. Springer, 246--255."},{"key":"e_1_3_2_1_37_1","unstructured":"John Schulman et al. 2017. Proximal Policy Optimization Algorithms. (2017). arXiv:1707.06347 [cs.LG]  John Schulman et al. 2017. Proximal Policy Optimization Algorithms. (2017). arXiv:1707.06347 [cs.LG]"},{"volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","key":"e_1_3_2_1_38_1","unstructured":"Richard S Sutton and Andrew G Barto . 2018. Reinforcement learning: An introduction . MIT press . Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/1577069.1755839"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/en13205396"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3427604"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115036"},{"volume-title":"Proceedings of the 7th ACM international conference on systems for energy-efficient buildings, cities, and transportation. 230--239","author":"Shichao","key":"e_1_3_2_1_43_1","unstructured":"Shichao Xu et al. 2020. 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. 230--239 . Shichao Xu et al. 2020. 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. 230--239."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12273-021-0861-0"},{"volume-title":"Proceedings of the International Conference on Autonomous Agents and Multi Agent Systems (AAMAS-21)","author":"Yaodong","key":"e_1_3_2_1_45_1","unstructured":"Yaodong Yang et al. 2021. Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems . In Proceedings of the International Conference on Autonomous Agents and Multi Agent Systems (AAMAS-21) . IFAAMAS. Yaodong Yang et al. 2021. Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems. In Proceedings of the International Conference on Autonomous Agents and Multi Agent Systems (AAMAS-21). IFAAMAS."},{"key":"e_1_3_2_1_46_1","unstructured":"Chao Yu et al. 2021. The Surprising Effectiveness of PPO in Cooperative MultiAgent Games. arXiv preprint arXiv:2103.01955 (2021).  Chao Yu et al. 2021. The Surprising Effectiveness of PPO in Cooperative MultiAgent Games. arXiv preprint arXiv:2103.01955 (2021)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Chi Zhang et al. 2022. Safe Building HVAC Control via Batch Reinforcement Learning. IEEE Transactions on Sustainable Computing (2022).  Chi Zhang et al. 2022. Safe Building HVAC Control via Batch Reinforcement Learning. IEEE Transactions on Sustainable Computing (2022).","DOI":"10.1109\/TSUSC.2022.3164084"},{"volume-title":"Proceedings of the Twelfth ACM International Conference on Future Energy Systems. ACM, 60--72","author":"Tianyu","key":"e_1_3_2_1_48_1","unstructured":"Tianyu Zhang et al. 2021. On the Joint Control of Multiple Building Systems with Reinforcement Learning . In Proceedings of the Twelfth ACM International Conference on Future Energy Systems. ACM, 60--72 . Tianyu Zhang et al. 2021. On the Joint Control of Multiple Building Systems with Reinforcement Learning. In Proceedings of the Twelfth ACM International Conference on Future Energy Systems. ACM, 60--72."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Tianyu Zhang et al. 2022. Addressing Data Inadequacy Challenges in Personal Comfort Models by Combining Pretrained Comfort Models. Energy and Buildings (2022) 112068.  Tianyu Zhang et al. 2022. Addressing Data Inadequacy Challenges in Personal Comfort Models by Combining Pretrained Comfort Models. Energy and Buildings (2022) 112068.","DOI":"10.1016\/j.enbuild.2022.112068"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302505.3310077"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3431119"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Peng Zhao et al. 2012. An energy management system for building structures using a multi-agent decision-making control methodology. IEEE transactions on industry applications 49 1 (2012) 322--330.  Peng Zhao et al. 2012. An energy management system for building structures using a multi-agent decision-making control methodology. IEEE transactions on industry applications 49 1 (2012) 322--330.","DOI":"10.1109\/TIA.2012.2229682"}],"event":{"name":"e-Energy '22: The Thirteenth ACM International Conference on Future Energy Systems","sponsor":["SIGEnergy ACM Special Interest Group on Energy Systems and Informatics"],"location":"Virtual Event","acronym":"e-Energy '22"},"container-title":["Proceedings of the Thirteenth ACM International Conference on Future Energy Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3538637.3539615","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3538637.3539615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:03:02Z","timestamp":1750186982000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3538637.3539615"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,28]]},"references-count":52,"alternative-id":["10.1145\/3538637.3539615","10.1145\/3538637"],"URL":"https:\/\/doi.org\/10.1145\/3538637.3539615","relation":{},"subject":[],"published":{"date-parts":[[2022,6,28]]},"assertion":[{"value":"2022-06-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}