We investigate classifier systems' reward schemes by way of an example that highlights the interaction of local reward schemes and recombination. We contrast averaging schemes and maximizing schemes. Our example illustrates a sense in which certain recombination operators mesh more gracefully with averaging schemes than with maximizing schemes.

Credit assignment, classifiers, genetic algorithms, reinforcement, reward, bucket brigade, Q-learning
This content is only available as a PDF.
© 2001 Massachusetts Institute of Technology
2001
You do not currently have access to this content.