A Coevolutionary Approach to Learning Sequential Decision Rules

We present a coevolutionary approach to learning sequential decision rules which appears to have a number of advantages over non-coevolutionary approaches. The coevolutionary approach encourages the formation of stable niches representing simpler subbehaviors. The evolutionary direction of each subbehavior can be controlled independently, providing an alternative to evolving complex behavior using intermediate training steps. Results are presented showing a significant learning rate speedup over a noncoevolutionary approach in a simulated robot domain. In addition, the results suggest the coevolutionary approach may lead to emergent problem decompositions.

[1]  K. Dejong,et al.  An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[2]  Kenneth Alan De Jong,et al.  An analysis of the behavior of a class of genetic adaptive systems. , 1975 .

[3]  John H. Holland,et al.  Cognitive systems based on adaptive algorithms , 1977, SGAR.

[4]  John H. Holland,et al.  COGNITIVE SYSTEMS BASED ON ADAPTIVE ALGORITHMS1 , 1978 .

[5]  Donald A. Waterman,et al.  Pattern-Directed Inference Systems , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Paul Bryant Grosso,et al.  Computer Simulations of Genetic Adaptation: Parallel Subcomponent Interaction in a Multilocus Model , 1985 .

[7]  Dana S. Richards,et al.  Punctuated Equilibria: A Parallel Genetic Algorithm , 1987, ICGA.

[8]  John J. Grefenstette,et al.  A Parallel Genetic Algorithm , 1987, ICGA.

[9]  Reiko Tanese,et al.  Distributed Genetic Algorithms , 1989, ICGA.

[10]  Kalyanmoy Deb,et al.  An Investigation of Niche and Species Formation in Genetic Function Optimization , 1989, ICGA.

[11]  L. Darrell Whitley,et al.  GENITOR II: a distributed genetic algorithm , 1990, J. Exp. Theor. Artif. Intell..

[12]  Hugo de Garis,et al.  Genetic Programming , 1990, ML.

[13]  W. Daniel Hillis,et al.  Co-evolving parasites improve simulated evolution as an optimization procedure , 1990 .

[14]  Yuval Davidor,et al.  A Naturally Occurring Niche and Species Phenomenon: The Model and First Results , 1991, ICGA.

[15]  Phil Husbands,et al.  Simulated Co-Evolution as the Mechanism for Emergent Planning and Scheduling , 1991, ICGA.

[16]  L.-J. Lin,et al.  Hierarchical learning of robot skills by reinforcement , 1993, IEEE International Conference on Neural Networks.

[17]  Alan S. Perelson,et al.  Using Genetic Algorithms to Explore Pattern Recognition in the Immune System , 1993, Evolutionary Computation.

[18]  Kenneth A. De Jong,et al.  A Cooperative Coevolutionary Approach to Function Optimization , 1994, PPSN.

[19]  Lorenza Saitta,et al.  Learning Disjunctive Concepts by Means of Genetic Algorithms , 1994, ICML.