Machine Learning

, Volume 13, Issue 2, pp 259–284

Genetic reinforcement learning for neurocontrol problems

  • Darrell Whitley
  • Stephen Dominic
  • Rajarshi Das
  • Charles W. Anderson
Article

DOI: 10.1007/BF00993045

Cite this article as:
Whitley, D., Dominic, S., Das, R. et al. Mach Learn (1993) 13: 259. doi:10.1007/BF00993045
  • 465 Downloads

Abstract

Empirical tests indicate that at least one class of genetic algorithms yields good performance for neural network weight optimization in terms of learning rates and scalability. The successful application of these genetic algorithms to supervised learning problems sets the stage for the use of genetic algorithms in reinforcement learning problems. On a simulated inverted-pendulum control problem, “genetic reinforcement learning” produces competitive results with AHC, another well-known reinforcement learning paradigm for neural networks that employs the temporal difference method. These algorithms are compared in terms of learning rates, performance-based generalization, and control behavior over time.

Keywords

Genetic algorithms reinforcement learning neural networks adaptive control 
Download to read the full article text

Copyright information

© Kluwer Academic Publishers 1993

Authors and Affiliations

  • Darrell Whitley
    • 1
  • Stephen Dominic
    • 1
  • Rajarshi Das
    • 1
  • Charles W. Anderson
    • 1
  1. 1.Computer Science DepartmentColorado State UniversityFort Collins

Personalised recommendations