{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T07:12:32Z","timestamp":1780557152083,"version":"3.54.1"},"reference-count":312,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2005,11,1]],"date-time":"2005-11-01T00:00:00Z","timestamp":1130803200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2005,11]]},"DOI":"10.1007\/s10458-005-2631-2","type":"journal-article","created":{"date-parts":[[2005,8,31]],"date-time":"2005-08-31T12:20:35Z","timestamp":1125490835000},"page":"387-434","source":"Crossref","is-referenced-by-count":811,"title":["Cooperative Multi-Agent Learning: The State of the Art"],"prefix":"10.1007","volume":"11","author":[{"given":"Liviu","family":"Panait","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean","family":"Luke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"2631_CR1","doi-asserted-by":"crossref","unstructured":"D. H. Ackley and M. Littman, \u201cAltruism in the evolution of communication,\u201d in Artificial Life IV: Proceedings of the International Workshop on the Synthesis and Simulation of Living Systems, (3rd edn.), MIT Press, 1994.","DOI":"10.7551\/mitpress\/1428.003.0008"},{"key":"2631_CR2","unstructured":"D. Andre, F. Bennett III, and J. Koza, \u201cDiscovery by genetic programming of a cellular automata rule that is better than any known rule for the majority classification problem,\u201d in Genetic Programming 1996: Proceedings of the First Annual Conference, MIT Press, 1996."},{"key":"2631_CR3","doi-asserted-by":"crossref","unstructured":"D. Andre and A. Teller, \u201cEvolving team Darwin United,\u201d in M. Asada and H. Kitano, (eds.), RoboCup-98: Robot Soccer World Cup II, Springer Verlag, 1999.","DOI":"10.1007\/3-540-48422-1_28"},{"key":"2631_CR4","unstructured":"P. Angeline and J. Pollack, \u201cCompetitive environments evolve better solutions for complex tasks,\u201d in S. Forrest, (ed.), Proceedings of the Fifth International Conference on Genetic Algorithms (ICGA), Morgan Kaufmann: San Mateo, CA, pp. 264\u2013270, 1993."},{"issue":"2","key":"2631_CR5","first-page":"406","volume":"84","author":"W. Arthur","year":"1994","journal-title":"Complex. Econ. Theory"},{"key":"2631_CR6","doi-asserted-by":"crossref","unstructured":"T. B\u00e4ck, Evolutionary Algorithms in Theory and Practice: Evolutionary Straegies, Evolutionary Programming, and Genetic Algorithms, Oxford Press, 1996.","DOI":"10.1093\/oso\/9780195099713.001.0001"},{"key":"2631_CR7","unstructured":"T. Balch, Learning roles: Behavioral diversity in robot teams, Technical Report GIT-CC-97-12, Georgia Institute of Technology, 1997."},{"key":"2631_CR8","unstructured":"T. Balch, Behavioral Diversity in Learning Robot Teams, PhD thesis, College of Computing, Georgia Institute of Technology, 1998."},{"key":"2631_CR9","unstructured":"T. Balch, \u201cReward and diversity in multirobot foraging,\u201d in IJCAI-99 Workshop on Agents Learning About, From and With other Agents, 1999."},{"key":"2631_CR10","unstructured":"B. Banerjee, R. Mukherjee, and S. Sen. \u201cLearning mutual trust,\u201d in Working Notes of AGENTS-00 Workshop on Deception, Fraud and Trust in Agent Societies, pp. 9\u201314, 2000."},{"key":"2631_CR11","unstructured":"A. Barto, R. Sutton, and C. Watkins, \u201cLearning and sequential decision making,\u201d in M. Gabriel and J. Moore, (eds.), Learning and Computational Neuroscience: Foundations of Adaptive Networks, MIT Press: Cambridge, MA, 1990."},{"key":"2631_CR12","doi-asserted-by":"crossref","unstructured":"J. Bassett and K. De Jong, \u201cEvolving behaviors for cooperating agents,\u201d in Z. Ras, (ed.), Proceedings from the Twelfth International Symposium on Methodologies for Intelligent Systems, Springer-Verlag: Charlotte, NC, pp. 157\u2013165, 2000.","DOI":"10.1007\/3-540-39963-1_17"},{"key":"2631_CR13","volume-title":"A study of generalization techniques in evolutionary rule learning","author":"J. K. Bassett","year":"2002"},{"key":"2631_CR14","doi-asserted-by":"crossref","unstructured":"R. Beckers, O. E. Holland, and J.-L. Deneubourg. \u201cFrom local actions to global tasks: Stigmergy and collective robotics,\u201d in Artificial Life IV: Proceedings of the International Workshop on the Synthesis and Simulation of Living Systems, (3rd edn.), MIT Press, 1994.","DOI":"10.7551\/mitpress\/1428.003.0022"},{"key":"2631_CR15","unstructured":"M. Benda, V. Jagannathan, and R. Dodhiawala, On optimal cooperation of knowledge sources - an empirical investigation, Technical Report BCS-G2010-28, Boeing Advanced Technology Center, Boeing Computer Services, 1986."},{"key":"2631_CR16","doi-asserted-by":"crossref","unstructured":"H. Berenji and D. Vengerov, \u201cAdvantages of cooperation between reinforcement learning agents in difficult stochastic problems,\u201d in Proceedings of 9th IEEE International Conference on Fuzzy Systems, 2000.","DOI":"10.1109\/FUZZY.2000.839146"},{"key":"2631_CR17","unstructured":"H. Berenji and D. Vengerov, Learning, cooperation, and coordination in multi-agent systems, Technical Report IIS-00-10, Intelligent Inference Systems Corp., 333 W. Maude Avennue, Suite 107, Sunnyvale, CA 94085-4367, 2000."},{"key":"2631_CR18","unstructured":"D. Bernstein, S. Zilberstein, and N. Immerman, \u201cThe complexity of decentralized control of MDPs,\u201d in Proceedings of UAI-2000: The Sixteenth Conference on Uncertainty in Artificial Intelligence, 2000."},{"key":"2631_CR19","unstructured":"H. J. Blumenthal and G. Parker, \u201cCo-evolving team capture strategies for dissimilar robots,\u201d in\u2019Proceedings of Artificial Multiagent Learning. Papers from the 2004 AAAI Fall Symposium. Technical Report FS-04-02, 2004."},{"key":"2631_CR20","doi-asserted-by":"crossref","unstructured":"E. Bonabeau, M. Dorigo, and G. Theraulaz, Swarm Intelligence: From Natural to Artificial Systems, SFI Studies in the Sciences of Complexity, Oxford University Press, 1999.","DOI":"10.1093\/oso\/9780195131581.001.0001"},{"key":"2631_CR21","unstructured":"J. C. Bongard, \u201cThe legion system: A novel approach to evolving heterogeneity for collective problem solving\u201d in R. Poli, W. Banzhaf, W. B. Langdon, J. F. Miller, P. Nordin, and T. C. Fogarty, (eds.), Genetic Programming: Proceedings of EuroGP-2000. Vol. 1802, Edinburgh, 15\u201316 2000. Springer-Verlag. ISBN 3-540-67339-3, pp. 16\u201328."},{"key":"2631_CR22","unstructured":"C. Boutilier, \u201cLearning conventions in multiagent stochastic domains using likelihood estimates,\u201d in\u2019Uncertainty in Artificial Intelligence, pp. 106\u2013114, 1996."},{"key":"2631_CR23","unstructured":"C. Boutilier, \u201cPlanning, learning and coordination in multiagent decision processes,\u201d in Proceedings of the Sixth Conference on Theoretical Aspects of Rationality and Knowledge (TARK96), pp. 195\u2013210, 1996."},{"key":"2631_CR24","unstructured":"M. Bowling, \u201cConvergence problems of general-sum multiagent reinforcement learning,\u201d in\u2019Proceedings of the Seventeenth International Conference on Machine Learning, Morgan Kaufmann: San Francisco, CA, pp. 89\u201394, 2000."},{"key":"2631_CR25","unstructured":"M. Bowling, Multiagent Learning in the Presence of Agents with Limitations, PhD thesis, Computer Science Department, Carnegie Mellon University, 2003."},{"key":"2631_CR26","unstructured":"M. Bowling and M. Veloso, An analysis of stochastic game theory for multiagent reinforcement learning, Technical Report CMU-CS-00\u2013165, Computer Science Department, Carnegie Mellon University, 2000."},{"key":"2631_CR27","unstructured":"M. Bowling and M. Veloso, \u201cRational and convergent learning in stochastic games,\u201d in Proceedings of Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-01), pp. 1021\u20131026, 2001."},{"key":"2631_CR28","unstructured":"M. Bowling and M. Veloso, Existence of multiagent equilibria with limited agents, Technical Report CMU-CS-02-104, Computer Science Department, Carnegie Mellon University, 2002."},{"issue":"2","key":"2631_CR29","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M. Bowling","year":"2002","journal-title":"Artif. Intell"},{"key":"2631_CR30","unstructured":"J. A. Boyan and M. Littman, \u201cPacket routing in dynamically changing networks: A reinforcement learning approach,\u201d in J. D. Cowan, G. Tesauro, and J. Alspector, (eds.), Advances in Neural Information Processing Systems, Vol. 6, Morgan Kaufmann, pp. 671\u2013678, 1994."},{"key":"2631_CR31","unstructured":"R. Brafman and M. Tennenholtz, \u201cEfficient learning equilibrium,\u201d in Advances in Neural Information Processing Systems (NIPS-2002), 2002."},{"key":"2631_CR32","doi-asserted-by":"crossref","unstructured":"W. Brauer and G. Wei\u00df, \u201cMulti-machine scheduling - a multi-agent learning approach,\u201d in Proceedings of the Third International Conference on Multi-Agent Systems, pp. 42\u201348, 1998.","DOI":"10.1109\/ICMAS.1998.699030"},{"key":"2631_CR33","doi-asserted-by":"crossref","unstructured":"P. Brazdil, M. Gams, S. Sian, L. Torgo, and W. van de Velde, \u201cLearning in distributed systems and multi-agent environments,\u201d in Y. Kodratoff, (ed.), Lecture Notes in Artificial Intelligence, Vol. 482, Springer-Verlag, pp. 412\u2013423, 1991.","DOI":"10.1007\/BFb0017034"},{"key":"2631_CR34","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1145\/375735.375826","volume-title":"Proceedings of the Fifth International Conference on Autonomous Agents","author":"O. Buffet","year":"2001"},{"key":"2631_CR35","doi-asserted-by":"crossref","unstructured":"O. Buffet, A. Dutech, and F. Charpillet, \u201cLearning to weigh basic behaviors in scalable agents,\u201d in Proceedings of the 1st International Joint Conference on Autonomous Agents and MultiAgent Systems (AAMAS\u201902), 2002.","DOI":"10.1145\/545056.545111"},{"key":"2631_CR36","doi-asserted-by":"crossref","unstructured":"H. Bui, S. Venkatesh, and D. Kieronska, \u201cA framework for coordination and learning among team of agents,\u201d in W. Wobcke, M. Pagnucco, and C. Zhang, (eds.), Agents and Multi-Agent Systems: Formalisms, Methodologies and Applications, Lecture Notes in Artificial Intelligence. Vol. 1441, Springer-Verlag, pp. 164\u2013178, 1998.","DOI":"10.1007\/BFb0055027"},{"issue":"4","key":"2631_CR37","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1142\/S0218843099000149","volume":"8","author":"H. Bui","year":"1999","journal-title":"Int. J. Coop. Inform. Syst."},{"key":"2631_CR38","unstructured":"L. Bull, \u201cEvolutionary computing in multi-agent environments: Partners,\u201d in T. Back, (ed.), Proceedings of the Seventh International Conference on Genetic Algorithms, Morgan Kaufmann, pp. 370\u2013377, 1997."},{"key":"2631_CR39","doi-asserted-by":"crossref","unstructured":"L. Bull, \u201cEvolutionary computing in multi-agent environments: Operators,\u201d in D. W. V. W. Porto, N. Saravanan, and A. E. Eiben, (eds.), Proceedings of the Seventh Annual Conference on Evolutionary Programming, Springer Verlag, pp. 43\u201352, 1998.","DOI":"10.1007\/BFb0040758"},{"key":"2631_CR40","unstructured":"L. Bull and T. C. Fogarty, \u201cEvolving cooperative communicating classifier systems\u201d, in A. V. Sebald and L. J. Fogel, (eds.), Proceedings of the Fourth Annual Conference on Evolutionary Programming (EP94), pp. 308\u2013315, 1994."},{"key":"2631_CR41","unstructured":"L. Bull and O. Holland, \u201cEvolutionary computing in multiagent environments: Eusociality\u201d, in Proceedings of Seventh Annual Conference on Genetic Algorithms, 1997."},{"issue":"2","key":"2631_CR42","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1109\/4235.918429","volume":"5","author":"A. Cangelosi","year":"2001","journal-title":"IEEE Trans. Evol. Comput."},{"issue":"1","key":"2631_CR43","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1023\/A:1008855018923","volume":"4","author":"Y.U. Cao","year":"1997","journal-title":"Auton. Robots"},{"key":"2631_CR44","unstructured":"D. Carmel, Model-based Learning of Interaction Strategies in Multi-agent systems, PhD thesis, Technion - Israel Institute of Technology, 1997."},{"key":"2631_CR45","unstructured":"D. Carmel and S. Markovitch, The M* algorithm: Incorporating opponent models into adversary search. Technical Report 9402, Technion - Israel Institute of Technology, March 1994"},{"key":"2631_CR46","doi-asserted-by":"crossref","unstructured":"L.-E. Cederman, Emergent Actors in World Politics: How States and Nations Develop and Dissolve, Princeton University Press, 1997","DOI":"10.1515\/9780691218038"},{"key":"2631_CR47","doi-asserted-by":"crossref","unstructured":"G. Chalkiadakis and C. Boutilier, \u201cCoordination in multiagent reinforcement learning: A Bayesian approach,\u201d in Proceedings of The Second International Joint Conference on Autonomous Agents & Multiagent Systems (AAMAS 2003). ACM, 2003. ISBN 1-58113-683-8","DOI":"10.1145\/860575.860689"},{"key":"2631_CR48","doi-asserted-by":"crossref","unstructured":"H. Chalupsky, Y. Gil, C. A. Knoblock, K. Lerman, J. Oh, D. Pynadath, T. Russ, and M. Tambe, \u201cElectric elves: Agent technology for supporting human organizations,\u201d in AI Magazine - Summer 2002, AAAI Press, 2002","DOI":"10.21236\/ADA459956"},{"key":"2631_CR49","unstructured":"Y.-H. Chang, T. Ho, and L. Kaelbling, \u201cAll learning is local: Multi-agent learning in global reward games,\u201d in Proceedings of Neural Information Processing Systems (NIPS-03), 2003"},{"key":"2631_CR50","unstructured":"Y.-H. Chang, T. Ho, and L. Kaelbling, \u201cMulti-agent learning in mobilized ad-hoc networks,\u201d in Proceedings of Artificial Multiagent Learning, Papers from the 2004 AAAI Fall Symposium, Technical Report FS-04-02, 2004"},{"key":"2631_CR51","unstructured":"C. Claus and C. Boutilier, \u201cThe dynamics of reinforcement learning in cooperative multiagent systems,\u201d in Proceedings of National Conference on Artificial Intelligence AAAI\/IAAI, pp. 746\u2013752, 1998"},{"key":"2631_CR52","doi-asserted-by":"crossref","unstructured":"D. Cliff and G. F. Miller, \u201cTracking the red queen: Measurements of adaptive progress in co-evolutionary simulations\u201d, in Proceedings of the Third European Conference on Artificial Life, Springer-Verlag, pp. 200\u2013218, 1995","DOI":"10.1007\/3-540-59496-5_300"},{"key":"2631_CR53","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/BFb0029761","volume-title":"Parallel Problem Solving from Nature: 1st Workshop (PPSN I)","author":"R. Collins","year":"1991"},{"key":"2631_CR54","first-page":"579","volume-title":"Artificial Life II","author":"R. Collins","year":"1992"},{"key":"2631_CR55","unstructured":"E. Crawford and M. Veloso, \u201cOpportunities for learning in multi-agent meeting scheduling\u201d, in Proceedings of Artificial Multiagent Learning, Papers from the 2004 AAAI Fall Symposium. Technical Report FS-04-02, 2004"},{"key":"2631_CR56","unstructured":"V. Crespi, G. Cybenko, M. Santini, and D. Rus. Decentralized control for coordinated flow of multi-agent systems. Technical Report TR2002-414, Dartmouth College, Computer Science, Hanover, NH, January 2002"},{"key":"2631_CR57","unstructured":"R. H. Crites, Large-Scale Dynamic Optimization Using Teams of Reinforcement Learning Agents, PhD thesis, University of Massachusetts Amherst, 1996"},{"key":"2631_CR58","first-page":"46","volume-title":"Readings in Agents","author":"M.R. Cutkosky","year":"1997"},{"key":"2631_CR59","doi-asserted-by":"crossref","unstructured":"T. Dahl, M. Mataric, and G. Sukhatme, \u201cAdaptive spatio-temporal organization in groups of robots,\u201d in Proceedings of the 2002 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS-02), 2002","DOI":"10.1109\/IRDS.2002.1041529"},{"key":"2631_CR60","doi-asserted-by":"crossref","unstructured":"R. Das, M. Mitchell, and J. Crutchfield, \u201cA genetic algorithm discovers particle-based computation in cellular automata\u201d, in Parallel Problem Solving from Nature III, LNCS 866, Springer-Verlag, pp.\u2019344\u2013353, 1994","DOI":"10.1007\/3-540-58484-6_278"},{"key":"2631_CR61","doi-asserted-by":"crossref","unstructured":"J. Davis and G. Kendall, \u201cAn investigation, using co-evolution, to evolve an awari player,\u201d in Proceedings of 2002 Congress on Evolutionary Computation (CEC2002), 2002","DOI":"10.1109\/CEC.2002.1004449"},{"key":"2631_CR62","unstructured":"B. de Boer, \u201cGenerating vowel systems in a population of agents,\u201d in Proceedings of the Fourth European Conference Artificial Life, MIT Press, 1997"},{"key":"2631_CR63","volume-title":"An Analysis of the Behavior of a Class of Genetic Adaptive Systems","author":"K. Jong De","year":"1975"},{"key":"2631_CR64","unstructured":"K. De Jong, Evolutionary Computation: A Unified Approach, MIT Press, 2005"},{"key":"2631_CR65","doi-asserted-by":"crossref","unstructured":"K. Decker, E. Durfee, and V. Lesser, \u201cEvaluating research in cooperative distributed problem solving,\u201d in L. Gasser and M. Huhns, (eds.), Distributed Artificial Intelligence Volume II, Pitman Publishing and Morgan Kaufmann, pp. 487\u2013519, 1989","DOI":"10.1016\/B978-1-55860-092-8.50023-X"},{"issue":"3","key":"2631_CR66","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1017\/S026988899900301X","volume":"14","author":"K. Decker","year":"1999","journal-title":"Knowl. Eng. Rev."},{"key":"2631_CR67","doi-asserted-by":"crossref","unstructured":"J. L. Deneubourg, S. Goss, N. Franks, A. Sendova-Franks, C. Detrain, and L. Chretien, \u201cThe dynamics of collective sorting: Robot-like ants and ant-like robots,\u201d in From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior, MIT Press, pp.\u2019356\u2013363, 1991","DOI":"10.7551\/mitpress\/3115.003.0048"},{"key":"2631_CR68","unstructured":"J. Denzinger and M. Fuchs, \u201cExperiments in learning prototypical situations for variants of the pursuit game,\u201d in Proceedings on the International Conference on Multi-Agent Systems (ICMAS-1996), pp. 48\u201355, 1996"},{"key":"2631_CR69","unstructured":"M. Dowell. Learning in Multiagent Systems, PhD thesis, University of South Carolina, 1995"},{"key":"2631_CR70","doi-asserted-by":"crossref","unstructured":"K. Dresner and P. Stone, \u201cMultiagent traffic management: A reservation-based intersection control mechanism,\u201d in AAMAS-2004 - Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems, 2004","DOI":"10.1145\/1082473.1082545"},{"key":"2631_CR71","doi-asserted-by":"crossref","unstructured":"G. Dudek, M. Jenkin, R. Milios, and D. Wilkes, \u201cA taxonomy for swarm robots,\u201d in Proceedings of IEEE\/RSJ Conference on Intelligent Robots and Systems, 1993","DOI":"10.1109\/IROS.1993.583135"},{"key":"2631_CR72","unstructured":"E. Durfee, \u201cWhat your computer really needs to know, you learned in kindergarten,\u201d in National Conference on Artificial Intelligence, pp. 858\u2013864, 1992"},{"issue":"11","key":"2631_CR73","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1109\/TC.1987.5009468","volume":"C-36","author":"E. Durfee","year":"1987","journal-title":"IEEE Trans. Comput"},{"issue":"1","key":"2631_CR74","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1109\/69.43404","volume":"KDE-1","author":"E. Durfee","year":"March 1989","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2631_CR75","unstructured":"A. Dutech, O. Buffet, and F. Charpillet, \u201cMulti-agent systems by incremental gradient reinforcement learning,\u201d in Proceedings of Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-01), pp. 833\u2013838, 2001"},{"issue":"4","key":"2631_CR76","first-page":"217","volume":"16","author":"F. Fernandez","year":"2001","journal-title":"Int. J. Robot. Autom."},{"key":"2631_CR77","first-page":"238","volume-title":"Proceedings of the Sixth International Conference on Artificial Life","author":"S. Ficici","year":"1998"},{"key":"2631_CR78","doi-asserted-by":"crossref","unstructured":"S. Ficici and J. Pollack, \u201cA game-theoretic approach to the simple coevolutionary algorithm\u201d, in Proceedings of the Sixth International Conference on Parallel Problem Solving from Nature (PPSN VI). Springer Verlag, 2000","DOI":"10.1007\/3-540-45356-3_46"},{"key":"2631_CR79","doi-asserted-by":"crossref","unstructured":"K. Fischer, N. Kuhn, H. J. Muller, J. P. Muller, and M. Pischel, \u201cSophisticated and distributed: The transportation domain,\u201d in Proceedings of the Fifth European Workshop on Modelling Autonomous Agents in a Multi-Agent World (MAAMAW\u201993), 1993","DOI":"10.1109\/CAIA.1993.366629"},{"key":"2631_CR80","unstructured":"D. Fogel, Blondie24: Playing at the Edge of Artificial Intelligence, Morgan Kaufmann, 2001. ISBN 1-55860-783-8"},{"key":"2631_CR81","unstructured":"L. Fogel, Intelligence Through Simulated Evolution: Forty Years of Evolutionary Programming, Wiley Series on Intelligent Systems, 1999"},{"key":"2631_CR82","unstructured":"D. Fudenberg and D. Levine, The Theory of Learning in Games, MIT Press, 1998"},{"key":"2631_CR83","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1023\/B:AGNT.0000018808.95119.9e","volume":"8","author":"A. Garland","year":"2004","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"2631_CR84","unstructured":"M. Ghavamzadeh and S. Mahadevan, \u201cLearning to communicate and act using hierarchical reinforcement learning,\u201d in AAMAS-2004 - Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems, 2004"},{"issue":"3","key":"2631_CR85","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1038\/scientificamerican0394-76","volume":"270","author":"N. Glance","year":"1994","journal-title":"Sci. Am."},{"key":"2631_CR86","unstructured":"P. Gmytrasiewicz, A Decision-Theoretic Model of Coordination and Communication in Autonomous Systems (Reasoning Systems), PhD thesis, University of Michigan, 1992"},{"key":"2631_CR87","volume-title":"Genetic Algorithms in Search, Optimization, and Machine Learning","author":"D. E. Goldberg","year":"1989"},{"key":"2631_CR88","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/3-540-60923-7_20","volume-title":"Adaptation and Learning in Multi-Agent Systems","author":"C. Goldman","year":"1996"},{"key":"2631_CR89","unstructured":"B. M. Good, Evolving multi-agent systems: Comparing existing approaches and suggesting new directions, Master\u2019s thesis, University of Sussex, 2000"},{"key":"2631_CR90","unstructured":"M. Gordin, S. Sen, and N. Puppala, \u201cEvolving cooperative groups: Preliminary results\u201d, in Working Papers of the AAAI-97 Workshop on Multiagent Learning, pp. 31\u201335, 1997"},{"issue":"1","key":"2631_CR91","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1023\/A:1010042522104","volume":"1","author":"S. Grand","year":"1998","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"2631_CR92","doi-asserted-by":"crossref","unstructured":"S. Grand, D. Cliff, and A. Malhotra, \u201cCreatures : Artificial life autonomous software agents for home entertainment\u201d, in Proceedings of the First International Conference on Autonomous Agents (Agents-97), pp. 22\u201329, 1997","DOI":"10.1145\/267658.267663"},{"key":"2631_CR93","unstructured":"D. L. Grecu, Using Learning to Improve Multi-Agent Systems for Design. PhD thesis, Worcester Polytechnic Institute, 1997"},{"key":"2631_CR94","unstructured":"A. Greenwald, J. Farago, and K. Hall, \u201cFair and efficient solutions to the Santa Fe bar problem,\u201d in\u2019Proceedings of the Grace Hopper Celebration of Women in Computing 2002, 2002"},{"key":"2631_CR95","unstructured":"A. Greenwald and K. Hall, \u201cCorrelated Q-learning,\u201d in Proceedings of the Twentieth International Conference on Machine Learning, 2003"},{"key":"2631_CR96","first-page":"303","volume-title":"Proceedings of the Fourth International Conference on Genetic Algorithms","author":"J. Grefenstette","year":"1991"},{"key":"2631_CR97","first-page":"355","volume":"5","author":"J. Grefenstette","year":"1990","journal-title":"Machine Learn."},{"key":"2631_CR98","unstructured":"C. Guestrin, M. Lagoudakis, and R. Parr, \u201cCoordinated reinforcement learning,\u201d in Proceedings of the 2002 AAAI Symposium Series: Collaborative Learning Agents, 2002"},{"key":"2631_CR99","volume-title":"Layered learning in genetic programming for a co-operative robot soccer problem","author":"S.M. Gustafson","year":"2000"},{"key":"2631_CR100","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/3-540-45355-5_23","volume-title":"Genetic Programming: Proceedings of EuroGP-2001","author":"S.M. Gustafson","year":"2001"},{"key":"2631_CR101","unstructured":"A. Hara and T. Nagao, \u201cEmergence of cooperative behavior using ADG; Automatically Defined Groups,\u201d in Proceedings of the 1999 Genetic and Evolutionary Computation Conference (GECCO-99), pp. 1038\u20131046, 1999"},{"key":"2631_CR102","unstructured":"I. Harvey, P. Husbands, D. Cliff, A. Thompson, and N. Jakobi, \u201cEvolutionary robotics: The Sussex approach,\u201d Robot. Auton. Syst., 1996"},{"key":"2631_CR103","unstructured":"T. Haynes, K. Lau, and S. Sen, \u201cLearning cases to compliment rules for conflict resolution in multiagent systems,\u201d in S. Sen, (ed.), AAAI Spring Symposium on Adaptation, Coevolution, and Learning in Multiagent Systems, pp. 51\u201356, 1996"},{"key":"2631_CR104","volume-title":"Adaptation and Learning in Multiagent Systems, Lecture Notes in Artificial Intelligence","author":"Haynes T.","year":"1995"},{"key":"2631_CR105","unstructured":"T. Haynes and S. Sen, \u201cAdaptation using cases in cooperative groups,\u201d in I. Imam (ed.), Working Notes of the AAAI-96 Workshop on Intelligent Adaptive Agents, Portland, OR, 1996"},{"key":"2631_CR106","unstructured":"T. Haynes and S. Sen, Cooperation of the fittest, Technical Report UTULSA-MCS-96-09, The University of Tulsa, Apr. 12, 1996"},{"key":"2631_CR107","unstructured":"T. Haynes and S. Sen, \u201cLearning cases to resolve conflicts and improve group behavior,\u201d in M. Tambe and P. Gmytrasiewicz, (eds.), Working Notes of the AAAI-96 Workshop on Agent Modeling, Portland, OR, pp. 46\u201352, 1996"},{"key":"2631_CR108","unstructured":"T. Haynes and S. Sen, \u201cCrossover operators for evolving a team,\u201d in J. R. Koza, K. Deb, M. Dorigo, D. B. Fogel, M. Garzon, H. Iba, and R. L. Riolo, (eds.), Genetic Programming 1997: Proceedings of the Second Annual Conference, Morgan Kaufmann: Stanford University, CA, USA, pp. 162\u2013167, 13\u201316 July 1997"},{"key":"2631_CR109","unstructured":"T. Haynes, S. Sen, D. Schoenefeld, and R. Wainwright, \u201cEvolving a team,\u201d in E. V. Siegel and J. R. Koza, (eds.), Working Notes for the AAAI Symposium on Genetic Programming, AAAI: MIT, Cambridge, MA, USA, pp. 23\u201330, 10\u201312 Nov. 1995"},{"key":"2631_CR110","unstructured":"T. Haynes, S. Sen, D. Schoenefeld, and R. Wainwright, Evolving multiagent coordination strategies with genetic programming, Technical Report UTULSA-MCS-95\u201304, The University of Tulsa, May 31, 1995"},{"key":"2631_CR111","unstructured":"T. Haynes, R. Wainwright, S. Sen, and D. Schoenefeld, \u201cStrongly typed genetic programming in evolving cooperation strategies,\u201d in L. Eshelman, (ed.), Genetic Algorithms: Proceedings of the Sixth International Conference (ICGA95), Morgan Kaufmann: Pittsburgh, PA, USA, pp. 271\u2013278, ISBN 1-55860-370-0, 15-19 July 1995"},{"key":"2631_CR112","unstructured":"T. D. Haynes and S. Sen, \u201cCo-adaptation in a team,\u201d Int. J. Comput. Intell. Org. (IJCIO), 1997"},{"key":"2631_CR113","first-page":"313","volume":"10","author":"D. Hillis","year":"1991","journal-title":"Artif. Life II, SFI Stud. Sci. Complex."},{"key":"2631_CR114","volume-title":"Adaptation in Natural and Artificial Systems","author":"J. Holland","year":"1975"},{"key":"2631_CR115","unstructured":"J. Holland, \u201cProperties of the bucket brigade,\u201d in Proceedings of an International Conference on Genetic Algorithms, 1985"},{"key":"2631_CR116","doi-asserted-by":"crossref","unstructured":"B. H\u00f6lldobler and E. O. Wilson, The Ants, Harvard University Press, 1990","DOI":"10.1007\/978-3-662-10306-7"},{"key":"2631_CR117","unstructured":"W. H. Hsu and S. M. Gustafson, \u201cGenetic programming and multi-agent layered learning by reinforcements,\u201d in W. B. Langdon, E. Cant\u00fa-Paz, K. Mathias, R. Roy, D. Davis, R. Poli, K.\u2019Balakrishnan, V. Honavar, G. Rudolph, J. Wegener, L. Bull, M. Potter, A. C. Schultz, J. F. Miller, E. Burke, and N. Jonoska, (eds.), GECCO 2002: Proceedings of the Genetic and Evolutionary Computation Conference, Morgan Kaufmann Publishers: New York, 9-13 July 2002, ISBN 1-55860-878-8, pp. 764-771"},{"key":"2631_CR118","unstructured":"J. Hu and M. Wellman, \u201cSelf-fulfilling bias in multiagent learning,\u201d in Proceedings of the Second International Conference on Multi-Agent Systems, 1996"},{"key":"2631_CR119","unstructured":"J. Hu and M. Wellman, \u201cMultiagent reinforcement learning: Theoretical framework and an algorithm,\u201d in Proceedings of the Fifteenth International Conference on Machine Learning, Morgan Kaufmann: San Francisco, CA, pp. 242\u2013250, 1998"},{"key":"2631_CR120","doi-asserted-by":"crossref","unstructured":"J. Hu and M. Wellman, \u201cOnline learning about other agents in a dynamic multiagent system,\u201d in K.\u2019P. Sycara and M. Wooldridge, (eds.), Proceedings of the Second International Conference on Autonomous Agents (Agents\u201998), ACM Press: New York, 1998, pp. 239\u2013246, ISBN 0-89791-983-1","DOI":"10.1145\/280765.280839"},{"key":"2631_CR121","first-page":"1039","volume":"4","author":"J. Hu","year":"2003","journal-title":"J. Machine Learn. Res."},{"key":"2631_CR122","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/3-540-58855-8_14","volume-title":"Intelligent Agents: Theories, Architectures, and Languages (LNAI Volume 890)","author":"J. Huang","year":"1995"},{"key":"2631_CR123","unstructured":"M. Huhns and M. Singh, \u201cAgents and multiagent systems: Themes, approaches and challenges,\u201d in\u2019M. Huhns and M. Singh, (eds.), Readings in Agents, Morgan Kaufmann, pp. 1\u201323, 1998"},{"key":"2631_CR124","doi-asserted-by":"crossref","unstructured":"M. Huhns and G. Wei\u00df, \u201cSpecial issue on multiagent learning,\u201d Machine Learn. J., vol. 33, nos. 2\u20133, 1998","DOI":"10.1023\/A:1007547205842"},{"key":"2631_CR125","unstructured":"H. Iba, \u201cEmergent cooperation for multiple agents using genetic programming,\u201d in H.-M. Voigt, W. Ebeling, I. Rechenberg, and H.-P. Schwefel, (eds.), Parallel Problem Solving from Nature IV: Proceedings of the International Conference on Evolutionary Computation, Vol. 1141 of LNCS, Springer Verlag: Berlin, Germany, 1996, pp. 32\u201341, ISBN 3-540-61723-X"},{"key":"2631_CR126","doi-asserted-by":"crossref","unstructured":"H. Iba, \u201cEvolutionary learning of communicating agents,\u201d Inform. Sci., vol. 108, 1998","DOI":"10.1016\/S0020-0255(97)10055-X"},{"key":"2631_CR127","first-page":"447","volume-title":"Advances in Genetic Programming 3","author":"H. Iba","year":"1999"},{"key":"2631_CR128","unstructured":"I. Imam, (ed.), Intelligent Adaptive Agents. Papers from the 1996 AAAI Workshop. Technical Report WS-96-04, AAAI Press, 1996"},{"key":"2631_CR129","unstructured":"A. Ito, \u201cHow do selfish agents learn to cooperate?,\u201d in Artificial Life V: Proceedings of the Fifth International Workshop on the Synthesis and Simulation of Living Systems, MIT Press, pp. 185\u2013192, 1997"},{"key":"2631_CR130","doi-asserted-by":"crossref","unstructured":"T. Jansen and R. P. Wiegand, \u201cExploring the explorative advantage of the cooperative coevolutionary (1+1) EA,\u201d in E. Cantu-Paz et al., (ed.), Prooceedings of the Genetic and Evolutionary Computation Conference (GECCO), Springer-Verlag, 2003","DOI":"10.1007\/3-540-45105-6_37"},{"key":"2631_CR131","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1023\/A:1010090405266","volume":"1","author":"N. Jennings","year":"1998","journal-title":"Auton Agents Multi-Agent Syst."},{"issue":"4","key":"2631_CR132","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/0952-1976(93)90016-Q","volume":"6","author":"N. Jennings","year":"1993","journal-title":"Int. J. Eng. Appl. Artif. Intell."},{"issue":"3","key":"2631_CR133","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1162\/106454600568861","volume":"6","author":"K.-C. Jim","year":"2000","journal-title":"Artif. Life"},{"key":"2631_CR134","unstructured":"H. Juille and J. Pollack, \u201cCoevolving the \u201cideal\u201d trainer: Application to the discovery of cellular automata rules\u201d, in Proceedings of the Third Annual Genetic Programming Conference (GP-98), 1998"},{"key":"2631_CR135","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L. Kaelbling","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"2631_CR136","doi-asserted-by":"crossref","unstructured":"S. Kapetanakis and D. Kudenko, Improving on the reinforcement learning of coordination in cooperative multi-agent systems, in Proceedings of the Second Symposium on Adaptive Agents and Multi-agent Systems (AISB02), 2002","DOI":"10.1007\/3-540-44826-8_2"},{"key":"2631_CR137","doi-asserted-by":"crossref","unstructured":"S. Kapetanakis and D. Kudenko, \u201cReinforcement learning of coordination in cooperative multi-agent systems\u201d, in Proceedings of the Nineteenth National Conference on Artificial Intelligence (AAAI02), 2002","DOI":"10.1007\/3-540-44826-8_2"},{"key":"2631_CR138","doi-asserted-by":"crossref","unstructured":"G. Kendall and G. Whitwell, \u201cAn evolutionary approach for the tuning of a chess evaluation function using population dynamics,\u201d in Proceedings of the 2001 Congress on Evolutionary Computation (CEC-2001), IEEE Press, pp. 995\u20131002, 27\u201330, 2001","DOI":"10.1109\/CEC.2001.934299"},{"key":"2631_CR139","doi-asserted-by":"crossref","unstructured":"G. Kendall and M. Willdig, \u201cAn investigation of an adaptive poker player\u201d, in Proceedings of the 14th Australian Joint Conference on Artificial Intelligence (AI\u201901), 2001","DOI":"10.1007\/3-540-45656-2_17"},{"key":"2631_CR140","doi-asserted-by":"crossref","unstructured":"H. Kitano, M. Asada, Y. Kuni\u0177oshi, I. Noda, and E. Osawa, \u201cRoboCup: The robot world cup initiative,\u201d in W. L. Johnson and B. Hayes-Roth, (eds.), Proceedings of the First International Conference on Autonomous Agents (Agents\u201997), ACM Press: New York, 5-8, ISBN 0-89791-877-0, pp.\u2019340-347, 1997","DOI":"10.1145\/267658.267738"},{"key":"2631_CR141","unstructured":"J. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection, MIT Press, 1992"},{"key":"2631_CR142","unstructured":"M. Lauer and M. Riedmiller, \u201cAn algorithm for distributed reinforcement learning in cooperative multi-agent systems,\u201d in Proceedings of the Seventeenth International Conference on Machine Learning, Morgan Kaufmann: San Francisco, CA, pp. 535\u2013542, 2000"},{"key":"2631_CR143","unstructured":"L. R. Leerink, S. R. Schultz, and M. A. Jabri, \u201cA reinforcement learning exploration strategy based on ant foraging mechanisms,\u201d in Proceedings of the Sixth Australian Conference on Neural Networks, Sydney, Australia, 1995"},{"issue":"1","key":"2631_CR144","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1109\/69.755622","volume":"11","author":"V. Lesser","year":"1999","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2631_CR145","unstructured":"V. Lesser, D. Corkill, and E. Durfee, An update on the distributed vehicle monitoring testbed, Technical Report UM-CS-1987-111, University of Massachessets Amherst, 1987"},{"key":"2631_CR146","doi-asserted-by":"crossref","unstructured":"M. I. Lichbach, The Cooperator\u2019s Dilemma, University of Michigan Press, 1996. ISBN 0472105728","DOI":"10.3998\/mpub.13808"},{"key":"2631_CR147","doi-asserted-by":"crossref","unstructured":"M. Littman, \u201cMarkov games as a framework for multi-agent reinforcement learning\u201d, in Proceedings of the 11th International Conference on Machine Learning (ML-94), Morgan Kaufmann: New Brunswick, NJ, pp. 157\u2013163, 1994","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"2631_CR148","unstructured":"M. Littman, \u201cFriend-or-foe Q-learning in general-sum games,\u201d in Proceedings of the Eighteenth International Conference on Machine Learning, Morgan Kaufmann, pp. 322\u2013328, 2001"},{"key":"2631_CR149","unstructured":"A. Lubberts and R. Miikkulainen, \u201cCo-evolving a go-playing neural network,\u201d in Coevolution: Turning Adaptive Algorithms upon Themselves, (Birds-on-a-Feather Workshop, Genetic and Evolutionary Computation Conference), 2001"},{"issue":"3","key":"2631_CR150","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1017\/S0269888998003014","volume":"13","author":"M. Luck","year":"1998","journal-title":"Knowl. Eng. Rev."},{"key":"2631_CR151","unstructured":"S. Luke, \u201cGenetic programming produced competitive soccer softbot teams for RoboCup97,\u201d in J. R. Koza et al, (ed.), Genetic Programming 1998: Proceedings of the Third Annual Conference, Morgan Kaufmann, pp. 214\u2013222, 1998"},{"key":"2631_CR152","doi-asserted-by":"crossref","unstructured":"S. Luke, C. Hohn, J. Farris, G. Jackson, and J. Hendler, \u201cCo-evolving soccer softbot team coordination with genetic programming,\u201d in Proceedings of the First International Workshop on RoboCup, at\u2019the International Joint Conference on Artificial Intelligence, Nagoya, Japan, 1997","DOI":"10.1007\/3-540-64473-3_76"},{"key":"2631_CR153","doi-asserted-by":"crossref","unstructured":"S. Luke and L. Spector, \u201cEvolving teamwork and coordination with genetic programming,\u201d in J. R. Koza, D. E. Goldberg, D. B. Fogel, and R. L. Riolo, (eds.), Genetic Programming 1996: Proceedings of the First Annual Conference, MIT Press: Stanford University, CA, USA, pp. 150\u2013156, 28-31 1996","DOI":"10.7551\/mitpress\/3242.003.0021"},{"key":"2631_CR154","doi-asserted-by":"crossref","unstructured":"S. Luke, K. Sullivan, G. C. Balan, and L. Panait, Tunably decentralized algorithms for cooperative target observation, Technical Report GMU-CS-TR-2004-1, Department of Computer Science, George Mason University, 2004","DOI":"10.1145\/1082473.1082611"},{"key":"2631_CR155","unstructured":"S. Luke and R. P. Wiegand, \u201cGuaranteeing coevolutionary objective measures\u201d, in Poli et al. [201], pp. 237\u2013251"},{"key":"2631_CR156","unstructured":"S. Mahadevan and J. Connell, \u201cAutomatic programming of behavior-based robots using reinforcement learning,\u201d in National Conference on Artificial Intelligence, pp. 768\u2013773, 1991"},{"key":"2631_CR157","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1145\/375735.376302","volume-title":"Proceedings of the Fifth International Conference on Autonomous Agents","author":"R. Makar","year":"2001"},{"key":"2631_CR158","doi-asserted-by":"crossref","DOI":"10.21236\/ADA290049","volume-title":"Interaction and Intelligent Behavior","author":"M. Mataric","year":"1994"},{"key":"2631_CR159","doi-asserted-by":"crossref","unstructured":"M. Mataric, \u201cLearning to behave socially,\u201d in Third International Conference on Simulation of Adaptive Behavior, 1994","DOI":"10.7551\/mitpress\/3117.003.0065"},{"key":"2631_CR160","doi-asserted-by":"crossref","unstructured":"M. Mataric, \u201cReward functions for accelerated learning,\u201d in International Conference on Machine Learning, pp. 181\u2013189, 1994","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"2631_CR161","doi-asserted-by":"crossref","unstructured":"M. Mataric, \u201cReinforcement learning in the multi-robot domain,\u201d Auton. Robots, vol. 4, no. 1, pp.\u201973\u201383, 1997","DOI":"10.1007\/978-1-4757-6451-2_4"},{"key":"2631_CR162","unstructured":"M. Mataric, \u201cUsing communication to reduce locality in distributed multi-agent learning,\u201d Joint Special Issue on Learn Auton. Robots, Machine Learn, vol. 31, nos. 1-3, pp. 141\u2013167, and Auton. Robots, vol. 5, nos. 3-4, pp. 335\u2013354, Jul\/Aug 1998"},{"key":"2631_CR163","doi-asserted-by":"crossref","unstructured":"M. Mataric, M. Nilsson, and K. Simsarian, \u201cCooperative multi-robot box-pushing,\u201d in Proceedings of IEEE\/RSJ Conference on Intelligent Robots and Systems, pp. 556\u2013561, 1995","DOI":"10.1109\/IROS.1995.525940"},{"key":"2631_CR164","doi-asserted-by":"crossref","unstructured":"Z. Michalewicz, Genetic Algorithms + Data Structures = Evolution Programs (3rd edn.), Springer-Verlag: Berlin, 1996","DOI":"10.1007\/978-3-662-03315-9"},{"key":"2631_CR165","unstructured":"T. Miconi, \u201cA collective genetic algorithm\u201d, in E. Cantu-Paz et al., (ed.), Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pp. 876\u2013883, 2001"},{"key":"2631_CR166","unstructured":"T. Miconi, \u201cWhen evolving populations is better than coevolving individuals: The blind mice problem,\u201d in Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-03), 2003"},{"key":"2631_CR167","unstructured":"M. Mitchell, J. Crutchfield, and R. Das, \u201cEvolving cellular automata with genetic algorithms: A\u2019review of recent work,\u201d in Proceedings of the First International Conference on Evolutionary Computation and its Applications (EvCA\u201996), 1996"},{"key":"2631_CR168","doi-asserted-by":"crossref","unstructured":"N. Monekosso, P. Remagnino, and A. Szarowicz, \u201cAn improved Q-learning algorithm using synthetic pheromones,\u201d in E. N. B. Dunin-Keplicz, (ed.), From Theory to Practice in Multi-Agent Systems, Second International Workshop of Central and Eastern Europe on Multi-Agent Systems, CEEMAS 2001 Cracow, Poland, September 26\u201329, 2001. Revised Papers, Lecture Notes in Artificial Intelligence LNAI-2296, Springer-Verlag, 2002","DOI":"10.1007\/3-540-45941-3_21"},{"key":"2631_CR169","doi-asserted-by":"crossref","unstructured":"N. D. Monekosso and P. Remagnino, \u201cPhe-Q: A pheromone based Q-learning,\u201d in Australian Joint Conference on Artificial Intelligence, pp. 345\u2013355, 2001","DOI":"10.1007\/3-540-45656-2_30"},{"key":"2631_CR170","doi-asserted-by":"crossref","unstructured":"N. D. Monekosso and P. Remagnino, \u201cAn analysis of the pheromone Q-learning algorithm,\u201d in\u2019Proceedings of the VIII Iberoamerican Conference on Artificial Intelligence IBERAMIA-02, pp. 224\u2013232, 2002","DOI":"10.1007\/3-540-36131-6_23"},{"key":"2631_CR171","doi-asserted-by":"crossref","unstructured":"N. D. Monekosso, P. Remagnino, and A. Szarowicz, \u201cAn improved Q-learning algorithm using synthetic pheromones,\u201d in Proceedings of the Second Workshop of Central and Eastern Europe on Multi-Agent Systems CEEMAS-01, pp. 197\u2013206, 2001","DOI":"10.1007\/3-540-45941-3_21"},{"key":"2631_CR172","unstructured":"J. Moody, Y. Liu, M. Saffell, and K. Youn, \u201cStochastic direct reinforcement: Application to simple games with recurrence,\u201d in Proceedings of Artificial Multiagent Learning, Papers from the 2004 AAAI Fall Symposium. Technical Report FS-04-02, 2004"},{"key":"2631_CR173","unstructured":"R. Mukherjee and S. Sen, \u201cTowards a pareto-optimal solution in general-sum games,\u201d in Agents-2001 Workshop on Learning Agents, 2001"},{"key":"2631_CR174","doi-asserted-by":"crossref","unstructured":"U. Mukhopadjyay, L. Stephens, and M. Huhns, \u201cAn intelligent system for document retrieval in distributed office environment,\u201d J. Am. Soc. Inform Sci., vol. 37, 1986","DOI":"10.1002\/(SICI)1097-4571(198605)37:3<123::AID-ASI3>3.0.CO;2-3"},{"issue":"1","key":"2631_CR175","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1142\/S021821579400003X","volume":"3","author":"J. Muller","year":"1994","journal-title":"J. Intell. Coop. Inform. Syst."},{"key":"2631_CR176","doi-asserted-by":"crossref","unstructured":"M. Mundhe and S. Sen, \u201cEvaluating concurrent reinforcement learners,\u201d in Proceedings of the International Conference on Multiagent System, 2000","DOI":"10.1109\/ICMAS.2000.858505"},{"key":"2631_CR177","unstructured":"M. Mundhe and S. Sen, \u201cEvolving agent societies that avoid social dilemmas,\u201d in D. Whitley, D.\u2019Goldberg, E. Cantu-Paz, L. Spector, I. Parmee, and H.-G. Beyer, (eds.), Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2000), Morgan Kaufmann: Las Vegas, Nevada, USA, 10-12 2000, pp. 809\u2013816, ISBN 1-55860-708-0"},{"key":"2631_CR178","doi-asserted-by":"crossref","unstructured":"Y. Nagayuki, S. Ishii, and K. Doya, \u201cMulti-agent reinforcement learning: An approach based on the other agent\u2019s internal model,\u201d in Proceedings of the International Conference on Multi-Agent Systems (ICMAS-00), 2000","DOI":"10.1109\/ICMAS.2000.858456"},{"key":"2631_CR179","unstructured":"M. V. Nagendra-Prasad, Learning Situation-Specific Control in Multi-Agent Systems, PhD thesis, University of Massachusetts Amherst, 1997"},{"key":"2631_CR180","unstructured":"R. Nair, D. Pynadath, M. Yokoo, M. Tambe, and S. Marsella, \u201cTaming decentralized POMDPs: Towards efficient policy computation for multiagent settings,\u201d in Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-03), 2003"},{"key":"2631_CR181","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1038\/31225","volume":"393","author":"M. Nowak","year":"1998","journal-title":"Nature"},{"key":"2631_CR182","unstructured":"A. Nowe, K. Verbeeck, and T. Lenaerts, Learning agents in a homo egualis society, Technical report, Computational Modeling Lab - VUB, March 2001"},{"key":"2631_CR183","unstructured":"L. Nunes and E. Oliveira, \u201cLearning from multiple sources,\u201d in AAMAS-2004- Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems, 2004"},{"key":"2631_CR184","doi-asserted-by":"crossref","unstructured":"T. Ohko, K. Hiraki, and Y. Arzai, \u201cAddressee learning and message interception for communication load reduction in multiple robots environments,\u201d in G. Wei\u00df, (ed.), Distributed Artificial Intelligence Meets Machine Learning: Learning in Multi-Agent Environments, Lecture Notes in Artificial Intelligence 1221, Springer-Verlag, 1997","DOI":"10.1007\/3-540-62934-3_52"},{"key":"2631_CR185","doi-asserted-by":"crossref","unstructured":"E. Ostergaard, G. Sukhatme, and M. Mataric, \u201cEmergent bucket brigading - a simple mechanism for improving performance in multi-robot constrainedspace foraging tasks,\u201d in Proceedings of the Fifth International Conference on Autonomous Agents, 2001","DOI":"10.1145\/375735.375825"},{"key":"2631_CR186","unstructured":"L. Pagie and M. Mitchell, \u201cA comparison of evolutionary and coevolutionary search,\u201d in R. K. Belew and H. Juill\u00e8, (eds.), Coevolution: Turning Adaptive Algorithms upon Themselves, San Francisco, California, USA, pp. 20\u201325, 7 2001"},{"key":"2631_CR187","doi-asserted-by":"crossref","unstructured":"L. Panait and S. Luke, \u201cAnt foraging revisited,\u201d in Proceedings of the Ninth International Conference on the Simulation and Synthesis of Living Systems (ALIFE9), 2004","DOI":"10.7551\/mitpress\/1429.003.0096"},{"key":"2631_CR188","doi-asserted-by":"crossref","unstructured":"L. Panait and S. Luke, \u201cLearning ant foraging behaviors,\u201d in Proceedings of the Ninth International Conference on the Simulation and Synthesis of Living Systems (ALIFE9), 2004","DOI":"10.7551\/mitpress\/1429.003.0097"},{"key":"2631_CR189","unstructured":"L. Panait and S. Luke, \u201cA pheromone-based utility model for collaborative foraging,\u201d in AAMAS-2004 - Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems, 2004"},{"key":"2631_CR190","doi-asserted-by":"crossref","unstructured":"L. Panait, R. P. Wiegand, and S. Luke, \u201cA sensitivity analysis of a cooperative coevolutionary algorithm biased for optimization,\u201d in Genetic and Evolutionary Computation Conference - GECCO-2004, Springer, 2004","DOI":"10.1007\/978-3-540-24854-5_59"},{"key":"2631_CR191","doi-asserted-by":"crossref","unstructured":"L. Panait, R. P. Wiegand, and S. Luke, \u201cA visual demonstration of convergence properties of cooperative coevolution,\u201d in Parallel Problem Solving from Nature - PPSN-2004, Springer, 2004","DOI":"10.1007\/978-3-540-30217-9_90"},{"key":"2631_CR192","unstructured":"L. A. Panait, R. P. Wiegand, and S. Luke, \u201cImproving coevolutionary search for optimal multiagent behaviors\u201d, in Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-03), 2003"},{"issue":"3","key":"2631_CR193","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1287\/moor.12.3.441","volume":"12","author":"C. Papadimitriou","year":"1987","journal-title":"Math. Operat. Res."},{"key":"2631_CR194","doi-asserted-by":"crossref","unstructured":"L. Parker, \u201cCurrent state of the art in distributed autonomous mobile robotics,\u201d in L. Parker, G.\u2019Bekey, and J. Barhen, (eds.), Distributed Autonomous Robotic Systems 4, Springer-Verlag, pp. 3\u201312, 2000","DOI":"10.1007\/978-4-431-67919-6_1"},{"key":"2631_CR195","doi-asserted-by":"crossref","unstructured":"L. Parker, \u201cMulti-robot learning in a cooperative observation task,\u201d in Proceedings of Fifth International Symposium on Distributed Autonomous Robotic Systems (DARS 2000), 2000","DOI":"10.1007\/978-4-431-67919-6_37"},{"key":"2631_CR196","doi-asserted-by":"crossref","unstructured":"L. Parker, \u201cDistributed algorithms for multi-robot observation of multiple moving targets,\u201d Auton Robots, vol. 12 no. 3, 2002","DOI":"10.1023\/A:1015256330750"},{"key":"2631_CR197","unstructured":"L. Parker, C. Touzet, and F. Fernandez, \u201cTechniques for learning in multi-robot teams,\u201d in T. Balch and L. Parker, (eds.), Robot Teams: From Diversity to Polymorphism, AK Peters, 2001"},{"key":"2631_CR198","unstructured":"M. Peceny, G. Wei\u00df, and W. Brauer, Verteiltes maschinelles lernen in fertigungsumgebungen, Technical Report FKI-218-96, Institut fur Informatik, Technische Universitat Munchen, 1996"},{"key":"2631_CR199","unstructured":"M. Peeters, K. Verbeeck, and A. Nowe, \u201cMulti-agent learning in conflicting multi-level games with incomplete information,\u201d in Proceedings of Artificial Multiagent Learning, Papers from the 2004 AAAI Fall Symposium. Technical Report FS-04-02, 2004"},{"key":"2631_CR200","unstructured":"L. Peshkin, K.-E. Kim, N. Meuleau, and L. Kaelbling, \u201cLearning to cooperate via policy search,\u201d in Sixteenth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, 2000, pp. 307\u2013314"},{"key":"2631_CR201","unstructured":"R. Poli, J. Rowe, and K. D. Jong, (eds.), Foundations of Genetic Algorithms (FOGA) VII, 2002, Morgan Kaufmann"},{"issue":"3","key":"2631_CR202","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1023\/A:1007417214905","volume":"32","author":"J. Pollack","year":"1998","journal-title":"Machine Learn."},{"key":"2631_CR203","first-page":"92","volume-title":"Artificial Life V: Proc. of the Fifth Int. Workshop on the Synthesis and Simulation of Living Systems","author":"J. Pollack","year":"1997"},{"key":"2631_CR204","doi-asserted-by":"crossref","unstructured":"E. Popovici and K. DeJong, \u201cUnderstanding competitive co-evolutionary dynamics via fitness landscapes,\u201d in Artificial Multiagent Symposium, Part of the 2004 AAAI Fall Symposium on Artificial Intelligence, 2004","DOI":"10.1145\/1068009.1068094"},{"key":"2631_CR205","volume-title":"The Design and Analysis of a Computational Model of Cooperative Coevolution, PhD thesis","author":"M. Potter","year":"1997"},{"key":"2631_CR206","doi-asserted-by":"crossref","unstructured":"M. Potter and K. De Jong, \u201cA cooperative coevolutionary approach to function optimization,\u201d in Y. Davidor and H.-P. Schwefel, (eds.), Proceedings of the Third International Conference on Parallel Problem Solving from Nature (PPSN III), Springer-Verlag, pp. 249\u2013257, 1994","DOI":"10.1007\/3-540-58484-6_269"},{"issue":"1","key":"2631_CR207","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/106365600568086","volume":"8","author":"M. Potter","year":"2000","journal-title":"Evol. Comput."},{"key":"2631_CR208","unstructured":"M. Potter, K. De Jong, and J. J. Grefenstette, \u201cA coevolutionary approach to learning sequential decision rules,\u201d in Proceedings from the Sixth International Conference on Genetic Algorithms, Morgan Kaufmann, pp. 366\u2013372, 1995"},{"key":"2631_CR209","unstructured":"M. Potter, L. Meeden, and A. Schultz, \u201cHeterogeneity in the coevolved behaviors of mobile robots: The emergence of specialists,\u201d in Proceedings of The Seventeenth International Conference on Artificial Intelligence (IJCAI-2001), 2001"},{"key":"2631_CR210","doi-asserted-by":"crossref","unstructured":"N. Puppala, S. Sen, and M. Gordin, \u201cShared memory based cooperative coevolution,\u201d in Proceedings of the 1998 IEEE World Congress on Computational Intelligence, IEEE Press: Anchorage, Alaska, USA, pp. 570\u2013574, 1998","DOI":"10.1109\/ICEC.1998.700091"},{"key":"2631_CR211","doi-asserted-by":"crossref","unstructured":"M. Quinn, \u201cA comparison of approaches to the evolution of homogeneous multi-robot teams,\u201d in Proceedings of the 2001 Congress on Evolutionary Computation (CEC2001), IEEE Press: COEX, World Trade Center, 159 Samseong-dong, Gangnam-gu, Seoul, Korea, 27\u201330 2001, pp. 128\u2013135. ISBN 0-7803-6658-1","DOI":"10.1109\/CEC.2001.934381"},{"key":"2631_CR212","doi-asserted-by":"crossref","unstructured":"M. Quinn, \u201cEvolving communication without dedicated communication channels,\u201d in Advances in Artificial Life: Sixth European Conference on Artificial Life (ECAL01), 2001","DOI":"10.1007\/3-540-44811-X_38"},{"key":"2631_CR213","unstructured":"M. Quinn, L. Smith, G. Mayley, and P. Husbands, Evolving formation movement for a homogeneous multi-robot system: Teamwork and role-allocation with real robots, Cognitive Science Research Paper 515. School of Cognitive and Computing Sciences, University of Sussex, Brighton, BN1 9QG. ISSN 1350\u20133162, 2002"},{"key":"2631_CR214","doi-asserted-by":"crossref","unstructured":"C. Reynolds, \u201cAn evolved, vision-based behavioral model of coordinated group motion,\u201d in From Animals to Animats 2: Proceedings of the Second International Conference on Simulation of Adaptive Behavior (SAB92), pp. 384\u2013392, 1993","DOI":"10.7551\/mitpress\/3116.003.0052"},{"key":"2631_CR215","doi-asserted-by":"crossref","unstructured":"C. Reynolds, \u201cCompetition, coevolution and the game of tag,\u201d in R. A. Brooks and P. Maes, (eds.), Artificial Life IV, Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems., MIT Press, pp. 59\u201369, 1994","DOI":"10.7551\/mitpress\/1428.003.0010"},{"issue":"4","key":"2631_CR216","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1145\/37402.37406","volume":"21","author":"C.W. Reynolds","year":"1987","journal-title":"Comput. Graph."},{"key":"2631_CR217","doi-asserted-by":"crossref","unstructured":"P. Riley and M. Veloso, \u201cOn behavior classification in adversarial environments,\u201d in L. Parker, G.\u2019Bekey, and J. Barhen (eds.), Distributed Autonomous Robotic Systems 4, Springer-Verlag, pp. 371\u2013380, 2000","DOI":"10.1007\/978-4-431-67919-6_35"},{"key":"2631_CR218","unstructured":"A. Robinson and L. Spector, \u201cUsing genetic programming with multiple data types and automatic modularization to evolve decentralized and coordinated navigation in multi-agent systems,\u201d in In\u2019Late-Breaking Papers of the Genetic and Evolutionary Computation Conference (GECCO-2002), The International Society for Genetic and Evolutionary Computation, 2002"},{"issue":"1","key":"2631_CR219","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/evco.1997.5.1.1","volume":"5","author":"C. Rosin","year":"1997","journal-title":"Evol. Comput."},{"key":"2631_CR220","doi-asserted-by":"crossref","unstructured":"R. Salustowicz, M. Wiering, and J. Schmidhuber, Learning team strategies with multiple policy-sharing agents: A soccer case study, Technical report, ISDIA, Corso Elvezia 36, 6900 Lugano, Switzerland, 1997","DOI":"10.1007\/BFb0020247"},{"issue":"2-3","key":"2631_CR221","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1023\/A:1007570708568","volume":"33","author":"R. Salustowicz","year":"1998","journal-title":"Machine Learn."},{"issue":"3","key":"2631_CR222","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1147\/rd.33.0210","volume":"3","author":"A. Samuel","year":"1994","journal-title":"IBM J. Res. Develop."},{"key":"2631_CR223","doi-asserted-by":"crossref","unstructured":"T. Sandholm and R. H. Crites, \u201cOn multiagent Q-learning in a semi-competitive domain,\u201d in\u2019Adaption and Learning in Multi-Agent Systems, pp. 191\u2013205, 1995","DOI":"10.1007\/3-540-60923-7_28"},{"key":"2631_CR224","unstructured":"H. Santana, G. Ramalho, V. Corruble, and B. Ratitch, \u201cMulti-agent patrolling with reinforcement learning,\u201d in AAMAS-2004 - Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems, 2004"},{"key":"2631_CR225","doi-asserted-by":"crossref","unstructured":"G. Saunders and J. Pollack, \u201cThe evolution of communication schemes over continuous channels,\u201d in\u2019From Animals to Animats 4 - Proceedings of the Fourth International Conference on Adaptive Behaviour, 1996","DOI":"10.7551\/mitpress\/3118.003.0070"},{"key":"2631_CR226","doi-asserted-by":"crossref","unstructured":"J. Sauter, R. S. Matthews, H. Van Dyke Parunak, and S. Brueckner, \u201cEvolving adaptive pheromone path planning mechanisms,\u201d in Proceedings of First International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-02), pp. 434\u2013440, 2002","DOI":"10.1145\/544741.544841"},{"key":"2631_CR227","unstructured":"J. Sauter, H. Van Dyke Parunak, S. Brueckner, and R. Matthews, \u201cTuning synthetic pheromones with evolutionary computing,\u201d in R. E. Smith, C. Bonacina, C. Hoile, and P. Marrow, (eds.), Evolutionary Computation and Multi-Agent Systems (ECOMAS), San Francisco, California, USA, 7\u00a0pp. 321\u2013324, 2001"},{"key":"2631_CR228","unstructured":"J. Schmidhuber, \u201cRealistic multi-agent reinforcement learning,\u201d in Learning in Distributed Artificial Intelligence Systems, Working Notes of the 1996 ECAI Workshop, 1996"},{"key":"2631_CR229","doi-asserted-by":"crossref","unstructured":"J. Schmidhuber and J. Zhao, \u201cMulti-agent learning with the success-story algorithm,\u201d in ECAI Workshop LDAIS\/ICMAS Workshop LIOME, pp. 82\u201393, 1996","DOI":"10.1007\/3-540-62934-3_43"},{"key":"2631_CR230","unstructured":"J. Schneider, W.-K. Wong, A. Moore, and M. Riedmiller, \u201cDistributed value functions,\u201d in Proceedings of the Sixteenth International Conference on Machine Learning, pp. 371\u2013378, 1999"},{"key":"2631_CR231","unstructured":"A. Schultz, J. Grefenstette, and W. Adams, \u201cRobo-shepherd: Learning complex robotic behaviors,\u201d in Robotics and Manufacturing: Recent Trends in Research and Applications. Vol. 6, ASME Press, pp. 763\u2013768, 1996"},{"key":"2631_CR232","unstructured":"U. M. Schwuttke and A. G. Quan, \u201cEnhancing performance of cooperating agents in realtime diagnostic systems\u201d, in Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence (IJCAI-93), 1993"},{"key":"2631_CR233","unstructured":"M. Sekaran and S. Sen, \u201cTo help or not to help\u201d, in Proceedings of the Seventeenth Annual Conference of the Cognitive Science Society, Pittsburgh, PA, pp. 736\u2013741, 1995"},{"key":"2631_CR234","doi-asserted-by":"crossref","unstructured":"S. Sen, \u201cMultiagent systems: Milestones and new horizons\u201d, Trends Cognitive Sci., vol. 1, no. 9, pp.\u2019334\u2013339, 1997","DOI":"10.1016\/S1364-6613(97)01100-5"},{"key":"2631_CR235","doi-asserted-by":"crossref","unstructured":"S. Sen, \u201cSpecial issue on evolution and learning in multiagent systems,\u201d Int. J. Human-Comput. Stud., vol. 48, no. 1, 1998","DOI":"10.1006\/ijhc.1997.0157"},{"key":"2631_CR236","doi-asserted-by":"crossref","unstructured":"S. Sen and M. Sekaran, \u201cUsing reciprocity to adapt to others\u201d, in G. Wei\u00df and S. Sen (eds.), International Joint Conference on Artificial Intelligence Workshop on Adaptation and Learning in Multiagent Sytems, Lecture Notes in Artificial Intelligence, Springer-Verlag, pp. 206\u2013217, 1995","DOI":"10.1007\/3-540-60923-7_29"},{"key":"2631_CR237","doi-asserted-by":"crossref","unstructured":"S. Sen and M. Sekaran, \u201cMultiagent coordination with learning classifier systems\u201d, in G. Wei\u00df and S.\u2019Sen, (eds.), Proceedings of the IJCAI Workshop on Adaption and Learning in Multi-Agent Systems, Volume 1042, Springer Verlag, pp. 218\u2013233, 1996. ISBN 3-540-60923-7","DOI":"10.1007\/3-540-60923-7_30"},{"issue":"3","key":"2631_CR238","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1080\/095281398146798","volume":"10","author":"S. Sen","year":"1998","journal-title":"J. Exp. Theo. Artif. Intel."},{"key":"2631_CR239","unstructured":"S. Sen, M. Sekaran, and J. Hale, \u201cLearning to coordinate without sharing information\u201d, in Proceedings of the Twelfth National Conference on Artificial Intelligence, pp. 426\u2013431, 1994"},{"key":"2631_CR240","unstructured":"Y. Shoham, R. Powers, and T. Grenager, \u201cOn the agenda(s) of research on multi-agent learning,\u201d in\u2019Proceedings of Artificial Multiagent Learning, Papers from the 2004 AAAI Fall Symposium. Technical Report FS-04\u201302, 2004"},{"key":"2631_CR241","unstructured":"R. Smith and B. Gray, Co-adaptive genetic algorithms: An example in othello strategy, Technical Report TCGA 94002, University of Alabama, Department of Engineering Science and Mechanics, 1993"},{"key":"2631_CR242","unstructured":"L. Spector and J. Klein, \u201cEvolutionary dynamics discovered via visualization in the breve simulation environment,\u201d in Workshop Proceedings of the 8th International Conference on the Simulation and Synthesis of Living Systems, pp. 163\u2013170, 2002"},{"key":"2631_CR243","doi-asserted-by":"crossref","unstructured":"L. Spector, J. Klein, C. Perry, and M. Feinstein, \u201cEmergence of collective behavior in evolving populations of flying agents,\u201d in E. Cantu-Paz et al., (ed.), Prooceedings of the Genetic and Evolutionary Computation Conference (GECCO). Springer-Verlag, 2003","DOI":"10.1007\/3-540-45105-6_6"},{"key":"2631_CR244","doi-asserted-by":"crossref","unstructured":"R. Steeb, S. Cammarata, F. Hayes-Roth, P. Thorndyke, and R. Wesson, \u201cDistributed intelligence for air fleet control,\u201d in A. Bond and L. Gasser (eds.), Readings in Distributed Artificial Intelligence, Morgan Kaufmann Publishers, pp. 90\u2013101, 1988","DOI":"10.1016\/B978-0-934613-63-7.50011-5"},{"issue":"3","key":"2631_CR245","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1162\/artl.1995.2.3.319","volume":"2","author":"L. Steels","year":"1995","journal-title":"Artif. Life"},{"key":"2631_CR246","doi-asserted-by":"crossref","unstructured":"L. Steels, \u201cEmergent adaptive lexicons,\u201d in P. Maes, (ed.), Proceedings of the Simulation of Adaptive Behavior Conference. MIT Press, 1996","DOI":"10.7551\/mitpress\/3118.003.0068"},{"key":"2631_CR247","unstructured":"L. Steels, \u201cSelf-organising vocabularies,\u201d in Proceedings of Artificial Life V, 1996"},{"key":"2631_CR248","volume-title":"Machine Intelligence 15","author":"L. Steels","year":"1996"},{"key":"2631_CR249","unstructured":"L. Steels, \u201cSynthesising the origins of language and meaning using co-evolution, self-organisation and level formation,\u201d in J. Hurford, C. Knight, and M. Studdert-Kennedy (eds.), Approaches to the Evolution of Language: Social and Cognitive Bases, Edinburgh University Press, 1997"},{"issue":"4","key":"2631_CR250","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/s001970050001","volume":"8","author":"L. Steels","year":"2000","journal-title":"Kognitionswissenschaft"},{"key":"2631_CR251","doi-asserted-by":"crossref","unstructured":"L. Steels and F. Kaplan, \u201cCollective learning and semiotic dynamics,\u201d in Proceedings of the European Conference on Artificial Life, pp. 679\u2013688, 1999","DOI":"10.1007\/3-540-48304-7_89"},{"key":"2631_CR252","unstructured":"P. Stone, \u201cLayered learning in multiagent systems,\u201d in Proceedings of National Conference on Artificial Intelligence AAAI\/IAAI, 1997"},{"key":"2631_CR253","unstructured":"P. Stone, \u201cLayered Learning in Multi-Agent Systems,\u201d PhD thesis, Carnegie Mellon University, 1998"},{"key":"2631_CR254","doi-asserted-by":"crossref","unstructured":"P. Stone and R. Sutton, \u201cKeepaway soccer: A machine learning testbed,\u201d in A. Birk, S. Coradeschi, and S. Tadokoro, (eds.), RoboCup 2001: Robot Soccer World Cup V, volume 2377 of Lecture Notes in Computer Science, Springer, pp. 214\u2013223, 2002. ISBN 3-540-43912-9","DOI":"10.1007\/3-540-45603-1_22"},{"issue":"3","key":"2631_CR255","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P. Stone","year":"2000","journal-title":"Auton. Robots"},{"key":"2631_CR256","unstructured":"N. Sturtevant and R. Korf, \u201cOn pruning techniques for multi-player games,\u201d in Proceedings of National Conference on Artificial Intelligence (AAAI), pp. 201\u2013207, 2000"},{"key":"2631_CR257","unstructured":"D. Subramanian, P. Druschel, and J. Chen, \u201cAnts and reinforcement learning: A case study in routing in dynamic networks,\u201d in Proceedings of Fifteenth International Joint Conference on Artificial Intelligence (IJCAI-97), pp. 832\u2013839, 1997"},{"key":"2631_CR258","doi-asserted-by":"crossref","unstructured":"N. Suematsu and A. Hayashi, \u201cA multiagent reinforcement learning algorithm using extended optimal response,\u201d in Proceedings of First International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-02), pp. 370\u2013377, 2002","DOI":"10.1145\/544741.544831"},{"key":"2631_CR259","doi-asserted-by":"crossref","unstructured":"D. Suryadi and P. J. Gmytrasiewicz, \u201cLearning models of other agents using influence diagrams,\u201d in\u2019Preceedings of the 1999 International Conference on User Modeling, pp. 223\u2013232, 1999","DOI":"10.1007\/978-3-7091-2490-1_22"},{"key":"2631_CR260","first-page":"9","volume":"3","author":"R. Sutton","year":"1998","journal-title":"Machine Learn."},{"key":"2631_CR261","doi-asserted-by":"crossref","unstructured":"R. Sutton and A. Barto, Reinforcement Learning: An Introduction, MIT Press, 1998","DOI":"10.1109\/TNN.1998.712192"},{"key":"2631_CR262","doi-asserted-by":"crossref","unstructured":"J. Svennebring and S. Koenig, \u201cTrail-laying robots for robust terrain coverage,\u201d in Proceedings of the International Conference on Robotics and Automation (ICRA-03), 2003","DOI":"10.1109\/ROBOT.2003.1241576"},{"key":"2631_CR263","unstructured":"P. \u2019t Hoen and K. Tuyls, \u201cAnalyzing multi-agent reinforcement learning using evolutionary dynamics,\u201d in Proceedings of the 15th European Conference on Machine Learning (ECML), 2004"},{"key":"2631_CR264","unstructured":"M. Tambe, \u201cRecursive agent and agent-group tracking in a real-time dynamic environment,\u201d in V.\u2019Lesser and L. Gasser (eds.), Proceedings of the First International Conference on Multiagent Systems (ICMAS-95). AAAI Press, 1995"},{"key":"2631_CR265","first-page":"487","volume-title":"Readings in Agents","author":"M. Tan","year":"1993"},{"key":"2631_CR266","doi-asserted-by":"crossref","unstructured":"P. Tangamchit, J. Dolan, and P. Khosla, \u201cThe necessity of average rewards in cooperative multirobot learning,\u201d in Proceedings of IEEE Conference on Robotics and Automation, 2002","DOI":"10.1109\/ROBOT.2002.1014721"},{"issue":"3","key":"2631_CR267","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G. Tesauro","year":"1995","journal-title":"Commun. ACM"},{"key":"2631_CR268","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1023\/A:1015504423309","volume":"8","author":"G. Tesauro","year":"2002","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"2631_CR269","unstructured":"S. Thrun, \u201cLearning to play the game of chess,\u201d in G. Tesauro, D. Touretzky, and T. Leen, (eds.), Advances in Neural Information Processing Systems 7, The MIT Press: Cambridge, MA, pp. 1069\u20131076, 1995"},{"key":"2631_CR270","doi-asserted-by":"crossref","unstructured":"K. Tumer, A. K. Agogino, and D. H. Wolpert, \u201cLearning sequences of actions in collectives of autonomous agents,\u201d in Proceedings of First International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-02), pp. 378\u2013385, 2002","DOI":"10.1145\/544741.544832"},{"key":"2631_CR271","doi-asserted-by":"crossref","unstructured":"K. Tuyls, K. Verbeeck, and T. Lenaerts, \u201cA selection-mutation model for Q-learning in multiagent systems,\u201d in AAMAS-2003 \u2014 Proceedings of the Second International Joint Conference on Autonomous Agents and Multi Agent Systems, 2003","DOI":"10.1145\/860575.860687"},{"key":"2631_CR272","unstructured":"W. Uther and M. Veloso, \u201cAdversarial reinforcement learning. Technical Report CMU-CS-03-107, School of Computer Science, Carnegie Mellon University, 2003"},{"key":"2631_CR273","unstructured":"H. Van Dyke Parunak, \u201cApplications of distributed artificial intelligence in industry,\u201d in G. M. P. O\u2019Hare and N. R. Jennings, (eds.), Foundations of Distributed AI. John Wiley & Sons, 1996"},{"issue":"4","key":"2631_CR274","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1016\/0957-4174(94)90080-9","volume":"7","author":"L.Z. Varga","year":"1994","journal-title":"Int. J. Expert Syst. Appl."},{"key":"2631_CR275","unstructured":"J. Vidal and E. Durfee, \u201cAgents learning about agents: A framework and analysis,\u201d in Working Notes of AAAI-97 Workshop on Multiagent Learning, 1997"},{"key":"2631_CR276","unstructured":"J. Vidal and E. Durfee, \u201cThe moving target function problem in multiagent learning,\u201d in Proceedings of the Third Annual Conference on Multi-Agent Systems, 1998"},{"key":"2631_CR277","doi-asserted-by":"crossref","unstructured":"J. Vidal and E. Durfee, \u201cPredicting the expected behavior of agents that learn about agents: The CLRI framework,\u201d Autonomous Agents and Multi-Agent Systems, January 2003","DOI":"10.1023\/A:1021765422660"},{"key":"2631_CR278","doi-asserted-by":"crossref","unstructured":"K. Wagner, \u201cCooperative strategies and the evolution of communication,\u201d Artif. Life, vol. 6, no. 2, pp. 149\u2013179, Spring 2000","DOI":"10.1162\/106454600568384"},{"key":"2631_CR279","unstructured":"X. Wang and T. Sandholm, \u201cReinforcement learning to play an optimal Nash equilibrium in team Markov games,\u201d in Advances in Neural Information Processing Systems (NIPS-2002), 2002"},{"key":"2631_CR280","unstructured":"R. Watson and J. Pollack, \u201cCoevolutionary dynamics in a minimal substrate,\u201d in E. Cantu-Paz et al, (eds.), Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), 2001"},{"key":"2631_CR281","unstructured":"R. Weihmayer and H. Velthuijsen, \u201cApplication of distributed AI and cooperative problem solving to telecommunications,\u201d in J. Liebowitz and D. Prereau, (eds.), AI Approaches to Telecommunications and Network Management, IOS Press, 1994"},{"key":"2631_CR282","unstructured":"M. Weinberg and J. Rosenschein, \u201cBest-response multiagent learning in non-stationary environments,\u201d in AAMAS-2004 \u2014 Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems, 2004"},{"key":"2631_CR283","unstructured":"G. Wei\u00df, Some studies in distributed machine learning and organizational design. Technical Report FKI-189-94, Institut f\u00b4\u2032ur Informatik, TU M\u00fcnchen, 1994"},{"key":"2631_CR284","volume-title":"Distributed Machine Learning","author":"G. Wei\u00df","year":"1995"},{"key":"2631_CR285","doi-asserted-by":"crossref","unstructured":"G. Wei\u00df, ed., Distributed Artificial Intelligence Meets Machine Learning: Learning in Multi-Agent Environments, Number 1221 in Lecture Notes in Artificial Intelligence, Springer-Verlag, 1997","DOI":"10.1007\/3-540-62934-3"},{"key":"2631_CR286","unstructured":"G. Wei\u00df (1998). \u201cSpecial issue on learning in distributed artificial intelligence systems\u201d. J. Exp. Theo. Artif. Intell. 10(3)."},{"key":"2631_CR287","unstructured":"G. Wei\u00df, ed., Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence. MIT Press, 1999"},{"key":"2631_CR288","unstructured":"G. Wei\u00df and P. Dillenbourg, \u201cWhat is \u2018multi\u2019 in multi-agent learning?\u201d in P. Dillenbourg, (ed.), Collaborative Learning, Cognitive and Computational Approaches, Pergamon Press, pp. 64\u201380, 1999"},{"key":"2631_CR289","doi-asserted-by":"crossref","unstructured":"G. Wei\u00df and S. Sen (eds.), Adaptation and Learning in Multiagent Systems,\u201d Lecture Notes in Artificial Intelligence Vol. 1042, Springer-Verlag, 1996","DOI":"10.1007\/3-540-60923-7"},{"issue":"2-3","key":"2631_CR290","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1023\/A:1007514623589","volume":"33","author":"M. Wellman","year":"1998","journal-title":"Machine Learn."},{"issue":"4","key":"2631_CR291","first-page":"388","volume":"4","author":"J. Werfel","year":"November 2000","journal-title":"IEEE Trans. Evol. Comput."},{"key":"2631_CR292","unstructured":"B. B. Werger and M. Mataric, \u201cExploiting embodiment in multi-robot teams, Technical Report IRIS-99-378, University of Southern California, Institute for Robotics and Intelligent Systems, 1999"},{"key":"2631_CR293","doi-asserted-by":"crossref","unstructured":"G. M. Werner and M. G. Dyer, \u201cEvolution of herding behavior in artificial animals,\u201d in From Animals to Animats 2: Proceedings of the Second International Conference on Simulation of Adaptive Behavior (SAB92), 1993","DOI":"10.7551\/mitpress\/3116.003.0053"},{"key":"2631_CR294","first-page":"22","volume-title":"Genetic Programming 1998: Proceedings of the Third Annual Conference","author":"T. White","year":"1998"},{"key":"2631_CR295","doi-asserted-by":"crossref","unstructured":"S. Whiteson and P. Stone, \u201cConcurrent layered learning,\u201d in AAMAS-2003 - Proceedings of the Second International Joint Conference on Autonomous Agents and Multi Agent Systems, 2003","DOI":"10.1145\/860575.860607"},{"key":"2631_CR296","unstructured":"R. P. Wiegand, Analysis of Cooperative Coevolutionary Algorithms, PhD thesis, Department of Computer Science, George Mason University, 2003"},{"key":"2631_CR297","unstructured":"R. P. Wiegand, W. Liles, and K. De Jong, \u201cAn empirical analysis of collaboration methods in cooperative coevolutionary algorithms,\u201d in E. Cantu-Paz et al., (ed.), Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pp. 1235\u20131242, 2001"},{"key":"2631_CR298","doi-asserted-by":"crossref","unstructured":"R. P. Wiegand, W. Liles, and K. De Jong, \u201cAnalyzing cooperative coevolution with evolutionary game theory,\u201d in D. Fogel, (ed.), Proceedings of Congress on Evolutionary Computation (CEC-02), IEEE Press, pp. 1600\u20131605, 2002","DOI":"10.1109\/CEC.2002.1004481"},{"key":"2631_CR299","unstructured":"R. P. Wiegand, W. Liles, and K. De Jong, \u201cModeling variation in cooperative coevolution using evolutionary game theory,\u201d in Poli et al. [201], pp. 231\u2013248"},{"key":"2631_CR300","doi-asserted-by":"crossref","unstructured":"R. P. Wiegand and J. Sarma, \u201cSpatial embedding and loss of gradient in cooperative coevolutionary algorithms,\u201d in Parallel Problem Solving from Nature - PPSN-2004, Springer, 2004","DOI":"10.1007\/978-3-540-30217-9_92"},{"issue":"1","key":"2631_CR301","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1023\/A:1008921914343","volume":"7","author":"M. Wiering","year":"1999","journal-title":"J. Auton. Robots"},{"key":"2631_CR302","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1023\/B:AGNT.0000011160.45980.4b","volume":"8","author":"A. Williams","year":"2004","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"2631_CR303","unstructured":"E. Wilson, Sociobiology: The New Synthesis, Belknap Press, 1975"},{"issue":"2-3","key":"2631_CR304","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1142\/S0219525901000188","volume":"4","author":"D.H. Wolpert","year":"2001","journal-title":"Adv. Complex Syst."},{"key":"2631_CR305","unstructured":"D. H. Wolpert, K. Tumer, and J. Frank, \u201cUsing collective intelligence to route internet traffic,\u201d in\u2019Advances in Neural Information Processing Systems-11, Denver, pp. 952\u2013958, 1998"},{"key":"2631_CR306","doi-asserted-by":"crossref","unstructured":"D. H. Wolpert, K. R. Wheller, and K. Tumer, \u201cGeneral principles of learning-based multi-agent systems,\u201d in O. Etzioni, J. P. M\u00fcller, and J. M. Bradshaw, (eds.), Proceedings of the Third International Conference on Autonomous Agents (Agents\u201999), ACM Press: Seattle, WA, USA, pp. 77\u201383, 1999","DOI":"10.1145\/301136.301167"},{"key":"2631_CR307","unstructured":"M. Wooldridge, S. Bussmann, and M. Klosterberg, \u201cProduction sequencing as negotiation,\u201d in\u2019Proceedings of the First International Conference on the Practical Application of Intelligent Agents and Multi-Agent Technology (PAAM-96), 1996"},{"key":"2631_CR308","doi-asserted-by":"crossref","unstructured":"A. Wu, A. Schultz, and A. Agah, \u201cEvolving control for distributed micro air vehicles,\u201d in IEEE Computational Intelligence in Robotics and Automation Engineers Conference, 1999","DOI":"10.1109\/CIRA.1999.810045"},{"key":"2631_CR309","doi-asserted-by":"crossref","unstructured":"H. Yanco and L. Stein, \u201cAn adaptive communication protocol for cooperating mobile robots,\u201d in\u2019From Animals to Animats: International Conference on Simulation of Adaptive Behavior, pp. 478\u2013485, 1993","DOI":"10.7551\/mitpress\/3116.003.0064"},{"key":"2631_CR310","doi-asserted-by":"crossref","unstructured":"N. Zaera, D. Cliff, and J. Bruten, (Not) Evolving collective behaviours in synthetic fish, Technical Report HPL-96-04, Hewlett-Packard Laboratories, 1996","DOI":"10.7551\/mitpress\/3118.003.0076"},{"key":"2631_CR311","unstructured":"B. Zhang and D. Cho, \u201cCoevolutionary fitness switching: Learning complex collective behaviors using genetic programming,\u201d in Advances in Genetic Programming III, MIT Press, 1998, pp. 425\u2013445"},{"key":"2631_CR312","first-page":"9","volume-title":"Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior: From Animals to Animats 4","author":"J. Zhao","year":"1996"}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-005-2631-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-005-2631-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-005-2631-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T21:26:53Z","timestamp":1735939613000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-005-2631-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,11]]},"references-count":312,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2005,11]]}},"alternative-id":["2631"],"URL":"https:\/\/doi.org\/10.1007\/s10458-005-2631-2","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,11]]}}}