Neuroevolution for adaotive teams
Authors:
- 9 July 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 2194-2201
Abstract
We introduce the Adaptive Team of Agents (ATA), a system of homogeneous agents with identical control policies which nevertheless adopt heterogeneous roles appropriate to their environment. ATAs have ap- plications in domains such as games, and can be evolved through neuroevolution. In this paper we show how ATAs can be evolved to solve the problem posed by a simple strategy game and discuss their application to richer environments.Keywords
This publication has 9 references indexed in Scilit:
- Active Guidance for a Finless Rocket Using Neuroevolution2003
- Genetic algorithms: bridging the convergence gapTheoretical Computer Science, 1999
- Forming Neural Networks Through Efficient and Adaptive CoevolutionEvolutionary Computation, 1997
- Incremental Evolution of Complex General BehaviorAdaptive Behavior, 1997
- Subsymbolic Case‐Role Analysis of Sentences with Embedded ClausesCognitive Science, 1996
- Analog computation via neural networksTheoretical Computer Science, 1994
- A review of evolutionary artificial neural networksInternational Journal of Intelligent Systems, 1993
- Finding structure in timeCognitive Science, 1990
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989