{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T18:03:24Z","timestamp":1725559404730},"publisher-location":"Berlin, Heidelberg","reference-count":86,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642144110"},{"type":"electronic","value":"9783642144127"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-14412-7_6","type":"book-chapter","created":{"date-parts":[[2010,7,17]],"date-time":"2010-07-17T04:13:53Z","timestamp":1279340033000},"page":"101-126","source":"Crossref","is-referenced-by-count":1,"title":["Multi-policy Optimization in Self-organizing Systems"],"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":"1","key":"6_CR1","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/s11721-008-0022-4","volume":"3","author":"D. Angus","year":"2009","unstructured":"Angus, D., Woodward, C.: Multiple objective ant colony optimisation. Swarm Intelligence\u00a03(1), 69\u201385 (2009)","journal-title":"Swarm Intelligence"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Babaoglu, O., Meling, H., Montresor, A.: Anthill: A framework for the development of agent-based peer-to-peer systems. In: International Conference on Distributed Computing Systems (2002)","DOI":"10.1109\/ICDCS.2002.1022238"},{"key":"6_CR3","first-page":"968","volume-title":"Advances in Neural Information Processing Systems","author":"L. Baird","year":"1999","unstructured":"Baird, L., Moore, A.: Gradient descent for general reinforcement learning. In: Advances in Neural Information Processing Systems, vol.\u00a011, pp. 968\u2013974. MIT Press, Cambridge (1999)"},{"key":"6_CR4","unstructured":"Baran, B., Schaerer, M.: A multiobjective ant colony system for vehicle routing problem with time windows. In: Proceedings of IASTED International Conference on Applied Informatics (2003)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Barrett, L., Narayanan, S.: Learning all optimal policies with multiple criteria. In: ICML 2008: Proceedings of the 25th International Conference on Machine Learning, pp. 41\u201347 (2008)","DOI":"10.1145\/1390156.1390162"},{"issue":"3","key":"6_CR6","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1147\/sj.413.0350","volume":"41","author":"J.P. Bigus","year":"2002","unstructured":"Bigus, J.P., Schlosnagle, D.A., Pilgrim, J.R., Nathaniel Mills III, W., Diao, Y.: Able: A toolkit for building multiagent autonomic systems. IBM Systems Journal\u00a041(3), 350\u2013371 (2002)","journal-title":"IBM Systems Journal"},{"key":"6_CR7","series-title":"Natural Computing Series","volume-title":"Swarm Intelligence: Introduction and Applications","year":"2008","unstructured":"Blum, C., Merkle, D. (eds.): Swarm Intelligence: Introduction and Applications. Natural Computing Series. Springer, Heidelberg (2008)"},{"key":"6_CR8","unstructured":"Brooks, R.: Achieving artificial intelligence through building robots. Technical report, Massachusetts Institute of Technology, Cambridge, MA, USA (1986)"},{"key":"6_CR9","first-page":"225","volume-title":"Architectures for Intelligence","author":"R.A. Brooks","year":"1991","unstructured":"Brooks, R.A.: How to build complete creatures rather than isolated cognitive simulators. In: Architectures for Intelligence, pp. 225\u2013239. Erlbaum, Mahwah (1991)"},{"key":"6_CR10","unstructured":"Busoniu, L., Schutter, B.D., Babuska, R.: Learning and coordination in dynamic multiagent systems. Technical Report 05-019, Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands (October 2005)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Cantu Paz, E., Kamath, C.: An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems\u00a035(5), 915\u2013927 (October 2005)","DOI":"10.1109\/TSMCB.2005.847740"},{"key":"6_CR12","first-page":"746","volume-title":"Proceedings of the Fifteenth National Conference on Artificial Intelligence","author":"C. Claus","year":"1998","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence, pp. 746\u2013752. AAAI Press, Menlo Park (1998)"},{"key":"6_CR13","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/BF03325101","volume":"1","author":"C.A.C. Coello","year":"1999","unstructured":"Coello, C.A.C.: A comprehensive survey of evolutionary-based multiobjective optimization techniques. Knowledge and Information Systems\u00a01, 269\u2013308 (1999)","journal-title":"Knowledge and Information Systems"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Cuayahuitl, H., Renals, S., Lemon, O., Shimodaira, H.: Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces. International Journal of Game Theory, 547\u2013565 (2006)","DOI":"10.21437\/Interspeech.2006-149"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Cui, X., Potok, T., Palathingal, P.: Document clustering using particle swarm optimization. In: Swarm Intelligence Symposium (2005)","DOI":"10.1109\/SIS.2005.1501621"},{"key":"6_CR16","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1613\/jair.530","volume":"9","author":"G. Caro Di","year":"1998","unstructured":"Di Caro, G., Dorigo, M.: AntNet: Distributed Stigmergetic Control for Communication Networks. Journal of Artificial Intelligence Research\u00a09, 317\u2013365 (1998)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"6_CR17","first-page":"443","volume":"16","author":"G. Caro Di","year":"2005","unstructured":"Di Caro, G., Ducatelle, F., Gambardella, L.M.: AntHocNet: An adaptive nature-inspired algorithm for routing in mobile ad hoc networks. European Transactions on Telecommunications, Special Issue on Self-organization in Mobile Networking\u00a016, 443\u2013455 (2005)","journal-title":"European Transactions on Telecommunications, Special Issue on Self-organization in Mobile Networking"},{"issue":"2","key":"6_CR18","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1017\/S0269888905000494","volume":"20","author":"G. Marzo Serugendo Di","year":"2005","unstructured":"Di Marzo Serugendo, G., Gleizes, M.-P., Karageorgos, A.: Self-organization in multi-agent systems. Knowl. Eng. Rev.\u00a020(2), 165\u2013189 (2005)","journal-title":"Knowl. Eng. Rev."},{"issue":"2","key":"6_CR19","first-page":"115","volume":"11","author":"K. Doerner","year":"2003","unstructured":"Doerner, K., Hartl, R., Reimann, M.: Are COMPETants more competent for problem solving? - the case of full truckload transportation. Central European Journal of Operations Research\u00a011(2), 115\u2013141 (2003)","journal-title":"Central European Journal of Operations Research"},{"key":"6_CR20","first-page":"11","volume-title":"The Ant Colony Optimization Meta-Heuristic","author":"M. Dorigo","year":"1999","unstructured":"Dorigo, M., Di Caro, G.D.: The Ant Colony Optimization Meta-Heuristic, pp. 11\u201332. McGraw-Hill, London (1999)"},{"key":"6_CR21","unstructured":"Dowling, J.: The Decentralised Coordination of Self-Adaptive Components for Autonomic Distributed Systems. PhD thesis, Trinity College Dublin (2005)"},{"issue":"3","key":"6_CR22","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1017\/S0269888906000956","volume":"21","author":"J. Dowling","year":"2006","unstructured":"Dowling, J., Cunningham, R., Curran, E., Cahill, V.: Building autonomic systems using collaborative reinforcement learning. Knowledge Engineering Review\u00a021(3), 231\u2013238 (2006)","journal-title":"Knowledge Engineering Review"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Dowling, J., Haridi, S.: Decentralized Reinforcement Learning for the Online Optimization of Distributed Systems. In: Reinforcement Learning. I-Tech Education and Publishing (2008)","DOI":"10.5772\/5279"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Dusparic, I., Cahill, V.: Distributed W-Learning: Multi-policy optimization in self-organizing systems. In: Third IEEE International Conference on Self-Adaptive and Self-Organizing Systems (2009)","DOI":"10.1109\/SASO.2009.23"},{"key":"6_CR25","series-title":"Natural Computing Series","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-05094-1","volume-title":"Introduction to Evolutionary Computing","author":"A. Eiben","year":"2003","unstructured":"Eiben, A., Smith, J.: Introduction to Evolutionary Computing. Natural Computing Series. Springer, Heidelberg (2003)"},{"key":"6_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/11428589_3","volume-title":"Self-star Properties in Complex Information Systems","author":"A.E. Eiben","year":"2005","unstructured":"Eiben, A.E.: Evolutionary computing and autonomic computing: Shared problems, shared solutions? In: Babao\u011flu, \u00d6., Jelasity, M., Montresor, A., Fetzer, C., Leonardi, S., van Moorsel, A., van Steen, M. (eds.) SELF-STAR 2004. LNCS, vol.\u00a03460, pp. 36\u201348. Springer, Heidelberg (2005)"},{"key":"6_CR27","first-page":"197","volume-title":"ICML 1998: Proceedings of the Fifteenth International Conference on Machine Learning","author":"Z. G\u00e1bor","year":"1998","unstructured":"G\u00e1bor, Z., Kalm\u00e1r, Z., Szepesv\u00e1ri, C.: Multi-criteria reinforcement learning. In: ICML 1998: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 197\u2013205. Morgan Kaufmann Publishers Inc., San Francisco (1998)"},{"issue":"1","key":"6_CR28","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1177\/105971230200900102","volume":"9","author":"S.C. Gadanho","year":"2001","unstructured":"Gadanho, S.C., Hallam, J.: Robot learning driven by emotions. Adaptive Behaviour\u00a09(1), 42\u201364 (2001)","journal-title":"Adaptive Behaviour"},{"key":"6_CR29","unstructured":"Gambardella, L.M., Taillard, E., Agazzi, G.: MACS-VRPTW: a multiple ant colony system for vehicle routing problems with time windows, pp. 63\u201376 (1999)"},{"issue":"1","key":"6_CR30","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.ejor.2006.03.041","volume":"180","author":"C. Garcia-Martinez","year":"2007","unstructured":"Garcia-Martinez, C., Cordon, O., Herrera, F.: A taxonomy and an empirical analysis of multiple objective ant colony optimization algorithms for the bi-criteria tsp. European Journal of Operational Research\u00a0180(1), 116\u2013148 (2007)","journal-title":"European Journal of Operational Research"},{"key":"6_CR31","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1145\/860575.860598","volume-title":"AAMAS 2003: Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems","author":"C.V. Goldman","year":"2003","unstructured":"Goldman, C.V., Zilberstein, S.: Optimizing information exchange in cooperative multi-agent systems. In: AAMAS 2003: Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 137\u2013144. ACM, New York (2003)"},{"key":"6_CR32","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1613\/jair.1427","volume":"22","author":"C.V. Goldman","year":"2004","unstructured":"Goldman, C.V., Zilberstein, S.: Decentralized control of cooperative systems: Categorization and complexity analysis. Journal of Artificial Intelligence Research (JAIR)\u00a022, 143\u2013174 (2004)","journal-title":"Journal of Artificial Intelligence Research (JAIR)"},{"key":"6_CR33","unstructured":"Guestrin, C., Koller, D., Parr, R.: Multiagent planning with factored MDPs. In: 14th Neural Information Processing Systems (NIPS-14), Vancouver, Canada, pp. 1523\u20131530 (December 2001)"},{"key":"6_CR34","unstructured":"Guestrin, C., Lagoudakis, M., Parr, R.: Coordinated reinforcement learning. In: Proceedings of the ICML 2002 The Nineteenth International Conference on Machine Learning, pp. 227\u2013234 (2002)"},{"key":"6_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/978-3-540-69158-7_51","volume-title":"Neural Information Processing","author":"K. Hiraoka","year":"2008","unstructured":"Hiraoka, K., Yoshida, M., Mishima, T.: Parallel reinforcement learning for weighted multi-criteria model with adaptive margin. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds.) ICONIP 2007, Part I. LNCS, vol.\u00a04984, pp. 487\u2013496. Springer, Heidelberg (2008)"},{"key":"6_CR36","first-page":"1910","volume-title":"CEC 2002: Proceedings of the Evolutionary Computation on 2002, CEC 2002. Proceedings of the 2002 Congress","author":"R. Hoar","year":"2002","unstructured":"Hoar, R., Penner, J., Jacob, C.: Evolutionary swarm traffic: if ant roads had traffic lights. In: CEC 2002: Proceedings of the Evolutionary Computation on 2002, CEC 2002. Proceedings of the 2002 Congress, Washington, DC, USA, pp. 1910\u20131915. IEEE Computer Society, Los Alamitos (2002)"},{"key":"6_CR37","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":"6_CR38","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1145\/508791.508968","volume-title":"SAC 2002: Proceedings of the 2002 ACM Symposium on Applied Computing","author":"B.A. Kadrovach","year":"2002","unstructured":"Kadrovach, B.A., Lamont, G.B.: A particle swarm model for swarm-based networked sensor systems. In: SAC 2002: Proceedings of the 2002 ACM Symposium on Applied Computing, pp. 918\u2013924. ACM, New York (2002)"},{"key":"6_CR39","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"L.P. Kaelbling","year":"1995","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artificial Intelligence\u00a0101, 99\u2013134 (1995)","journal-title":"Artificial Intelligence"},{"key":"6_CR40","volume-title":"Multi-Objective Optimization Using Evolutionary Algorithms","author":"D. Kalyanmoy","year":"2001","unstructured":"Kalyanmoy, D.: Multi-Objective Optimization Using Evolutionary Algorithms. Wiley, Chichester (2001)"},{"key":"6_CR41","unstructured":"Karlsson, J.: Learning to solve multiple goals. PhD thesis, Rochester, NY, USA (1997)"},{"key":"6_CR42","volume-title":"Swarm Intelligence, The Morgan Kaufmann Series in Artificial Intelligence","author":"J. Kennedy","year":"2001","unstructured":"Kennedy, J., Russell, E.C.: Swarm Intelligence, The Morgan Kaufmann Series in Artificial Intelligence. Morgan Kaufmann, San Francisco (March 2001)"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Kephart, J.O., Walsh, W.E.: An artificial intelligence perspective on autonomic computing policies. In: IEEE International Workshop on Policies for Distributed Systems and Networks (2004)","DOI":"10.1109\/POLICY.2004.1309145"},{"key":"6_CR44","unstructured":"Kok, J.R., \u2019t\u00a0Hoen, P.J., Bakker, B., Vlassis, N.: Utile coordination: learning interdependencies among cooperative agents. In: Proceedings of the IEEE Symposium on Computational Intelligence and Games (CIG), Colchester, United Kingdom, pp. 29\u201336 (April 2005)"},{"key":"6_CR45","first-page":"1789","volume":"7","author":"J.R. Kok","year":"2006","unstructured":"Kok, J.R., Vlassis, N.: Collaborative multiagent reinforcement learning by payoff propagation. Journal of Machine Learning Research\u00a07, 1789\u20131828 (2006)","journal-title":"Journal of Machine Learning Research"},{"key":"6_CR46","unstructured":"Lekavy, M.: Optimising Multi-agent Cooperation using Evolutionary Algorithm. In: Bielikova, M. (ed.) Proceedings of IIT.SRC 2005: Student Research Conference in Informatics and Information Technologies, Bratislava, pp. 49\u201356. Faculty of Informatics and Information Technologies, Slovak University of Technology in Bratislava (April 2005)"},{"key":"6_CR47","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1109\/ICAC.2004.1301380","volume-title":"ICAC 2004: Proceedings of the First International Conference on Autonomic Computing","author":"M.L. Littman","year":"2004","unstructured":"Littman, M.L., Ravi, N., Fenson, E., Howard, R.: Reinforcement learning for autonomic network repair. In: ICAC 2004: Proceedings of the First International Conference on Autonomic Computing, Washington, DC, USA, pp. 284\u2013285. IEEE Computer Society, Los Alamitos (2004)"},{"key":"6_CR48","volume-title":"New Optimization Techniques in Engineering","author":"V. Maniezzo","year":"2004","unstructured":"Maniezzo, V., Gambardella, L.M., Luigi, F.D.: Ant Colony Optimization. In: New Optimization Techniques in Engineering. Springer, Heidelberg (2004)"},{"key":"6_CR49","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1007\/3-540-44399-1_30","volume-title":"Advances in Artificial Intelligence","author":"C. Mariano","year":"2000","unstructured":"Mariano, C., Morales, E.F.: A new distributed reinforcement learning algorithm for multiple objective optimization problems. In: Monard, M.C., Sichman, J.S. (eds.) SBIA 2000 and IBERAMIA 2000. LNCS (LNAI), vol.\u00a01952, pp. 290\u2013299. Springer, Heidelberg (2000)"},{"key":"6_CR50","unstructured":"Melo, F., Veloso, M.: Learning of coordination: Exploiting sparse interactions in multiagent systems. In: Proceedings of the 8th International Conference on Autonomous Agents and Multi-Agent Systems (2009)"},{"key":"6_CR51","doi-asserted-by":"crossref","unstructured":"Mikami, S., Kakazu, Y.: Genetic reinforcement learning for cooperative traffic signal control. In: International Conference on Evolutionary Computation, pp. 223\u2013228 (1994)","DOI":"10.1109\/ICEC.1994.350012"},{"key":"6_CR52","unstructured":"Montresor, A., Meling, H., Babaoglu, O.: Messor: Load-balancing through a swarm of autonomous agents. Technical Report UBLCS-02-08, Departement of Computer Science, University of Bologna, Bologna, Italy (May 2002)"},{"key":"6_CR53","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1145\/1102351.1102427","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":"6_CR54","unstructured":"Oxford. The Oxford English Dictionary. Oxford University Press (2000)"},{"key":"6_CR55","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1007\/978-3-540-24840-8_30","volume-title":"Advances in Artificial Intelligence","author":"S. Paquet","year":"2004","unstructured":"Paquet, S., Bernier, N., Chaib-draa, B.: Multi-attribute decision making in a complex multiagent environment using reinforcement learning with selective perception. In: Tawfik, A.Y., Goodwin, S.D. (eds.) Canadian AI 2004. LNCS (LNAI), vol.\u00a03060, pp. 416\u2013421. Springer, Heidelberg (2004)"},{"key":"6_CR56","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1145\/508791.508907","volume-title":"SAC 2002: Proceedings of the 2002 ACM Symposium on Applied Computing","author":"K.E. Parsopoulos","year":"2002","unstructured":"Parsopoulos, K.E., Vrahatis, M.N.: Particle swarm optimization method in multiobjective problems. In: SAC 2002: Proceedings of the 2002 ACM Symposium on Applied Computing, pp. 603\u2013607. ACM, New York (2002)"},{"key":"6_CR57","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1109\/CCGRID.2008.33","volume-title":"CCGRID 2008: Proceedings of the 2008 Eighth IEEE International Symposium on Cluster Computing and the Grid","author":"J. Perez","year":"2008","unstructured":"Perez, J., Germain-Renaud, C., Kegl, B., Loomis, C.: Grid differentiated services: A reinforcement learning approach. In: CCGRID 2008: Proceedings of the 2008 Eighth IEEE International Symposium on Cluster Computing and the Grid, Washington, DC, USA, pp. 287\u2013294. IEEE Computer Society, Los Alamitos (2008)"},{"key":"6_CR58","first-page":"489","volume-title":"Proceedings of the 16th Annual Conference on Uncertainty in Artificial Intelligence (UAI 2000)","author":"L. Peshkin","year":"2000","unstructured":"Peshkin, L., Eung Kim, K., Meuleau, N., Kaelbling, L.P.: Learning to cooperate via policy search. In: Proceedings of the 16th Annual Conference on Uncertainty in Artificial Intelligence (UAI 2000), pp. 489\u2013496. Morgan Kaufmann, San Francisco (2000)"},{"key":"6_CR59","doi-asserted-by":"crossref","unstructured":"Pugh, J., Zhang, Y., Martinoli, A.: Particle swarm optimization for unsupervised robotic learning. In: Swarm Intelligence Symposium, pp. 92\u201399 (2005)","DOI":"10.1109\/SIS.2005.1501607"},{"issue":"16-18","key":"6_CR60","doi-asserted-by":"publisher","first-page":"2171","DOI":"10.1016\/j.neucom.2005.07.008","volume":"69","author":"P. Raicevic","year":"2006","unstructured":"Raicevic, P.: Parallel reinforcement learning using multiple reward signals. Neurocomputing\u00a069(16-18), 2171\u20132179 (2006)","journal-title":"Neurocomputing"},{"issue":"2","key":"6_CR61","doi-asserted-by":"crossref","first-page":"16","DOI":"10.4018\/jcini.2007040102","volume":"1","author":"A. Ramdane-Cherif","year":"2007","unstructured":"Ramdane-Cherif, A.: Toward autonomic computing: Adaptive neural network for trajectory planning. International Journal of Cognitive Informatics and Natural Intelligence\u00a01(2), 16\u201333 (2007)","journal-title":"International Journal of Cognitive Informatics and Natural Intelligence"},{"issue":"3","key":"6_CR62","first-page":"287","volume":"2","author":"M. Reyes-Sierra","year":"2006","unstructured":"Reyes-Sierra, M., Coello, C.A.C.: Multi-objective particle swarm optimizers: A survey of the state-of-the-art. International Journal of Computational Intelligence Research\u00a02(3), 287\u2013308 (2006)","journal-title":"International Journal of Computational Intelligence Research"},{"key":"6_CR63","unstructured":"Richter, S.: Learning traffic control - towards practical traffic control using policy gradients. Technical report, Albert-Ludwigs-Universitat Freiburg (2006)"},{"issue":"1","key":"6_CR64","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1023\/A:1008916000526","volume":"9","author":"J.K. Rosenblatt","year":"2000","unstructured":"Rosenblatt, J.K.: Optimal selection of uncertain actions by maximizing expected utility. Autonomous Robots\u00a09(1), 17\u201325 (2000)","journal-title":"Autonomous Robots"},{"key":"6_CR65","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":"6_CR66","first-page":"656","volume-title":"International Conference on Machine Learning","author":"S.J. Russell","year":"2003","unstructured":"Russell, S.J., Zimdars, A.: Q-decomposition for reinforcement learning agents. In: Fawcett, T., Mishra, N. (eds.) International Conference on Machine Learning, pp. 656\u2013663. AAAI Press, Menlo Park (2003)"},{"key":"6_CR67","doi-asserted-by":"crossref","unstructured":"Salkham, A., Cunningham, R., Garg, A., Cahill, V.: A collaborative reinforcement learning approach to urban traffic control optimization. In: IEEE\/WIC\/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), vol.\u00a02, pp. 560\u2013566 (2008)","DOI":"10.1109\/WIIAT.2008.88"},{"key":"6_CR68","first-page":"371","volume-title":"Proceedings of the Sixteenth International Conference on Machine Learning","author":"J. Schneider","year":"1999","unstructured":"Schneider, J., Wong, W.-K., Moore, A., Riedmiller, M.: Distributed value functions. In: Proceedings of the Sixteenth International Conference on Machine Learning, pp. 371\u2013378. Morgan Kaufmann, San Francisco (1999)"},{"key":"6_CR69","unstructured":"Shelton, C.R.: Balancing multiple sources of reward in reinforcement learning. In: Neural Information Processing Systems, pp. 1082\u20131088 (2000)"},{"key":"6_CR70","unstructured":"Sprague, N., Ballard, D.: Multiple-goal reinforcement learning with modular Sarsa(0). In: International Joint Conference on Artificial Intelligence (2003)"},{"issue":"3","key":"6_CR71","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1109\/TITS.2006.874716","volume":"7","author":"D. Srinivasan","year":"2006","unstructured":"Srinivasan, D., Choy, M.C., Cheu, R.L.: Neural networks for real-time traffic signal control. IEEE Transactions on Intelligent Transportation Systems\u00a07(3), 261\u2013272 (2006)","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"6_CR72","first-page":"832","volume-title":"IJCAI (2)","author":"D. Subramanian","year":"1998","unstructured":"Subramanian, D., Druschel, P., Chen, J.: Ants and reinforcement learning: A case study in routing in dynamic networks. In: IJCAI (2), pp. 832\u2013838. Morgan Kaufmann, San Francisco (1998)"},{"key":"6_CR73","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Suton","year":"1998","unstructured":"Suton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book\/The MIT Press, Cambridge (1998)"},{"key":"6_CR74","volume-title":"Multiobjective Evolutionary Algorithms and Applications, Advanced Information and Knowledge Processing","author":"K.C. Tan","year":"2005","unstructured":"Tan, K.C., Lee, E.F.K., Heng, T.: Multiobjective Evolutionary Algorithms and Applications, Advanced Information and Knowledge Processing. Springer, New York (2005)"},{"key":"6_CR75","first-page":"330","volume-title":"Proceedings of the Tenth International Conference on Machine Learning","author":"M. Tan","year":"1993","unstructured":"Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative agents. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 330\u2013337. Morgan Kaufmann, San Francisco (1993)"},{"key":"6_CR76","doi-asserted-by":"crossref","unstructured":"Tesauro, G.: Pricing in agent economies using neural networks and multi-agent Q-learning. In: Proceedings of Workshop ABS-3: Learning About, From and With other Agents (1999)","DOI":"10.1007\/3-540-44565-X_13"},{"issue":"1","key":"6_CR77","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MIC.2007.21","volume":"11","author":"G. Tesauro","year":"2007","unstructured":"Tesauro, G.: Reinforcement learning in autonomic computing: A manifesto and case studies. IEEE Internet Computing\u00a011(1), 22\u201330 (2007)","journal-title":"IEEE Internet Computing"},{"key":"6_CR78","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: International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 464\u2013471 (2004)"},{"key":"6_CR79","doi-asserted-by":"crossref","unstructured":"Tesauro, G., Das, R., Walsh, W.E., Kephart, J.O.: Utility-function-driven resource allocation in autonomic systems. In: International Conference on Autonomic Computing, pp. 342\u2013343 (2005)","DOI":"10.1109\/ICAC.2005.65"},{"key":"6_CR80","volume-title":"Proceedings of the Eleventh International Conference on Machine Learning","author":"C.K. Tham","year":"1994","unstructured":"Tham, C.K., Prager, R.W.: A modular Q-learning architecture for manipulator task decomposition. In: Proceedings of the Eleventh International Conference on Machine Learning. Morgan Kaufmann, San Francisco (1994)"},{"issue":"2","key":"6_CR81","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1162\/106365600568158","volume":"8","author":"D.A. Veldhuizen Van","year":"2000","unstructured":"Van Veldhuizen, D.A., Lamont, G.B.: Multiobjective evolutionary algorithms: Analyzing the state-of-the-art. Evolutionary Computation\u00a08(2), 125\u2013147 (2000)","journal-title":"Evolutionary Computation"},{"key":"6_CR82","doi-asserted-by":"crossref","unstructured":"Vlassis, N.: A Concise Introduction to Multiagent Systems and Distributed Artificial Intelligence. Morgan and Claypool Publishers (2007)","DOI":"10.2200\/S00091ED1V01Y200705AIM002"},{"issue":"3","key":"6_CR83","first-page":"279","volume":"8","author":"C.J.C.H. Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Technical note: Q-learning. Machine Learning\u00a08(3), 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"6_CR84","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/BFb0027021","volume-title":"Artificial Neural Networks: An Introduction to ANN Theory and Practice","author":"A.J.M.M. Weijters","year":"1995","unstructured":"Weijters, A.J.M.M., Hoppenbrouwers, G.A.J.: Backpropagation networks for grapheme-phoneme conversion: a non-technical introduction. In: Artificial Neural Networks: An Introduction to ANN Theory and Practice, London, UK, pp. 11\u201336. Springer, Heidelberg (1995)"},{"key":"6_CR85","doi-asserted-by":"crossref","unstructured":"Yagan, D., Tham, C.-K.: Coordinated reinforcement learning for decentralized optimal control. In: IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (2007)","DOI":"10.1109\/ADPRL.2007.368202"},{"key":"6_CR86","doi-asserted-by":"crossref","unstructured":"Yang, Z., Chen, X., Tang, Y., Sun, J.: Intelligent cooperation control of urban traffic networks. In: Proceedings of 2005 International Conference on Machine Learning and Cybernetics, pp. 1482\u20131486 (2005)","DOI":"10.1109\/ICMLC.2005.1527178"}],"container-title":["Lecture Notes in Computer Science","Self-Organizing Architectures"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-14412-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T13:11:26Z","timestamp":1711631486000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-14412-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642144110","9783642144127"],"references-count":86,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-14412-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}