{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T12:00:11Z","timestamp":1773835211080,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,12]],"date-time":"2020-06-12T00:00:00Z","timestamp":1591920000000},"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":[[2020,6,12]]},"DOI":"10.1145\/3396851.3397694","type":"proceedings-article","created":{"date-parts":[[2020,6,18]],"date-time":"2020-06-18T22:03:20Z","timestamp":1592517800000},"page":"57-67","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":42,"title":["MARCO - Multi-Agent Reinforcement learning based COntrol of building HVAC systems"],"prefix":"10.1145","author":[{"given":"Srinarayana","family":"Nagarathinam","sequence":"first","affiliation":[{"name":"TCS Research, India, TCS Research&Innovation, IIT-Madras Research Park, Chennai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishnu","family":"Menon","sequence":"additional","affiliation":[{"name":"TCS Research, India, TCS Research&Innovation, IIT-Madras Research Park, Chennai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arunchandar","family":"Vasan","sequence":"additional","affiliation":[{"name":"TCS Research, India, TCS Research&Innovation, IIT-Madras Research Park, Chennai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anand","family":"Sivasubramaniam","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Pennsylvania State University University Park, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,6,18]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Buildings Energy Data Book. 2011.  Buildings Energy Data Book. 2011."},{"key":"e_1_3_2_1_2_1","first-page":"246","volume-title":"Proceedings of IPSN","author":"Agarwal Y.","year":"2011","unstructured":"Y. Agarwal , B. Balaji , S. Dutta , R. K. Gupta , and T. Weng . Duty-cycling buildings aggressively: The next frontier in hvac control . In Proceedings of IPSN , pages 246 -- 257 . IEEE, 2011 . Y. Agarwal, B. Balaji, S. Dutta, R. K. Gupta, and T. Weng. Duty-cycling buildings aggressively: The next frontier in hvac control. In Proceedings of IPSN, pages 246--257. IEEE, 2011."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1878431.1878433"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIU.2018.8404287"},{"key":"e_1_3_2_1_5_1","first-page":"17","volume-title":"Proceedings of SenSys","author":"Balaji B.","unstructured":"B. Balaji , J. Xu , A. Nwokafor , R. Gupta , and Y. Agarwal . Sentinel: occupancy based hvac actuation using existing wifi infrastructure within commercial buildings . In Proceedings of SenSys , page 17 . ACM, 2013. B. Balaji, J. Xu, A. Nwokafor, R. Gupta, and Y. Agarwal. Sentinel: occupancy based hvac actuation using existing wifi infrastructure within commercial buildings. In Proceedings of SenSys, page 17. ACM, 2013."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2674061.2674072"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2528282.2528301"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040278"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360849"},{"key":"e_1_3_2_1_10_1","volume-title":"A new framework for multi-agent reinforcement learning - centralized training and exploration with decentralized execution via policy distillation","author":"Chen G.","year":"2019","unstructured":"G. Chen . A new framework for multi-agent reinforcement learning - centralized training and exploration with decentralized execution via policy distillation , 2019 . G. Chen. A new framework for multi-agent reinforcement learning - centralized training and exploration with decentralized execution via policy distillation, 2019."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2962435"},{"key":"e_1_3_2_1_12_1","volume-title":"Dynamic chiller plant optimization","author":"Cheng E.","year":"2018","unstructured":"E. Cheng . Dynamic chiller plant optimization . ATAL Building Services Engineering Ltd , 2018 . E. Cheng. Dynamic chiller plant optimization. ATAL Building Services Engineering Ltd, 2018."},{"key":"e_1_3_2_1_13_1","volume-title":"https:\/\/github.com\/fchollet\/keras","author":"Chollet F.","year":"2015","unstructured":"F. Chollet . https:\/\/github.com\/fchollet\/keras , 2015 . F. Chollet et al. Keras. https:\/\/github.com\/fchollet\/keras, 2015."},{"key":"e_1_3_2_1_14_1","volume-title":"11th REHVA World Congress CLIMA","author":"Cigler J.","year":"2013","unstructured":"J. Cigler , J. Siroky , M. Korda , and C. Jones . On the selection of the most appropriate mpc problem formulation for buildings . In 11th REHVA World Congress CLIMA , 2013 . J. Cigler, J. Siroky, M. Korda, and C. Jones. On the selection of the most appropriate mpc problem formulation for buildings. In 11th REHVA World Congress CLIMA, 2013."},{"key":"e_1_3_2_1_15_1","first-page":"49","article-title":"Energyplus: Energy simulation program","volume":"42","author":"Crawley D. B.","year":"2000","unstructured":"D. B. Crawley , C. O. Pedersen , L. K. Lawrie , and F. C. Winkelmann . Energyplus: Energy simulation program . ASHRAE Journal , 42 : 49 -- 56 , 2000 . D. B. Crawley, C. O. Pedersen, L. K. Lawrie, and F. C. Winkelmann. Energyplus: Energy simulation program. ASHRAE Journal, 42:49--56, 2000.","journal-title":"ASHRAE Journal"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360857"},{"key":"e_1_3_2_1_17_1","volume-title":"Rl2: Fast reinforcement learning via slow reinforcement learning. ArXiv, abs\/1611.02779","author":"Duan Y.","year":"2017","unstructured":"Y. Duan , J. Schulman , X. Chen , P. L. Bartlett , I. Sutskever , and P. Abbeel . Rl2: Fast reinforcement learning via slow reinforcement learning. ArXiv, abs\/1611.02779 , 2017 . Y. Duan, J. Schulman, X. Chen, P. L. Bartlett, I. Sutskever, and P. Abbeel. Rl2: Fast reinforcement learning via slow reinforcement learning. ArXiv, abs\/1611.02779, 2017."},{"key":"e_1_3_2_1_18_1","volume-title":"Thermal Comfort: Analysis and Applications in Environmental Engineering","author":"Fanger P.","year":"1970","unstructured":"P. Fanger . Thermal Comfort: Analysis and Applications in Environmental Engineering . McGraw Hill , 1970 . P. Fanger. Thermal Comfort: Analysis and Applications in Environmental Engineering. McGraw Hill, 1970."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2012.08.002"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1469986"},{"key":"e_1_3_2_1_21_1","first-page":"2613","volume-title":"Advances in Neural Information Processing Systems 23","author":"Hasselt H. V.","year":"2010","unstructured":"H. V. Hasselt . Double q-learning. In J. D. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R. S. Zemel, and A. Culotta, editors , Advances in Neural Information Processing Systems 23 , pages 2613 -- 2621 . Curran Associates, Inc. , 2010 . H. V. Hasselt. Double q-learning. In J. D. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R. S. Zemel, and A. Culotta, editors, Advances in Neural Information Processing Systems 23, pages 2613--2621. Curran Associates, Inc., 2010."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/645529.658113"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2012.12.007"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CoASE.2015.7294119"},{"issue":"1","key":"e_1_3_2_1_25_1","first-page":"101","article-title":"Stochastic model predictive control for building hvac systems: Complexity and conservatism. Control Systems Technology","volume":"23","author":"Ma Y.","year":"2015","unstructured":"Y. Ma , J. Matusko , and F. Borrelli . Stochastic model predictive control for building hvac systems: Complexity and conservatism. Control Systems Technology , IEEE Transactions on , 23 ( 1 ): 101 -- 116 , 2015 . Y. Ma, J. Matusko, and F. Borrelli. Stochastic model predictive control for building hvac systems: Complexity and conservatism. Control Systems Technology, IEEE Transactions on, 23(1):101--116, 2015.","journal-title":"IEEE Transactions on"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2834219"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2019.00060"},{"key":"e_1_3_2_1_28_1","volume-title":"Deep reinforcement learning for multi-agent systems: A review of challenges, solutions and applications. ArXiv, abs\/1812.11794","author":"Nguyen T. T.","year":"2018","unstructured":"T. T. Nguyen , N. D. Nguyen , and S. Nahavandi . Deep reinforcement learning for multi-agent systems: A review of challenges, solutions and applications. ArXiv, abs\/1812.11794 , 2018 . T. T. Nguyen, N. D. Nguyen, and S. Nahavandi. Deep reinforcement learning for multi-agent systems: A review of challenges, solutions and applications. ArXiv, abs\/1812.11794, 2018."},{"key":"e_1_3_2_1_29_1","volume-title":"Handbook Of Research On Machine Learning Applications and Trends: Algorithms, Methods and Techniques - 2 Volumes. Information Science Reference - Imprint of: IGI Publishing","author":"Olivas E. S.","year":"2009","unstructured":"E. S. Olivas , J. D. M. Guerrero , M. M. Sober , J. R. M. Benedito , and A. J. S. Lopez . Handbook Of Research On Machine Learning Applications and Trends: Algorithms, Methods and Techniques - 2 Volumes. Information Science Reference - Imprint of: IGI Publishing , Hershey, PA , 2009 . E. S. Olivas, J. D. M. Guerrero, M. M. Sober, J. R. M. Benedito, and A. J. S. Lopez. Handbook Of Research On Machine Learning Applications and Trends: Algorithms, Methods and Techniques - 2 Volumes. Information Science Reference - Imprint of: IGI Publishing, Hershey, PA, 2009."},{"key":"e_1_3_2_1_30_1","first-page":"1","volume-title":"Proceedings of BuildSys","author":"H.","year":"2013","unstructured":"Parisio, Alessandra and Varagnolo, Damiano and Risberg, Daniel and Pattarello, Giorgio and Molinari, Marco and Johansson, Karl H. Randomized model predictive control for HVAC systems . In Proceedings of BuildSys , pages 1 -- 8 . ACM, 2013 . Parisio, Alessandra and Varagnolo, Damiano and Risberg, Daniel and Pattarello, Giorgio and Molinari, Marco and Johansson, Karl H. Randomized model predictive control for HVAC systems. In Proceedings of BuildSys, pages 1--8. ACM, 2013."},{"key":"e_1_3_2_1_31_1","volume-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games","author":"Peng P.","year":"2017","unstructured":"P. Peng , Y. Wen , Y. Yang , Q. Yuan , Z. Tang , H. Long , and J. Wang . Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games , 2017 . P. Peng, Y. Wen, Y. Yang, Q. Yuan, Z. Tang, H. Long, and J. Wang. Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games, 2017."},{"key":"e_1_3_2_1_32_1","volume-title":"I-blend, a campus-scale commercial and residential buildings electrical energy dataset. Scientific Data, 6(190015)","author":"Rashid H.","year":"2019","unstructured":"H. Rashid , P. Singh , and A. Singh . I-blend, a campus-scale commercial and residential buildings electrical energy dataset. Scientific Data, 6(190015) , 2019 . H. Rashid, P. Singh, and A. Singh. I-blend, a campus-scale commercial and residential buildings electrical energy dataset. Scientific Data, 6(190015), 2019."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2017.04.024"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA.2012.6489619"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2781130"},{"key":"e_1_3_2_1_36_1","first-page":"476","article-title":"Energy efficient thermal comfort in open-plan office buildings","volume":"139","author":"Srinarayana N.","year":"2014","unstructured":"N. Srinarayana , D. Harish , V. Arunchandar , P. Venkata Ramakrishna , S. Venkatesh , and S. Anand . Energy efficient thermal comfort in open-plan office buildings . Energy & Buildings , 139 : 476 -- 486 , 2014 . N. Srinarayana, D. Harish, V. Arunchandar, P. Venkata Ramakrishna, S. Venkatesh, and S. Anand. Energy efficient thermal comfort in open-plan office buildings. Energy & Buildings, 139:476--486, 2014.","journal-title":"Energy & Buildings"},{"key":"e_1_3_2_1_37_1","first-page":"157","volume-title":"Proceedings of BuildSys","author":"Srinarayana N.","year":"2015","unstructured":"N. Srinarayana , A. Vasan , P. Venkata Ramakrishna , S. Iyer , V. Sarangan , and A. Sivasubramaniam . Centralized management of hvac energy in large multi-ahu zones . In Proceedings of BuildSys , pages 157 -- 166 . ACM, 2015 . N. Srinarayana, A. Vasan, P. Venkata Ramakrishna, S. Iyer, V. Sarangan, and A. Sivasubramaniam. Centralized management of hvac energy in large multi-ahu zones. In Proceedings of BuildSys, pages 157--166. ACM, 2015."},{"key":"e_1_3_2_1_38_1","volume-title":"Thermal environmental conditions for human occupancy","author":"Standard A.","year":"2010","unstructured":"A. Standard . 55 ( 2010 ). Thermal environmental conditions for human occupancy . A. Standard. 55 (2010). Thermal environmental conditions for human occupancy."},{"key":"e_1_3_2_1_39_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018","unstructured":"R. S. Sutton and A. G. Barto . Reinforcement Learning: An Introduction . The MIT Press , second edition, 2018 . R. S. Sutton and A. G. Barto. Reinforcement Learning: An Introduction. The MIT Press, second edition, 2018."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v33i3.2426"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2019.03.038"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062224"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1080\/19401493.2010.518631"},{"key":"e_1_3_2_1_44_1","volume-title":"Flow: A modular learning framework for autonomy in traffic","author":"Wu C.","year":"2017","unstructured":"C. Wu , A. Kreidieh , K. Parvate , E. Vinitsky , and A. M. Bayen . Flow: A modular learning framework for autonomy in traffic , 2017 . C. Wu, A. Kreidieh, K. Parvate, E. Vinitsky, and A. M. Bayen. Flow: A modular learning framework for autonomy in traffic, 2017."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.07.286"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360861"},{"key":"e_1_3_2_1_47_1","volume-title":"2018 Building Performance Analysis Conference and SimBuild","author":"Zhang Z.","year":"2018","unstructured":"Z. Zhang , A. Chong , Y. Pan , C. Zhang , S. Lu , and K. P. Lam . A deep reinforcement learning approach to using whole building energy model for hvac optimal control . In 2018 Building Performance Analysis Conference and SimBuild , 2018 . Z. Zhang, A. Chong, Y. Pan, C. Zhang, S. Lu, and K. P. Lam. A deep reinforcement learning approach to using whole building energy model for hvac optimal control. In 2018 Building Performance Analysis Conference and SimBuild, 2018."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3208903.3208913"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2019.2932045"},{"key":"e_1_3_2_1_50_1","volume-title":"Optimization method for the chiller plant of central air-conditioning system parameters on association rules analysis for energy conservation","author":"Zhou X.","year":"2018","unstructured":"X. Zhou , B. Wang , L. Liang , J. Yan , and D. Pan . Optimization method for the chiller plant of central air-conditioning system parameters on association rules analysis for energy conservation . 2018 . X. Zhou, B. Wang, L. Liang, J. Yan, and D. Pan. Optimization method for the chiller plant of central air-conditioning system parameters on association rules analysis for energy conservation. 2018."}],"event":{"name":"e-Energy '20: The Eleventh ACM International Conference on Future Energy Systems","location":"Virtual Event Australia","acronym":"e-Energy '20","sponsor":["SIGEnergy ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the Eleventh ACM International Conference on Future Energy Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3396851.3397694","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3396851.3397694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:33:29Z","timestamp":1750199609000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3396851.3397694"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,12]]},"references-count":50,"alternative-id":["10.1145\/3396851.3397694","10.1145\/3396851"],"URL":"https:\/\/doi.org\/10.1145\/3396851.3397694","relation":{},"subject":[],"published":{"date-parts":[[2020,6,12]]},"assertion":[{"value":"2020-06-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}