{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T03:48:13Z","timestamp":1760586493814,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642027031"},{"type":"electronic","value":"9783642027048"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-02704-8_9","type":"book-chapter","created":{"date-parts":[[2009,6,29]],"date-time":"2009-06-29T13:32:50Z","timestamp":1246282370000},"page":"105-119","source":"Crossref","is-referenced-by-count":3,"title":["Using Reinforcement Learning for Multi-policy Optimization in Decentralized Autonomic Systems \u2013 An Experimental Evaluation"],"prefix":"10.1007","author":[{"given":"Ivana","family":"Dusparic","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinny","family":"Cahill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"3","key":"9_CR1","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)","volume":"129","author":"B. Abdulhai","year":"2003","unstructured":"Abdulhai, B., Pringle, R., Karakoulas, G.: Reinforcement learning for the true adaptive traffic signal control. Journal of Transportation Engineering\u00a0129(3), 278\u2013285 (2003)","journal-title":"Journal of Transportation Engineering"},{"issue":"1","key":"9_CR2","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10458-004-6975-9","volume":"10","author":"A.L. Bazzan","year":"2005","unstructured":"Bazzan, A.L.: A distributed approach for coordination of traffic signal agents. Autonomous Agents and Multi-Agent Systems\u00a010(1), 131\u2013164 (2005)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Cuay\u00e1huitl, H., Renals, S., Lemon, O., Shimodaira, H.: Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces. Int. Journal of Game Theory, 547\u2013565 (2006)","DOI":"10.21437\/Interspeech.2006-149"},{"key":"9_CR4","unstructured":"Dowling, J.: The Decentralised Coordination of Self-Adaptive Components for Autonomic Distributed Systems. PhD thesis, Trinity College Dublin (2005)"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"He, L., Nort, N.: Hybrid genetic algorithms for telecommunications network back-up routeing. BT Technology Journal\u00a018(4) (October 2000)","DOI":"10.1023\/A:1026702624501"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Humphrys, M.: Action Selection methods using Reinforcement Learning. PhD thesis, University of Cambridge (1996)","DOI":"10.7551\/mitpress\/3118.003.0018"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Kadrovach, B.A., Lamont, G.B.: A particle swarm model for swarm-based networked sensor systems. In: SAC, pp. 918\u2013924 (2002)","DOI":"10.1145\/508791.508968"},{"issue":"1","key":"9_CR8","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MC.2003.1160055","volume":"36","author":"J.O. Kephart","year":"2003","unstructured":"Kephart, J.O., Chess, D.M.: The vision of autonomic computing. Computer\u00a036(1), 41\u201350 (2003)","journal-title":"Computer"},{"issue":"6","key":"9_CR9","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1016\/j.simpat.2007.02.005","volume":"15","author":"D. Meignan","year":"2007","unstructured":"Meignan, D., Simonin, O., Koukam, A.: Simulation and evaluation of urban bus-networks using a multiagent approach. Simulation Modelling Practice and Theory\u00a015(6), 659\u2013671 (2007)","journal-title":"Simulation Modelling Practice and Theory"},{"key":"9_CR10","series-title":"LNAI","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/3-540-45074-2_12","volume-title":"Agents and Peer-to-Peer Computing","author":"A. Montresor","year":"2003","unstructured":"Montresor, A., Meling, H., Babao\u011flu, \u00d6.: Messor: Load-balancing through a swarm of autonomous agents. In: Moro, G., Koubarakis, M. (eds.) AP2PC 2002. LNCS (LNAI), vol.\u00a02530, pp. 125\u2013137. Springer, Heidelberg (2003)"},{"key":"9_CR11","first-page":"601","volume-title":"ICML 2005: Proceedings of the 22nd international conference on Machine learning","author":"S. Natarajan","year":"2005","unstructured":"Natarajan, S., Tadepalli, P.: Dynamic preferences in multi-criteria reinforcement learning. In: ICML 2005: Proceedings of the 22nd international conference on Machine learning, pp. 601\u2013608. ACM, New York (2005)"},{"key":"9_CR12","unstructured":"Oliveira, E., Duarte, N.: Making way for emergency vehicles. In: Proc. of the 2005 European Simulation and Modelling Conference, pp. 128\u2013135 (2005)"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Papageorgiou, M., Diakaki, C., Dinopoulou, V.: Review of road traffic control strategies. Proc. of the IEEE\u00a091(12) (December 2003)","DOI":"10.1109\/JPROC.2003.819610"},{"key":"9_CR14","first-page":"404","volume-title":"AGENTS 2000","author":"M.D. Pendrith","year":"2000","unstructured":"Pendrith, M.D.: Distributed reinforcement learning for a traffic engineering application. In: AGENTS 2000, pp. 404\u2013411. ACM Press, New York (2000)"},{"key":"9_CR15","volume-title":"InterSense 2006","author":"V. Reynolds","year":"2006","unstructured":"Reynolds, V., Cahill, V., Senart, A.: Requirements for an ubiquitous computing simulation and emulation environment. In: InterSense 2006. ACM Press, New York (2006)"},{"key":"9_CR16","unstructured":"Richter, S.: Learning traffic control - towards practical traffic control using policy gradients. Technical report, Albert-Ludwigs-Universit\u00e4t Freiburg (2006)"},{"key":"9_CR17","volume-title":"Aritifical Intelligence - A Modern Approach","author":"S. Russell","year":"2003","unstructured":"Russell, S., Norvig, P.: Aritifical Intelligence - A Modern Approach. Prentice-Hall, Englewood Cliffs (2003)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Salkham, A., Cunningham, R., Garg, A., Cahill, V.: A collaborative reinforcement learning approach to urban traffic control optimization. In: International Conference on Intelligent Agent Technology (December 2008)","DOI":"10.1109\/WIIAT.2008.88"},{"key":"9_CR19","unstructured":"Shelton, C.R.: Balancing multiple sources of reward in reinforcement learning. In: Neural Information Processing Systems 2000, pp. 1082\u20131088 (2000)"},{"key":"9_CR20","unstructured":"Suton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book. MIT Press, Cambridge (2002)"},{"key":"9_CR21","unstructured":"Tesauro, G., Chess, D.M., Walsh, W.E., Das, R., Segal, A., Whalley, I., Kephart, J.O., White, S.R.: A multi-agent systems approach to autonomic computing. In: AAMAS 2004, pp. 464\u2013471 (2004)"},{"key":"9_CR22","first-page":"1151","volume-title":"Proc. of 17th Int. Conf. on Machine Learning","author":"M. Wiering","year":"2000","unstructured":"Wiering, M.: Multi-agent reinforcement learning for traffic light control. In: Proc. of 17th Int. Conf. on Machine Learning, pp. 1151\u20131158. Morgan Kaufmann, San Francisco (2000)"}],"container-title":["Lecture Notes in Computer Science","Autonomic and Trusted Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-02704-8_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T22:56:43Z","timestamp":1710457003000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-02704-8_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642027031","9783642027048"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-02704-8_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}