{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T09:30:12Z","timestamp":1781688612874,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,9]],"date-time":"2022-11-09T00:00:00Z","timestamp":1667952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,9]]},"DOI":"10.1145\/3563357.3566165","type":"proceedings-article","created":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T13:31:36Z","timestamp":1670506296000},"page":"466-470","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Behavioural cloning based RL agents for district energy management"],"prefix":"10.1145","author":[{"given":"Sharath Ram","family":"Kumar","sequence":"first","affiliation":[{"name":"Univ. Grenoble Alpes, Grenoble, France and Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arvind","family":"Easwaran","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benoit","family":"Delinchant","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, Grenoble, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Remy","family":"Rigo-Mariani","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, Grenoble, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,12,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2021.3122570"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21041278"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Anjukan Kathirgamanathan Kacper Twardowski Eleni Mangina and Donal Finn. 2020. A Centralised Soft Actor Critic Deep Reinforcement Learning Approach to District Demand Side Management through CityLearn. (2020). 10.48550\/ARXIV.2009.10562","DOI":"10.48550\/ARXIV.2009.10562"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abo0235"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2010.2050156"},{"key":"e_1_3_2_1_6_1","volume-title":"Ngoc Duy Nguyen, and Saeid Nahavandi","author":"Nguyen Thanh Thi","year":"2020","unstructured":"Thanh Thi Nguyen, Ngoc Duy Nguyen, and Saeid Nahavandi. 2020. Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications. IEEE transactions on cybernetics 50, 9 (2020), 3826--3839."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Kingsley Nweye Bo Liu Peter Stone and Zoltan Nagy. 2021. Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings. 10.48550\/ARXIV.2112.06127","DOI":"10.48550\/ARXIV.2112.06127"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Takayuki Osa Joni Pajarinen Gerhard Neumann J Andrew Bagnell Pieter Abbeel Jan Peters et al. 2018. An algorithmic perspective on imitation learning. Foundations and Trends\u00ae in Robotics 7 1--2 (2018) 1--179.","DOI":"10.1561\/2300000053"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Nicola Pezzotti. 2021. MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowl. 10.48550\/ARXIV.2108.09478","DOI":"10.48550\/ARXIV.2108.09478"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2017.01.062"},{"key":"e_1_3_2_1_11_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3427604"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.11.002"}],"event":{"name":"BuildSys '22: The 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","location":"Boston Massachusetts","acronym":"BuildSys '22","sponsor":["SIGEnergy ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563357.3566165","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3563357.3566165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T07:27:39Z","timestamp":1755847659000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563357.3566165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,9]]},"references-count":13,"alternative-id":["10.1145\/3563357.3566165","10.1145\/3563357"],"URL":"https:\/\/doi.org\/10.1145\/3563357.3566165","relation":{},"subject":[],"published":{"date-parts":[[2022,11,9]]},"assertion":[{"value":"2022-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}