{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T10:28:56Z","timestamp":1779877736537,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,8]]},"DOI":"10.1145\/3703412.3703422","type":"proceedings-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T11:49:51Z","timestamp":1741175391000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ORCHID: Offline RL for Control of HVAC in Buildings using Historical and Low-Fidelity Simulation Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9579-0559","authenticated-orcid":false,"given":"Richa","family":"Verma","sequence":"first","affiliation":[{"name":"TCS Research, Bangalore, IN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3654-4143","authenticated-orcid":false,"given":"Srikar Babu","family":"Gadipudi","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology, Madras, Chennai, IN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1549-2135","authenticated-orcid":false,"given":"Srinarayana","family":"Nagarathinam","sequence":"additional","affiliation":[{"name":"Tata Consultancy Services Ltd, Chennai, IN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3601-778X","authenticated-orcid":false,"given":"Harshad","family":"Khadilkar","sequence":"additional","affiliation":[{"name":"Tata Consultancy Services Ltd., Mumbai, IN"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,5]]},"reference":[{"key":"e_1_3_3_2_2_2","first-page":"246","volume-title":"Proceedings of the 10th ACM\/IEEE international conference on information processing in sensor networks","author":"Agarwal Yuvraj","year":"2011","unstructured":"Yuvraj Agarwal, Bharathan Balaji, Seemanta Dutta, Rajesh\u00a0K Gupta, and Thomas Weng. 2011. Duty-cycling buildings aggressively: The next frontier in HVAC control. In Proceedings of the 10th ACM\/IEEE international conference on information processing in sensor networks. IEEE, 246\u2013257."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/1878431.1878433"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2517351.2517370"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2674061.2674072"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2528282.2528301"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040278"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360849"},{"key":"e_1_3_3_2_9_2","volume-title":"11th REHVA World Congress CLIMA 2013","author":"Cigler Jiri","year":"2013","unstructured":"Jiri Cigler, Jan Siroky, Milan Korda, and Colin Jones. 2013. On the selection of the most appropriate MPC problem formulation for buildings. In 11th REHVA World Congress CLIMA 2013."},{"key":"e_1_3_3_2_10_2","unstructured":"Drury\u00a0B Crawley Linda\u00a0K Lawrie Curtis\u00a0O Pedersen and Frederick\u00a0C Winkelmann. 2000. Energy plus: energy simulation program. ASHRAE journal 42 4 (2000) 49\u201356."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360857"},{"key":"e_1_3_3_2_12_2","unstructured":"US DoE et\u00a0al. 2011. Buildings energy data book. Energy Efficiency & Renewable Energy Department 286 (2011) 1\u20133."},{"key":"e_1_3_3_2_13_2","unstructured":"Poul\u00a0O Fanger et\u00a0al. 1970. Thermal comfort. Analysis and applications in environmental engineering. Thermal comfort. Analysis and applications in environmental engineering. (1970)."},{"key":"e_1_3_3_2_14_2","unstructured":"Justin Fu Aviral Kumar Ofir Nachum George Tucker and Sergey Levine. 2020. D4rl: Datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2004.07219 (2020)."},{"key":"e_1_3_3_2_15_2","first-page":"2052","volume-title":"International conference on machine learning","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, David Meger, and Doina Precup. 2019. Off-policy deep reinforcement learning without exploration. In International conference on machine learning. PMLR, 2052\u20132062."},{"key":"e_1_3_3_2_16_2","unstructured":"Tuomas Haarnoja Aurick Zhou Kristian Hartikainen George Tucker Sehoon Ha Jie Tan Vikash Kumar Henry Zhu Abhishek Gupta Pieter Abbeel et\u00a0al. 2018. Soft actor-critic algorithms and applications. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.05905 (2018)."},{"key":"e_1_3_3_2_17_2","unstructured":"Ilya Kostrikov Ashvin Nair and Sergey Levine. 2021. Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.06169 (2021)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Beat Lehmann Dimitrios Gyalistras Markus Gwerder Katharina Wirth and Stephan Carl. 2013. Intermediate complexity model for model predictive control of integrated room automation. Energy and Buildings 58 (2013) 250\u2013262.","DOI":"10.1016\/j.enbuild.2012.12.007"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CoASE.2015.7294119"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS54341.2022.00023"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575813.3595202"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Srinarayana Nagarathinam Harish Doddi Arunchandar Vasan Venkatesh Sarangan P\u00a0Venkata Ramakrishna and Anand Sivasubramaniam. 2017. Energy efficient thermal comfort in open-plan office buildings. Energy and Buildings 139 (2017) 476\u2013486.","DOI":"10.1016\/j.enbuild.2017.01.043"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3396851.3397694"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2821650.2821655"},{"key":"e_1_3_3_2_25_2","unstructured":"Ashvin Nair Abhishek Gupta Murtaza Dalal and Sergey Levine. 2020. Awac: Accelerating online reinforcement learning with offline datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.09359 (2020)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2019.00060"},{"key":"e_1_3_3_2_27_2","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et\u00a0al. 2019. Pytorch: An imperative style high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/PSCC.2014.7038106"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Frederik Ruelens Sandro Iacovella Bert\u00a0J Claessens and Ronnie Belmans. 2015. Learning agent for a heat-pump thermostat with a set-back strategy using model-free reinforcement learning. Energies 8 8 (2015) 8300\u20138318.","DOI":"10.3390\/en8088300"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA.2012.6489619"},{"key":"e_1_3_3_2_32_2","unstructured":"ASHRAE Standard et\u00a0al. 2010. Standard 55-2010 Thermal environmental conditions for human occupancy. American Society of Heating Refrigerating and Air Conditioning Engineers (2010)."},{"key":"e_1_3_3_2_33_2","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard\u00a0S","year":"2018","unstructured":"Richard\u00a0S Sutton and Andrew\u00a0G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062224"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Michael Wetter. 2011. Co-simulation of building energy and control systems with the Building Controls Virtual Test Bed. Journal of Building Performance Simulation 4 3 (2011) 185\u2013203.","DOI":"10.1080\/19401493.2010.518631"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360861"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Chi Zhang Sanmukh\u00a0Rao Kuppannagari and Viktor\u00a0K Prasanna. 2022. Safe building hvac control via batch reinforcement learning. IEEE Transactions on Sustainable Computing 7 4 (2022) 923\u2013934.","DOI":"10.1109\/TSUSC.2022.3164084"},{"key":"e_1_3_3_2_38_2","first-page":"22","volume-title":"2018 Building Performance Analysis Conference and SimBuild","volume":"3","author":"Zhang Zhiang","year":"2018","unstructured":"Zhiang Zhang, Adrian Chong, Yuqi Pan, Chenlu Zhang, Siliang Lu, and Khee\u00a0Poh Lam. 2018. A deep reinforcement learning approach to using whole building energy model for hvac optimal control. In 2018 Building Performance Analysis Conference and SimBuild , Vol.\u00a03. 22\u201323."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3208903.3208913"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Zimu Zheng Qiong Chen Cheng Fan Nan Guan Arun Vishwanath Dan Wang and Fangming Liu. 2019. An edge based data-driven chiller sequencing framework for HVAC electricity consumption reduction in commercial buildings. IEEE Transactions on Sustainable Computing 7 3 (2019) 487\u2013498.","DOI":"10.1109\/TSUSC.2019.2932045"}],"event":{"name":"AIMLSystems 2024: The 4th International Conference on AI-ML Systems","location":"Baton Rouge Louisiana USA","acronym":"AIMLSystems 2024"},"container-title":["Proceedings of the 4th International Conference on AI-ML Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703412.3703422","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703412.3703422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703412.3703422"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":39,"alternative-id":["10.1145\/3703412.3703422","10.1145\/3703412"],"URL":"https:\/\/doi.org\/10.1145\/3703412.3703422","relation":{},"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"2025-03-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}