{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:57:27Z","timestamp":1742972247444,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730573"},{"type":"electronic","value":"9783031730580"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73058-0_21","type":"book-chapter","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T08:44:29Z","timestamp":1735807469000},"page":"256-267","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transfer Learning with\u00a0TD3 for\u00a0Adaptive HVAC Control in\u00a0Diverse Building Environments"],"prefix":"10.1007","author":[{"given":"Kevlyn","family":"Kadamala","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Des","family":"Chambers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enda","family":"Barrett","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"21_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.118346","volume":"309","author":"J Arroyo","year":"2022","unstructured":"Arroyo, J., Manna, C., Spiessens, F., Helsen, L.: Reinforced model predictive control (RL-MPC) for building energy management. Appl. Energy 309, 118346 (2022)","journal-title":"Appl. Energy"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Barrett, E., Linder, S.: Autonomous HVAC control, a reinforcement learning approach. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2015, Porto, Portugal, 7\u201311 September 2015, Proceedings, Part III 15, pp. 3\u201319. Springer (2015)","DOI":"10.1007\/978-3-319-23461-8_1"},{"issue":"1","key":"21_CR3","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1080\/1350486042000271638","volume":"12","author":"FE Benth","year":"2005","unstructured":"Benth, F.E., \u0160altyt\u0117-Benth, J.: Stochastic modelling of temperature variations with a view towards weather derivatives. Appl. Math. Finance 12(1), 53\u201385 (2005)","journal-title":"Appl. Math. Finance"},{"key":"21_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117164","volume":"298","author":"M Biemann","year":"2021","unstructured":"Biemann, M., Scheller, F., Liu, X., Huang, L.: Experimental evaluation of model-free reinforcement learning algorithms for continuous HVAC control. Appl. Energy 298, 117164 (2021)","journal-title":"Appl. Energy"},{"key":"21_CR5","unstructured":"Department of Climate Change, Energy, t.E., Water, G.o.A.: HVAC energy breakdown. https:\/\/www.environment.gov.au\/system\/files\/energy\/files\/hvac-factsheet-energy-breakdown.pdf. Accessed 03 Apr 2024"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Coraci, D., Brandi, S., Hong, T., Capozzoli, A.: An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems. In: Building Simulation, pp. 1\u201332. Springer (2024)","DOI":"10.1007\/s12273-024-1109-6"},{"issue":"4","key":"21_CR7","doi-asserted-by":"publisher","first-page":"997","DOI":"10.3390\/en14040997","volume":"14","author":"D Coraci","year":"2021","unstructured":"Coraci, D., Brandi, S., Piscitelli, M.S., Capozzoli, A.: Online implementation of a soft actor-critic agent to enhance indoor temperature control and energy efficiency in buildings. Energies 14(4), 997 (2021)","journal-title":"Energies"},{"key":"21_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2022.108938","volume":"215","author":"A Dmitrewski","year":"2022","unstructured":"Dmitrewski, A., Molina-Solana, M., Arcucci, R.: CntrlDA: a building energy management control system with real-time adjustments. Application to indoor temperature. Build. Environ. 215, 108938 (2022)","journal-title":"Build. Environ."},{"key":"21_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.applthermaleng.2022.118552","volume":"212","author":"X Fang","year":"2022","unstructured":"Fang, X., et al.: Deep reinforcement learning optimal control strategy for temperature setpoint real-time reset in multi-zone building HVAC system. Appl. Therm. Eng. 212, 118552 (2022)","journal-title":"Appl. Therm. Eng."},{"key":"21_CR10","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"21_CR11","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"21_CR12","unstructured":"Huang, S., et al.: CleanRL: high-quality single-file implementations of deep reinforcement learning algorithms. J. Mach. Learn. Res. 23(274), 1\u201318 (2022). http:\/\/jmlr.org\/papers\/v23\/21-1342.html"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Jim\u00e9nez-Raboso, J., Campoy-Nieves, A., Manjavacas-Lucas, A., G\u00f3mez-Romero, J., Molina-Solana, M.: Sinergym: a building simulation and control framework for training reinforcement learning agents. In: Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, pp. 319\u2013323 (2021)","DOI":"10.1145\/3486611.3488729"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Kadamala, K., Chambers, D., Barrett, E.: Enhancing HVAC control systems through transfer learning with deep reinforcement learning agents. Smart Energy 100131 (2024)","DOI":"10.1016\/j.segy.2024.100131"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Li, B., Xia, L.: A multi-grid reinforcement learning method for energy conservation and comfort of HVAC in buildings. In: 2015 IEEE International Conference on Automation Science and Engineering (CASE), pp. 444\u2013449. IEEE (2015)","DOI":"10.1109\/CoASE.2015.7294119"},{"key":"21_CR16","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"21_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2020.100043","volume":"3","author":"P Lissa","year":"2021","unstructured":"Lissa, P., Deane, C., Schukat, M., Seri, F., Keane, M., Barrett, E.: Deep reinforcement learning for home energy management system control. Energy AI 3, 100043 (2021)","journal-title":"Energy AI"},{"issue":"3","key":"21_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-020-00146-7","volume":"1","author":"P Lissa","year":"2020","unstructured":"Lissa, P., Schukat, M., Barrett, E.: Transfer learning applied to reinforcement learning-based HVAC control. SN Comput. Sci. 1(3), 1\u201312 (2020)","journal-title":"SN Comput. Sci."},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Liu, H.Y., Balaji, B., Gupta, R., Hong, D.: Rule-based policy regularization for reinforcement learning-based building control. In: Proceedings of the 14th ACM International Conference on Future Energy Systems, pp. 242\u2013265 (2023)","DOI":"10.1145\/3575813.3595202"},{"key":"21_CR20","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Wei, T., Wang, Y., Zhu, Q.: Deep reinforcement learning for building HVAC control. In: Proceedings of the 54th Annual Design Automation Conference 2017, pp. 1\u20136 (2017)","DOI":"10.1145\/3061639.3062224"},{"key":"21_CR22","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, pp. 230\u2013239 (2020)","DOI":"10.1145\/3408308.3427617"},{"issue":"5","key":"21_CR23","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1016\/j.conengprac.2010.01.018","volume":"18","author":"Z Yu","year":"2010","unstructured":"Yu, Z., Dexter, A.: Online tuning of a supervisory fuzzy controller for low-energy building system using reinforcement learning. Control. Eng. Pract. 18(5), 532\u2013539 (2010)","journal-title":"Control. Eng. Pract."},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, X., Jin, X., Tripp, C., Biagioni, D.J., 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, pp. 43\u201347 (2020)","DOI":"10.1145\/3427773.3427865"}],"container-title":["Communications in Computer and Information Science","Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins: The PAAMS Collection"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73058-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T09:04:55Z","timestamp":1735808695000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73058-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031730573","9783031730580"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73058-0_21","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAAMS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Practical Applications of Agents and Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salamanca","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"paams2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.paams.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}