Advertisement

Autonomous Robots

, Volume 8, Issue 3, pp 345–383 | Cite as

Multiagent Systems: A Survey from a Machine Learning Perspective

  • Peter Stone
  • Manuela Veloso
Article

Abstract

Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is concerned with systems that consist of multiple independent entities that interact in a domain. Traditionally, DAI has been divided into two sub-disciplines: Distributed Problem Solving (DPS) focuses on the information management aspects of systems with several components working together towards a common goal; Multiagent Systems (MAS) deals with behavior management in collections of several independent entities, or agents. This survey of MAS is intended to serve as an introduction to the field and as an organizational framework. A series of general multiagent scenarios are presented. For each scenario, the issues that arise are described along with a sampling of the techniques that exist to deal with them. The presented techniques are not exhaustive, but they highlight how multiagent systems can be and have been used to build complex systems. When options exist, the techniques presented are biased towards machine learning approaches. Additional opportunities for applying machine learning to MAS are highlighted and robotic soccer is presented as an appropriate test bed for MAS. This survey does not focus exclusively on robotic systems. However, we believe that much of the prior research in non-robotic MAS is relevant to robotic MAS, and we explicitly discuss several robotic MAS, including all of those presented in this issue.

multiagent systems machine learning survey robotics intelligent agents robotic soccer pursuit domain homogeneous agents heterogeneous agents communicating agents 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. AAAI. 1995. Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, CA, AAAI Press. Victor Lessor-General Chair.Google Scholar
  2. Achim, S., Stone, P., and Veloso, M. 1996. Building a dedicated robotic soccer system. In Proceedings of the IROS-96 Workshop on RoboCup, Osaka, Japan, pp. 41–48.Google Scholar
  3. Andou, T. 1998. Refinement of soccer agents' positions using reinforcement learning. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlins, pp. 373–388.Google Scholar
  4. Andre, E., Herzog, G., and Rist, T. 1988. On the simultaneous interpretation of real world image sequences and their natural language description: The system soccer. In Proc.of the 8th ECAI, Munich, pp. 449–454.Google Scholar
  5. Andre, E., Herzog, G., and Rist, T. 1998. Generating multimedia presentations for RoboCup soccer games. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 200–215.Google Scholar
  6. Andre, D. and Teller, A. 1999. Evolving team Darwin United. In RoboCup-98: Robot SoccerWorld Cup II, M. Asada and H. Kitano (Eds.), Springer Verlag: Berlin.Google Scholar
  7. Arora, N. and Sen, S. 1996. Resolving social dilemmas using genetic algorithms. In Adaptation, Coevolution and Learning in Multiagent Systems: Papers from the 1996 AAAI Spring Symposium, Menlo Park, CA, AAAI Press, pp. 1–5. AAAI Technical Report SS-96-01.Google Scholar
  8. Asada, M. and Kitano, H. (Eds.) 1999. RoboCup-98: Robot Soccer World Cup II, Springer Verlag: Berlin. Lecture Notes in Artificial Intelligence, vol. 1604.Google Scholar
  9. Asada, M., Noda, S., and Hosoda, K. 1996. Action-based sensor space categorization for robot learning. In Proc.of IEEE/RSJ International Conference on Intelligent Robots and Systems 1996 (IROS' 96), pp. 1502–1509.Google Scholar
  10. Asada, M., Noda, S., Tawaratsumida, S., and Hosoda, K. 1994a. Purposive behavior acquisition on a real robot by vision-based reinforcement learning. In Proc.of MLC-COLT (Machine Learning Confernce and Computer Learning Theory) Workshop on Robot Learning, pp. 1–9.Google Scholar
  11. Asada, M., Uchibe, E., Noda, S., Tawaratsumida, S., and Hosoda, K. 1994b. Coordination of multiple behaviors acquired by visionbased reinforcement learning. In Proc.of IEEE/RSJ/GI International Conference on Intelligent Robots and Systems 1994, pp. 917–924.Google Scholar
  12. Balch, T. 1998. Behavioral diversity in learning robot teams. PhD Thesis, College of Computing, Georgia Institute of Technology.Google Scholar
  13. Balch, T. 2000. Social entropy: An information theoretic measure of robot team diversity. Autonomous Robots, 8(3):1–25.Google Scholar
  14. Balch, T. and Arkin, R.C. 1994. Communication in reactive multiagent robotic systems. Autonomous Robots, 1(1).Google Scholar
  15. Balch, T. and Arkin, R.C. 1995. Motor schema-based formation control for multiagent robot teams. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 10–16.Google Scholar
  16. Barbuceanu, M. and Fox, M.S. 1995. COOL: A language for describing coordination in multi agent systems. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 17–24.Google Scholar
  17. Barman, R.A., Kingdon, S.J., Little, J.J., Mackworth, A.K., Pai, D.K., Sahota, M., Wilkinson, H., and Zhang, Y. 1993. DYNAMO: Real-time experiments with multiple mobile robots. In Intelligent Vehicles Symposium, Tokyo, pp. 261–266.Google Scholar
  18. Beckers, R., Holland, E., and Deneubourg, J.L. 1994. From local actions to global tasks: Stigmergy and collective robotics. In Artifical Life IV: Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems, R. Brooks and P. Maes (Eds.), MIT Press, pp. 181–189.Google Scholar
  19. Benda, M., Jagannathan, V., and Dodhiawala, R. 1986. On optimal cooperation of knowledge sources—an empirical investigation. Technical Report BCS-G2010-28, Boeing Advanced Technology Center, Boeing Computing Services, Seattle, Washington.Google Scholar
  20. Binsted, K. 1999. Character design for soccer commentary. In RoboCup-98: Robot SoccerWorld Cup II, M. Asada and H. Kitano (Eds.), Springer Verlag: Berlin.Google Scholar
  21. Bond, A.H. and Gasser, L. 1988. An analysis of problems and research in DAI. In Readings in Distributed Artificial Intelligence, A.H. Bond and L. Gasser (Eds.), Morgan Kaufmann Publishers: San Mateo, CA, pp. 3–35.Google Scholar
  22. Bowling, M. and Veloso, M. 1999. Motion control in dynamic multirobot environments. In Proceedings of The 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA'99), Monterrey.Google Scholar
  23. Bull, L., Fogarty, T.C., and Snaith, M. 1995. Evolution in multi-agent systems: Evolving communicating classifier systems for gait in a quadrupedal robot. In Proceedings of the Sixth International Conference on Genetic Algorithms, S. Forrest (Ed.), Morgan Kaufman: San Mateo, CA, pp. 382–388.Google Scholar
  24. Cao, Y.U., Fukunaga, A.S., and Kahng, A.B. 1997. Cooperative mobile robotics: Antecedents and directions. Autonomous Robots, 4:7–27.Google Scholar
  25. Castaño, A., Shen, W.-M., and Will, P. 2000. CONRO: Towards deployable robots with inter-robot metamorphic capabilities. Autonomous Robots, 8(3):309–324.Google Scholar
  26. Castelfranchi, C. 1995. Commitments: From individual intentions to groups and organizations. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 41–48.Google Scholar
  27. Ch'ng, S. and Padgham, L. 1998. From roles to teamwork: A framework and architecture. Applied Artificial Intelligence, 12:211–232.Google Scholar
  28. rCheng, G. and Zelinsky. A. 1998. Real-time vision processing for a soccer playing mobile robot. In RoboCup-97: Robot SoccerWorld Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 144–155.Google Scholar
  29. Clouse, J.A. 1996. Learning from an automated training agent. In Adaptation and Learning in Multiagent Systems, G. Weiß and S. Sen (Eds.), Springer Verlag: Berlin.Google Scholar
  30. Cohen, P.R. and Levesque, H.J. 1995. Communicative actions for artificial agents. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 65–72.Google Scholar
  31. Coradeschi, S. and Karlsson, L. 1998. A role-based decisionmechanism for teams of reactive and coordinating agents. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 112–122.Google Scholar
  32. Dautenhahn, K. 1995. Getting to know each other—artificial social intelligence for autonomous robots. Robotics and Autonomous Systems, 16:333–356.Google Scholar
  33. de la, Rosa, J.Ll. Oller, A., Vehi, J., and Puyol, J. 1997. Soccer team based on agent-oriented programming. Robotics and Autonomous Systems, 21(2):161–176.Google Scholar
  34. Decker, K.S. 1987. Distributed problem solving: A survey. IEEE Transactions on Systems, Man, and Cybernetics, 17(5):729–740.Google Scholar
  35. Decker, K.S. 1995. Environment centered analysis and design of coordination mechanisms. PhD Thesis, University of Massachusetts.Google Scholar
  36. Decker, K.S. 1996a. Distributed artificial intelligence testbeds. In Foundations of Distributed Artificial Intelligence, G.M.P. O'Hare and N.R. Jennings (Eds.), Wiley Interscience, pp. 119–138.Google Scholar
  37. Decker, K.S. 1996b. Personal correspondence.Google Scholar
  38. Decker, K.S. 1996c. Task environment centered simulation. In Simulating Organizations: Computational Models of Institutions and Groups, M. Prietula, K. Carley, and L. Gasser (Eds.), AAAI Press/MIT Press.Google Scholar
  39. Decker, K.S. and Lesser, V.R. 1995. Designing a family of coordination algorithms. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 73–80.Google Scholar
  40. Drogoul, A. and Collinot, A. 1998. Applying an agent-oriented methodology to the design of artificial organizations: Acase study in robotic soccer. Autonomous Agents and Multi-Agent Systems, 1(1):113–129.Google Scholar
  41. Dudek, G., Jenkin, M.R.M., Milios, E., and Wilkes, D. 1996. A taxonomy for multi-agent robotics. Autonomous Robots, 3(4):375–397.Google Scholar
  42. Durfee, E.H. 1992. What your computer really needs to know, you learned in kindergarten. In Proceedings of the Tenth National Conference on Artificial Intelligence, Philadelphia, PA, Morgan Kaufman.Google Scholar
  43. Durfee, E.H. 1995. Blissful ignorance: Knowing just enough to coordinate well. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 406–413.Google Scholar
  44. Durfee, E.H., Lesser, V.R., and Corkill, D.D. 1989. Trends in cooperative distributed problem solving. IEEE Transactions on Knowledge and Data Engineering, 1(1):63–83.Google Scholar
  45. Fenster, M., Kraus, S., and Rosenschein, J.S. 1995. Coordination without communication: Experimental validation of focal point techniques. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 102–108.Google Scholar
  46. Ferguson, I.A. and Karakoulas, G.J. 1996. Multiagent learning and adaptation in an information filtering market. In Adaptation, Coevolution and Learning in Multiagent Systems: Papers from the 1996 AAAI Spring Symposium, Menlo Park, CA, AAAI Press, pp. 28–32. AAAI Technical Report SS-96-01.Google Scholar
  47. Finin, T., McKay, D., Fritzson, R., and McEntire, R. 1994. KQML: An information and knowledge exchange protocol. In Knowledge Building and Knowledge Sharing, K. Fuchi and T. Yokoi (Eds.), Ohmsha and IOS Press.Google Scholar
  48. Ford, R., Boutilier, C., and Kanazawa, K. 1994. Exploiting natural structure in reinforcement learning: Experience in robot soccerplaying. Unpublished Manuscript.Google Scholar
  49. Fox, D., Burgard, W., Kruppa, H., and Thrun, S. 2000. Aprobabilistic approach to collaborative multi-robot localization. Autonomous Robots, 8(3):325–344.Google Scholar
  50. rFujita, M. and Kageyama, K. 1997. An open architecture for robot entertainment. In Proceedings of the First International Conference on Autonomous Agents, Marina del Rey, CA, pp. 435–442.Google Scholar
  51. Genesereth, M.R. and Fikes, R.E. 1992. Knowledge interchange format, version 3.0 reference manual. Technical Report Logic-92-1, Computer Science Department, Stanford University.Google Scholar
  52. Glance, N.S. and Hogg, T. 1995. Dilemmas in computational societies. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 117–124.Google Scholar
  53. Goldman, C. and Rosenschein, J. 1994. Emergent coordination through the use of cooperative state-changing rules. In Proceedings of the Twelfth National Conference on Artificial Intelligence, Philadelphia, PA, Morgan Kaufman, pp. 408–413.Google Scholar
  54. Grabowski, R., Navarro-Serment, L.E., Paredis, C.J.J., and Khosla, P.K. 2000. Heterogeneous teams of modular robots for mapping and exploration. Autonomous Robots, 8(3):293–308.Google Scholar
  55. Grand, S. and Cliff, D. 1998. Creatures: Entertainment software agents with artificial life. Autonomous Agents and Multi-Agent Systems, 1(1):39–58.Google Scholar
  56. Grefenstette, J. and Daley, R. 1996. Methods for competitive and cooperative co-evolution. In Adaptation, Coevolution and Learning in Multiagent Systems: Papers from the 1996 AAAI Spring Symposium, Menlo Park, CA, AAAI Press, pp. 45–50, AAAI Technical Report SS-96-01.Google Scholar
  57. Gutmann, J.-S., Hattzack, W., Herrmann, I., Nebel, B., Rittinger, F., Topor, A., Weigel, T., and Welsch, B. 1998. The CS Freiburg team. In Proceedings of the Second RoboCupWorkshop, M. Asada (Ed.), Paris, France, pp. 451–458.Google Scholar
  58. Haddadi, A. 1995. Towards a pragmatic theory of interactions. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 133–139.Google Scholar
  59. Han, W.-G., Baek, S.-M., Kuc, T.-Y., and Kwan, S.K. 1996. Path planning of visual-served multiple mobile robots using the genetic algorithms. In Proceedings of the Micro-Robot World Cup Soccer Tournament, Taejon, Korea, IEEE Robotics and Automation Society, pp. 57–63.Google Scholar
  60. Han, K. and Veloso, M. 1998. Reactive visual control of multiple non-holonomic robotic agents. In Proceedings of the International Conference on Robotics and Automation, Leuven, Belgium.Google Scholar
  61. Hayes-Roth, B., Brownston, L., and van Gent, R. 1995. Multiagent collaboration in directed improvisation. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 148–154.Google Scholar
  62. Haynes, T. and Sen, S. 1998. Evolving behavioral strategies in predators and prey. In Adaptation and Learning in Multiagent Systems, G. Weiß and S. Sen (Eds.), Springer Verlag: Berlin, pp. 113–126.Google Scholar
  63. Haynes, T. and Sen, S. 1998. Learning cases to resolve conflicts and improve group behavior. International Journal of Human-Computer Studies, 48:31–49.Google Scholar
  64. Haynes, T., Wainwright, R., Sen, S., and Schoenefeld, D. 1995. Strongly typed genetic programming in evolving cooperation strategies. In Proceedings of the Sixth International Conference on Genetic Algorithms, S. Forrest (Ed.), Morgan Kaufman: San Mateo, CA, pp. 271–278.Google Scholar
  65. Hirai, K. 1997. Development of the Honda humanoid robot. Presentation at the CMU Robotics Institute Seminar. At URL http://www.honda.co.jp/home/hpr/e news/robot/.Google Scholar
  66. Holland, O.E. 1996. Multiagent systems: Lessons from social insects and collective robotics. In Adaptation, Coevolution and Learning in Multiagent Systems: Papers fromthe 1996 AAAI Spring Symposium, Menlo Park, CA, AAAI Press, pp. 57–62. AAAI Technical Report SS-96-01.Google Scholar
  67. Hong, S.-G., Eom, T.-D., Jeong, Il.-K., Choi, C., Shin, J.-H. and Lee, J.-J. 1996. Development of soccer-playing robots: Control, cooperation, and strategy. In Proceedings of the Micro-Robot World Cup Soccer Tournament, Taejon, Korea, IEEE Robotics and Automation Society, pp. 134–141.Google Scholar
  68. Hsia, T.C. and Soderstrand, M. 1996. Development of a micro robot system for playing soccer games. In Proceedings of the Micro-RobotWorld Cup Soccer Tournament, Taejon, Korea, IEEE Robotics and Automation Society, pp. 149–152.Google Scholar
  69. Huber, M.J. and Durfee, E.H. 1995. Deciding when to commit to action during observation-based coordination. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 163–170.Google Scholar
  70. Huberman, B. and Clearwater, S.H. 1995. A multi-agent system for controlling building environments. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 171–176.Google Scholar
  71. Inoue, N. and Wilkin, S. 1997. Learning system for the formation and the pass-play. Presented at the Poster Session of the IROS-96 Workshop on RoboCup.Google Scholar
  72. Jennings, N.R. and Wittig, T. 1992. Archon: Theory and practice. In Distributed Artificial Intelligence: Theory and Praxis, N.M. Avouris and L. Gasser (Eds.), Kluwer Academic Press, pp. 179–195.Google Scholar
  73. Jung, D. and Zelinsky, A. 2000. Grounded symbolic communication between heterogeneous cooperating robots. Autonomous Robots, 8(3):269–292.Google Scholar
  74. Kaelbling, L.P., Littman, M.L., and Moore, A.W. 1996. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4:237–285.Google Scholar
  75. Kim, J.-H. (Ed.). 1996. Proceedings of the Micro-Robot World Cup Soccer Tournament, Taejon, Korea.Google Scholar
  76. Kim, D.-Y. and Chung, M.J. 1996. Path planning for multi-mobile robots in the dynamic environment. In Proceedings of the Micro-Robot World Cup Soccer Tournament, Taejon, Korea, IEEE Robotics and Automation Society, pp. 127–132.Google Scholar
  77. Kim, K.-H., Ko, K.-W., Kim, J.-G., Lee, S.-H., and Cho, H.S. 1996. Multiple micro robots playing robot soccer game. In Proceedings of the Micro-RobotWorld Cup Soccer Tournament, Taejon, Korea, IEEE Robotics and Automation Society, pp. 38–43.Google Scholar
  78. Kitano, H. (Ed.). 1996. Proceedings of the IROS-96 Workshop on RoboCup, Osaka, Japan.Google Scholar
  79. Kitano, H. (Ed.). 1998. RoboCup-97: Robot Soccer World Cup I, Springer Verlag: Berlin.Google Scholar
  80. Kitano, H., Asada, M., Noda, I., and Matsubara, H. 1998. RoboCup: Robot world cup. Crossroads, 4.3.Google Scholar
  81. Kitano, H., Kuniyoshi, Y., Noda, I., Asada, M., Matsubara, H., and Osawa, E. 1997a. RoboCup: A challenge problem for AI. AI Magazine, 18(1):73–85.Google Scholar
  82. Kitano, H., Tambe, M., Stone, P., Veloso, M., Coradeschi, S. Osawa, E., Matsubara, H., Noda, I., and Asada, M. 1997b. The RoboCup synthetic agent challenge 97. In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, San Francisco, CA, Morgan Kaufmann, pp. 24–29.Google Scholar
  83. Korf, R.E. 1992. A simple solution to pursuit games. In Working Papers of the 11th InternationalWorkshop on Distributed Artificial Intelligence, pp. 183–194.Google Scholar
  84. Koza, J.R. 1992. Genetic Programming, MIT Press.Google Scholar
  85. Lesser, V.R. 1995. Multiagent systems: An emerging subdiscipline of AI. ACM Computing Surveys, 27(3):340–342.Google Scholar
  86. Lesser, V. 1998. Reflections on the nature of multi-agent coordination and its implications for an agent architecture. Autonomous Agents and Multi-Agent Systems, 1(1):89–112.Google Scholar
  87. rLevy, R. and Rosenschein, J.S. 1992. A game theoretic approach to the pursuit problem. In Working Papers of the 11th International Workshop on Distributed Artificial Intelligence, pp. 195–213.Google Scholar
  88. Littman, M.L. 1994. Markov games as a framework for multi-agent reinforcement learning. In Proceedings of the Eleventh International Conference on Machine Learning, San Mateo, CA, Morgan Kaufman, pp. 157–163.Google Scholar
  89. Luke, S., Hohn, C., Farris, J., Jackson, G., and Hendler, J. 1998. Co-evolving soccer softbot team coordination with genetic programming. In RoboCup-97: Robot SoccerWorld Cup I,, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 398–411.Google Scholar
  90. Lux, A. and Steiner, D. 1995. Understanding cooperation: Anagent's perspective. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 261–268.Google Scholar
  91. Mackworth, A.K. 1993. On seeing robots. In Computer Vision: Systems, Theory, and Applications, A. Basu and X. Li (Eds.), World Scientific Press: Singapore, pp. 1–13.Google Scholar
  92. Mataric, M.J. 1994a. Interaction and intelligent behavior. MIT EECS PhD Thesis AITR-1495, MIT AI Lab.Google Scholar
  93. Mataric, M.J. 1994b. Learning to behave socially. In Third International Conference on Simulation of Adaptive Behavior.Google Scholar
  94. Matsubara, H., Frank, I., Tanaka-Ishii, K., Noda, I., Nakashima, H., and Hasida, K. 1999. Automatic soccer commentary and RoboCup. In RoboCup-98: Robot SoccerWorld Cup II, M. Asada and H. Kitano (Eds.), Springer Verlag: Berlin.Google Scholar
  95. Matsubara, H., Noda, I., and Hiraki, K. 1996. Learning of cooperative actions in multi-agent systems: a case study of pass play in soccer. In Adaptation, Coevolution and Learning in Multiagent Systems: Papers from the 1996 AAAI Spring Symposium, Menlo Park, CA, AAAI Press, pp. 63–67. AAAI Technical Report SS-96-01.Google Scholar
  96. Matsumoto, A. and Nagai, H. 1998. Decision making by the characteristics and the interaction in multi-agent robotics soccer. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 132–143.Google Scholar
  97. Matsuyama, T. 1997. Cooperative distributed vision. In Proceedings of the First International Workshop on Cooperative Distributed Vision, Kyoto, Japan.Google Scholar
  98. Minsky, M.L. 1988. The Society of Mind, Simon & Schuster.Google Scholar
  99. Mizuno, H., Kourogi, M., Kawamoto, Y., and Muraoka, Y. 1998. A method applied for soccer's behaviors using proper feedback and feedforward control. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 156–167.Google Scholar
  100. Mizuno, H., Kourogi, M., and Muraoka, Y. 1996. Building shoobot possible to dribble and shoot. In Proceedings of the IROS-96Workshop on RoboCup.Google Scholar
  101. Mor, Y. and Rosenschein, J. 1995. Time and the prisoner's dilemma. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 276–282.Google Scholar
  102. Moukas, A. and Maes, P. 1997. Trafficopter: A distributed collection system for traffic information. At URL http://trafficopter. www.media.mit.edu/projects/trafficopter/.Google Scholar
  103. Nadella, R. and Sen, S. 1997. Correlating internal parameters and external performance: Learning soccer agents. In Distributed Artificial Intelligence Meets Machine Learning, G. Weiß (Ed.), Springer-Verlag, pp. 137–150.Google Scholar
  104. Nakashima, H., Noda, I., and Ohsawa, I. 1995. Organic programming for multi-agents. In Proceedings of the First International Conference on Multi-Agent Systems, V. Lesser (Ed.), MIT Press: San Francisco, CA, p. 459.Google Scholar
  105. Noda, I. 1998. Team GAMMA: Agent programming on gaea. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 500–507.Google Scholar
  106. Noda, I., Matsubara, H., Hiraki, K., and Frank, I. 1998. Soccer server: A tool for research on multiagent systems. Applied Artificial Intelligence, 12:233–250.Google Scholar
  107. Osawa, E.-I. 1995. A metalevel coordination strategy for reactive cooperative planning. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 297–303.Google Scholar
  108. Parker, L.E. 1994. Heterogeneous multi-robot cooperation. PhD Thesis, Massachusetts Institute of Technology.Google Scholar
  109. Parker, L.E. 2000. Life-long adaptation in heterogeneous multi-robot teams: Response to continual variation in individual robot performance. Autonomous Robots, 8(3):239–267.Google Scholar
  110. Van Dyke Parunak, H. 1996. Applications of distributed artificial intelligence in industry. In Foundations of Distributed Artificial Intelligence, G.M.P. O'Hare and N.R. Jennings (Eds.), Wiley Interscience, pp. 139–164.Google Scholar
  111. Van Dyke Parunak, H., Ward, A., and Sauter, J. 1998. A systematic market approach to distributed constraint problems. In Proceedings of the Third International Conference on Multi-Agent Systems, pp. 455–456.Google Scholar
  112. Permpoontanalarp, Y. 1995. Generalised proof-theory for multiagent autoepistemic reasoning. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 304–311.Google Scholar
  113. Pormerleau, D.A. 1993. Neural NetworkPerception for Mobile Robot Guidance, Kluwer Academic Publishers.Google Scholar
  114. Potter, M.A., De Jong, K.A., and Grefenstette, J.J. 1995. A coevolutionary approach to learning sequential decision rules. In Proceedings of the Sixth International Conference on Genetic Algorithms, S. Forrest (Ed.), Morgan Kaufman: San Mateo, CA, pp. 366–372.Google Scholar
  115. Prasad, M.V.N., Lander, S.E., and Lesser, V.R. 1998. Learning organizational roles for negotiated search in a multiagent system. International Journal of Human-Computer Studies, 48:51–67.Google Scholar
  116. Price, A., Jennings, A., and Kneen, J. 1998. RoboCup97: An omnidirectional perspective. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 320–332. Proceedings of the 10th International Workshop on Distributed Artificial Intelligence, Bandera, Texas, October 1990.Google Scholar
  117. Rao, A.S. and Georgeff, M.P. 1995. BDI agents: From theory to practice. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 312–319.Google Scholar
  118. Ridley, M. 1997. The Origins of Virtue: Human Instincts and the Evolution of Cooperation, Viking Press.Google Scholar
  119. Riekki, J. and Roening, J. 1998. Playing soccer by modifying and combining primitive reactions. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 74–87.Google Scholar
  120. Rosenschein, J.S. and Zlotkin, G. 1994. Rules of Encounter, MIT Press.Google Scholar
  121. Rosin, C.D. and Belew, R.K. 1995. Methods for competitive coevolution: Finding opponentsworth beating. In Proceedings of the Sixth International Conference on Genetic Algorithms, S. Forrest (Ed.), Morgan Kaufman: San Mateo, CA, pp. 373–380.Google Scholar
  122. Russell, S.J. and Norvig, P. 1995. Artificial Intelligence: A Modern Approach, Prentice Hall: Englewood Cliffs, NJ.Google Scholar
  123. Sahota, M.K. 1994. Reactive deliberation: An architecture for realtime intelligent control in dynamic environments. In Proceedings of the Twelfth National Conference on Artificial Intelligence, pp. 1303–1308.Google Scholar
  124. Sahota, M.K. 1996. Dynasim user guide. At URL http://www. cs.ubc.ca/nest/lci/soccer.Google Scholar
  125. Sahota, M.K., Mackworth, A.K., Barman, R.A., and Kingdon, S.J. 1995. Real-time control of soccer-playing robots using off-board vision: The Dynamite testbed. In IEEE International Conference on Systems, Man, and Cybernetics, pp. 3690–3663.Google Scholar
  126. Sanchez, J.A., Azevedo, F.S., and Leggett, J.J. 1995. Paragente: Exploring the issues in agent-based user interfaces. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 320–327.Google Scholar
  127. Sandholm, T.W. and Crites, R.H. 1996. On multiagent Q-learning in a semi-competitive domain. In Adaptation and Learning in Multiagent Systems, G. Weiß and S. Sen (Eds.), SpringerVerlag: Berlin.Google Scholar
  128. Sandholm, T. and Lesser, V. 1995. Coalition formation among bounded rational agents. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, Los Angeles, CA, Morgan Kaufman, pp. 662–669.Google Scholar
  129. Sandholm, T. and Lesser, V. 1995. Issues in automated negotiation and electronic commerce: Extending the contract net framework. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 328–335.Google Scholar
  130. Sandholm, T. and Lesser, V. 1996. Advantages of a leveled commitment contracting protocol. In Proceedings of the Thirteenth National Conference on Artificial Intelligence, Menlo Park, California, AAAI Press, pp. 126–133.Google Scholar
  131. Sargent, R., Bailey, B., Witty, C., and Wright, A. 1997. Dynamic object capture using fast vision tracking. AI Magazine, 18(1):65–72.Google Scholar
  132. Scerri, P. 1998. A multi-layered behavior based system for controlling RoboCup agents. In RoboCup-97: Robot SoccerWorld Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 467–474.Google Scholar
  133. Schaerf, A., Shoham, Y., and Tennenholtz, M. 1995. Adaptive load balancing: A study in multi-agent learning. Journal of Artificial Intelligence Research, 2:475–500.Google Scholar
  134. Schmidhuber, J. 1996. A general method for multi-agent reinforcement learning in unrestricted environments. In Adaptation, Coevolution and Learning in Multiagent Systems: Papers from the 1996 AAAI Spring Symposium, Menlo Park, CA, AAAI Press, pp. 84–87. AAAI Technical Report SS-96-01.Google Scholar
  135. Sen, S. (Ed.). 1996. Adaptation, Coevolution and Learning in Multiagent Systems: Papers from the 1996 AAAI Spring Symposium, Menlo Park, CA, AAAI, AAAI Press. AAAI Technical Report SS-96-01.Google Scholar
  136. Sen, S., Arora, N., and Roychowdhury, S. 1998. Using limited information to enhance group stabilitys. International Journal of Human-Computer Studies, 48:69–82.Google Scholar
  137. Shehory, O. and Kraus, S. 1995. Task allocation via coalition formation among autonomous agents. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, Los Angeles, CA, Morgan Kaufman, pp. 655–661.Google Scholar
  138. Shen, W.-M., Adibi, J., Adobbati, R., Cho, B., Erdem, A., Moradi, H., Salemi, B., and Tejada, S. 1998. Building integrated mobile robots for soccer competition. In Proceedings of the International Conference on Robotics and Automation.Google Scholar
  139. Shim, H.-S., Jung, M.-J., Kim, H.-S., Choi, I.-H., Han, W.-S., and Kim, J.-H. 1996. Designing distributed control architecture for cooperative multiagent systems. In Proceedings of the Micro-Robot World Cup Soccer Tournament, Taejon, Korea, IEEE Robotics and Automation Society, pp. 19–25.Google Scholar
  140. Shinjoh, A. 1998. RoboCup-3D: The construction of intelligent navigation system. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 188–199.Google Scholar
  141. Shoham, Y. 1990. Agent-oriented programming. Technical Report CS-1335-90, Computer Science Dept., Stanford University.Google Scholar
  142. Sichman, J.S. and Demazeau, Y. 1995. Exploiting social reasoning to deal with agency level inconistency. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 352–359.Google Scholar
  143. Smith, R.G. 1980. The contract net protocol: High-level communication and control in a distributed problem solver. IEEE Transactions on Computers, C-29(12):1104–1113.Google Scholar
  144. Stephens, L.M. and Merx, M.B. 1990. The effect of agent control strategy on the performance of a dai pursuit problem. In Proceedings of the 10th International Workshop on Distributed Artificial Intelligence, Bandera, Texas.Google Scholar
  145. Stone, P. 2000. Layered learning in multiagent systems: A winning approach to robotic soccer. Intelligent Robotics and Autonomous Agents, MIT Press.Google Scholar
  146. Stone, P. and Veloso, M. 1996. Beating a defender in robotic soccer: Memory-based learning of a continuous function. In Advances in Neural Information Processing Systems 8, D.S. Touretzky, M.C. Mozer, and M.E. Hasselmo (Eds.), MIT Press: Cambridge, MA, pp. 896–902.Google Scholar
  147. Stone, P. and Veloso, M. 1996. Using machine learning in the soccer server. In Proceedings of the IROS-96 Workshop on RoboCups, Osaka, Japan, pp. 19–27.Google Scholar
  148. Stone, P. and Veloso, M. 1998. Towards collaborative and adversarial learning: A case study in robotic soccer. International Journal of Human-Computer Studies, 48(1):83–104.Google Scholar
  149. rStone, P. and Veloso, M. 1999. Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork. Artificial Intelligence, 110(2):241–273.Google Scholar
  150. Stone, P., Veloso, M., and Riley, P. 1999. The CMUnited-98 champion simulator team. In RoboCup-98: Robot Soccer World Cup II. M. Asada and H. Kitano (Eds.), Springer Verlag: Berlin.Google Scholar
  151. Sugawara, T. and Lesser, V. 1993.On-line learning of coordination plans. COINS Technical Report 93-27, University of Massachussetts Computer Science Department.Google Scholar
  152. Sugawara, T. and Lesser, V. 1995. Learning coordination plans in distributed OS environments. In Proceedings of the First International Conference on Multi-Agent Systems, V. Lesser (Ed.), San Francisco, CA, MIT Press, p. 462.Google Scholar
  153. Sycara, K., Decker, K., Pannu, A., Williamson, M., and Zeng, D. 1996. Distributed intelligent agents. IEEE Expert, 11(6):36–46.Google Scholar
  154. Tambe, M. 1995. Recursive agent and agent-group tracking in a realtime, dynamic environment. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 368–375.Google Scholar
  155. Tambe, M. 1996. Tracking dynamic team activitys. In Proceedings of the Thirteenth National Conference on Artificial Intelligence, Menlo Park, California, AAAI Press.Google Scholar
  156. Tambe, M. 1997. Towards flexible teamwork. Journal of Artificial Intelligence Research, 7:81–124.Google Scholar
  157. Tambe, M., Adibi, J., Al-Onaizan, Y., Erdem, A., Kaminka, A., Marsela, S.C., Muslea, I., and Tallis, M. 1998. Using an explicit model of teamwork in RoboCup-97. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 123–131.Google Scholar
  158. Tan, M. 1993. Multi-agent reinforcement learning: Independent vs. cooperative agents. In Proceedings of the Tenth International Conference on Machine Learning, pp. 330–337.Google Scholar
  159. Uchibe, E., Asada, M., and Hosoda, K. 1996. Behavior coordination for a mobile robot using modular reinforcement learning. In Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems 1996 (IROS' 96), pp. 1329–1336.Google Scholar
  160. Uther, W.T.B. and Veloso, M.M. 1997. Generalizing adversarial reinforcement learning. In Proceedings of the AAAI Fall Symposium on Model Directed Autonomous Systems.Google Scholar
  161. Veloso, M., Bowling, M., Achim, S., Han, K., and Stone, P. 1999. The CMUnited-98 champion small robot team. In RoboCup-98: Robot Soccer World Cup II, M. Asada and H. Kitano (Eds.), Springer Verlag: Berlin.Google Scholar
  162. Veloso, M., Pagello, E., and Kitano, H. (Eds.). 2000. RoboCup-99: Robot Soccer World Cup III. Springer Verlag: Berlin.Google Scholar
  163. Veloso, M., Stone, P., and Han, K. 1998a. CMUnited-97: RoboCup-97 small-robot world champion team. AI Magazine, 19(3):61–69.Google Scholar
  164. Veloso, M., Stone, P., Han, K., and Achim, S. 1998b. The CMUnited-97 small-robot team. In RoboCup-97: Robot Soccer World Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 242–256.Google Scholar
  165. Veloso, M. and Uther, W. 1999. The CMTrio-98 Sony legged robot team. In RoboCup-98: Robot Soccer World Cup II, M. Asada and H. Kitano (Eds.), Springer Verlag: Berlins.Google Scholar
  166. Veloso, M., Uther, W., Fujita, M., Asada, M., and Kitano, H. 1998c. Playing soccer with legged robots. In Proceedings of IROS-98, Intelligent Robots and Systems Conferences, Victoria, Canada.Google Scholar
  167. Vidal, J.M. and Durfee, E.H. 1995. Recursive agent modeling using limited rationality. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 376–383.Google Scholar
  168. Walker, A. and Wooldridge, M. 1995. Understanding the emergence of conventions in multi-agent systems. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), Menlo Park, California, AAAI Press, pp. 384–389.Google Scholar
  169. Wang, X. 1996. Planning while learning operators. In Proceedings of the Third International Conference on AI Planning Systems.Google Scholar
  170. Weiß, G. 1995. Distributed reinforcement learning. Robotics and Autonomous Systems, 15:135–142.Google Scholar
  171. Weiß, G. 1996. ECAI-96 Workshop on Learning in Distributed Arti-ficial Intelligence, Call for Papers.Google Scholar
  172. Weiß, G. and Sen, S. (Eds.)(1996). Adaptation and Learning in Multiagent Systems, Springer Verlag: Berlin.Google Scholar
  173. Yokota, K., Ozaki, K., Matsumoto, A., Kawabata, K., Kaetsu, H. and Asama, H. 1998. Omni-directional autonomous robots cooperating for team play. In RoboCup-97: Robot SoccerWorld Cup I, H. Kitano (Ed.), Springer Verlag: Berlin, pp. 333–347.Google Scholar
  174. Zeng, D. and Sycara, K. 1998. Bayesian learning in negotiation. International Journal of Human-Computer Studies, 48:125–141.Google Scholar
  175. Zlotkin, G. and Rosenschein, J.S. 1994. Coalition, cryptography, and stability: Mechanisms for coalition formation in task oriented domains. In Proceedings of the Twelfth National Conference on Artificial Intelligence, Menlo Park, California, AAAI Press, pp. 432–437.Google Scholar

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Peter Stone
    • 1
  • Manuela Veloso
    • 2
  1. 1.AT&T Labs—ResearchFlorham Park
  2. 2.Computer Science DepartmentCarnegie Mellon UniversityPittsburgh

Personalised recommendations