Coevolutionary Learning: A Case Study

Coevolutionary learning, which involves the embedding of adaptive learning agents in a tness environment that dynamically responds to their progress, is a potential solution for many technological chicken and egg problems. However, several impediments have to be overcome in order for coevolutionary learning to achieve continuous progress in the long term. This paper presents some of those problems and proposes a framework to address them. This presentation is illustrated with a case study: the evolution of CA rules. Our application of coevolutionary learning resulted in a very signi cant improvement for that problem compared to the best known results.

[1]  Richard K. Belew,et al.  Methods for Competitive Co-Evolution: Finding Opponents Worth Beating , 1995, ICGA.

[2]  Richard K. Belew,et al.  New Methods for Competitive Coevolution , 1997, Evolutionary Computation.

[3]  Kenneth A. De Jong,et al.  Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents , 2000, Evolutionary Computation.

[4]  Dave Cliff,et al.  Tracking the Red Queen: Measurements of Adaptive Progress in Co-Evolutionary Simulations , 1995, ECAL.

[5]  James P. Crutchfield,et al.  A Genetic Algorithm Discovers Particle-Based Computation in Cellular Automata , 1994, PPSN.

[6]  Samir W. Mahfoud.  Niching methods for genetic algorithms , 1996 .

[7]  Melanie Mitchell,et al.  Evolving cellular automata to perform computations: mechanisms and impediments , 1994 .

[8]  Land,et al.  No perfect two-state cellular automata for density classification exists. , 1995, Physical review letters.

[9]  Jan Paredis,et al.  Coevolving Cellular Automata: Be Aware of the Red Queen! , 1997, ICGA.

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

[11]  Richard K. Belew,et al.  Coevolutionary search among adversaries , 1997 .

[12]  Jordan B. Pollack,et al.  Co-Evolving Intertwined Spirals , 1996, Evolutionary Programming.

[13]  Corso Elvezia.  Discovering Solutions with Low Kolmogorov Complexity and High Generalization Capability , 1995 .

[14]  Jordan B. Pollack,et al.  Coevolution of a Backgammon Player , 1996 .

[15]  James P. Crutchfield,et al.  Revisiting the Edge of Chaos: Evolving Cellular Automata to Perform Computations , 1993, Complex Syst..

[16]  Capcarrere,et al.  Two-state, r=1 Cellular Automaton that Classifies Density. , 1996, Physical review letters.