Designing good pursuit problems as testbeds for distributed AI: A novel application of genetic algorithms
A basic N x M instance (game) of the Pursuit Problem is one in which N pursuing agents try to capture as many as possible of M prey agents by surrounding them, on a rectilinear grid. The 4 × 1 game has been considered as a testbed for comparing the effectiveness of different multiagent distributed architectures, and the 6 × 2 game has received a little attention. This paper reports a systematic exercise in evaluating the quality of pursuit games as potential testbeds for distributed artificial intelligence (DAI). Genetic algorithms (GAs) have been used both to optimise low-level architectural features of agents and to search the (N, M) space of games. The conclusion from experiments is that (M + 4) × M games have the right complexity to be good testbeds, provided that M > 4. Additionally, the paper demonstrates the usefulness of GAs as tools to help DAI designers, and argues that boredom is a concept that deserves consideration as a feature of general agent architectures.
KeywordsAutonomous Agent Success Ratio Agent Architecture Pursuit Problem Blue Agent
Unable to display preview. Download preview PDF.
- T.L. Anderson and M. Donath (1990). Animal behavior as a paradigm for developing robot autonomy. In P. Maes (ed.), Designing autonomous agents: theory and practice from biology to engineering and back, 145–168. Cambridge, Massachussets: MIT Press.Google Scholar
- N. M. Avouris and L. Gasser (1992). Distributed Artificial Intelligence: Theory and Praxis, 1–7, Dordrecht: Kluwer Academic Publishers.Google Scholar
- M. Benda, V. Jagannathan, and R. Dodhiawala. On optimal cooperation of knowledge sources. Technical Report BCS-G2010-28, Boeing AI Center, Boeing Computer Services, Bellevue, Washington, August 1985. Cited in L. Gasser, N. F. Rouquette, R. W. Hill, and J. Lieb, (1989). Representing and Using Organizational Knowledge in Distributed AI Systems. In L. Gasser and M. N. Huhns (eds.), Distributed Artificial Intelligence, 2: 55–78, London: Pitman.Google Scholar
- L. Gasser and M. N. Huhns, Themes in Distributed Artificial Intelligence Research (1989). In L. Gasser and M. N. Huhns (eds.), Distributed Artificial Intelligence, 2: vii–xv, London: Pitman.Google Scholar
- L. Gasser, N. F. Rouquette, R. W. Hill, and J. Lieb, Representing and Using Organizational Knowledge in Distributed AI Systems. In L. Gasser and M. N. Huhns (eds.), Distributed Artificial Intelligence, 2: 55–78, London: Pitman.Google Scholar
- L. Gasser (1992). An Overview of DAI. In N. M. Avouris and L. Gasser (eds.), Distributed Artificial Intelligence: Theory and Praxis, 9–30. Dordrecht: Kluwer Academic Publishers.Google Scholar
- D. E. Goldberg (1989). Genetic Algorithms in Search, Optimization and Machine Learning. Reading, Massachussets: Addison Wesley.Google Scholar
- J. H. Holland (1975). Adaptation in natural and artificial systems. Ann Arbor, Michigan: University of Michigan Press.Google Scholar
- R. Levy and J. S. Rosenschein (1992). A Game Theoretic Approach to Distributed Artificial Intelligence and the Pursuit Problem. In Y. Demazeau and E. Werner (eds.), Decentralized Artificial Intelligence III, 129–146, Amsterdam: Elsevier Science Publishers B.V./North-Holland.Google Scholar
- L. M. Stephens and M. B. Merx (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, October 1990.Google Scholar
- E. Werner, Cooperative Agents: A Unified Theory of Communication and Social Structure. In L. Gasser and M. N. Huhns (eds.), Distributed Artificial Intelligence, 2: 3–36, London: Pitman.Google Scholar