{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:45:22Z","timestamp":1785336322066,"version":"3.55.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319234601","type":"print"},{"value":"9783319234618","type":"electronic"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-23461-8_1","type":"book-chapter","created":{"date-parts":[[2015,8,28]],"date-time":"2015-08-28T08:20:16Z","timestamp":1440750016000},"page":"3-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["Autonomous HVAC Control, A Reinforcement Learning Approach"],"prefix":"10.1007","author":[{"given":"Enda","family":"Barrett","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen","family":"Linder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,8,29]]},"reference":[{"key":"1_CR1","unstructured":"Fuzzy logic inference temp. controller for air conditioner, September 1, 1999. https:\/\/www.google.fr\/patents\/CN2336254Y?cl=en . cN Patent 2,336,254"},{"key":"1_CR2","unstructured":"Honeywell evohome, January 01, 2015. http:\/\/evohome.honeywell.com\/"},{"key":"1_CR3","unstructured":"Nest thermostat, January 01, 2015. https:\/\/nest.com\/thermostat\/life-with-nest-thermostat"},{"key":"1_CR4","unstructured":"Ahmed, O.: Method and apparatus for determining a thermal setpoint in a hvac system, November 9, 2004. https:\/\/www.google.fr\/patents\/CA2289237C?cl=en . cA Patent 2,289,237"},{"issue":"1","key":"1_CR5","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1080\/09540091.2014.885268","volume":"26","author":"E Barrett","year":"2014","unstructured":"Barrett, E., Duggan, J., Howley, E.: A parallel framework for bayesian reinforcement learning. Connection Science 26(1), 7\u201323 (2014)","journal-title":"Connection Science"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Barrett, E., Howley, E., Duggan, J.: A learning architecture for scheduling workflow applications in the cloud. In: 2011 Ninth IEEE European Conference on Web Services (ECOWS), pp. 83\u201390. IEEE (2011)","DOI":"10.1109\/ECOWS.2011.27"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Barrett, E., Howley, E., Duggan, J.: Applying reinforcement learning towards automating resource allocation and application scalability in the cloud. Concurrency and Computation: Practice and Experience (2012)","DOI":"10.1002\/cpe.2864"},{"key":"1_CR8","unstructured":"Choi, S., Yeung, D.Y.: Predictive q-routing: a memory-based reinforcement learning approach to adaptive tra c control. In: Advances in Neural Information Processing Systems 8, pp. 945\u2013951 (1996)"},{"key":"1_CR9","unstructured":"Dage, G., Davis, L., Matteson, R., Sieja, T.: Method and system for controlling an automotive hvac system, July 22, 1998. https:\/\/www.google.fr\/patents\/EP0706682B1?cl=en . eP Patent 0,706,682"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Dorigo, M., Gambardella, L.: Ant-q: a reinforcement learning approach to the traveling salesman problem. In: Proceedings of ML-95, Twelfth Intern. Conf. on Machine Learning, pp. 252\u2013260 (2014)","DOI":"10.1016\/B978-1-55860-377-6.50039-6"},{"key":"1_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jwsr.2005010101","volume":"2","author":"P Doshi","year":"2005","unstructured":"Doshi, P., Goodwin, R., Akkiraju, R., Verma, K.: Dynamic workflow composition using markov decision processes. International Journal of Web Services Research 2, 1\u201317 (2005)","journal-title":"International Journal of Web Services Research"},{"key":"1_CR12","unstructured":"Dutreilh, X., Kirgizov, S., Melekhova, O., Malenfant, J., Rivierre, N., Truck, I.: Using reinforcement learning for autonomic resource allocation in clouds: towards a fully automated workflow. In: The Seventh International Conference on Autonomic and Autonomous Systems, ICAS 2011, pp. 67\u201374 (2011)"},{"key":"1_CR13","unstructured":"Fadell, A., Rogers, M., Satterthwaite, E., Smith, I., Warren, D., Palmer, J., Honjo, S., Erickson, G., Dutra, J., Fiennes, H.: User-friendly, network connected learning thermostat and related systems and methods, July 4, 2013. https:\/\/www.google.fr\/patents\/US20130173064 . uS Patent App. 13\/656,189"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Grzes, M., Kudenko, D.: Learning shaping rewards in model-based reinforcement learning. In: Proc. AAMAS 2009 Workshop on Adaptive Learning Agents, vol. 115 (2009)","DOI":"10.1007\/978-3-642-03603-3_2"},{"key":"1_CR15","unstructured":"Karray, F.O., De Silva, C.W.: Soft computing and intelligent systems design: theory, tools, and applications. Pearson Education (2004)"},{"key":"1_CR16","volume-title":"Automated Planning: Theory & Practice","author":"D Nau","year":"2004","unstructured":"Nau, D., Ghallab, M., Traverso, P.: Automated Planning: Theory & Practice. Morgan Kaufmann Publishers Inc., San Francisco (2004)"},{"key":"1_CR17","volume-title":"Artificial intelligence: a modern approach","author":"S Russell","year":"1995","unstructured":"Russell, S., Norvig, P., Canny, J., Malik, J., Edwards, D.: Artificial intelligence: a modern approach, vol. 2. Prentice hall Englewood Cliffs, NJ (1995)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Scott, J., Bernheim Brush, A., Krumm, J., Meyers, B., Hazas, M., Hodges, S., Villar, N.: Preheat: controlling home heating using occupancy prediction. In: Proceedings of the 13th International Conference on Ubiquitous Computing, pp. 281\u2013290. ACM (2011)","DOI":"10.1145\/2030112.2030151"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Spiegelhalter, D.J., Dawid, A.P., Lauritzen, S.L., Cowell, R.G.: Bayesian analysis in expert systems. Statistical science, 219\u2013247 (1993)","DOI":"10.1214\/ss\/1177010888"},{"key":"1_CR20","unstructured":"Strens, M.: A bayesian framework for reinforcement learning, pp. 943\u2013950 (2000)"},{"issue":"3","key":"1_CR21","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal difference learning and td-gammon. Communications of the ACM 38(3), 58\u201368 (1995)","journal-title":"Communications of the ACM"},{"issue":"3","key":"1_CR22","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1023\/A:1015504423309","volume":"5","author":"G Tesauro","year":"2002","unstructured":"Tesauro, G., Kephart, J.O.: Pricing in agent economies using multi-agent q-learning. Autonomous Agents and Multi-Agent Systems 5(3), 289\u2013304 (2002)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"1_CR23","unstructured":"Watkins, C.: Learning from Delayed Rewards. Ph.D. thesis, University of Cambridge, England (1989)"},{"key":"1_CR24","unstructured":"Wiering, M.: Multi-agent reinforcement learning for traffic light control. In: ICML, pp. 1151\u20131158 (2000)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-23461-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,21]],"date-time":"2022-05-21T01:56:51Z","timestamp":1653098211000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-23461-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319234601","9783319234618"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-23461-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"29 August 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}