Machine Learning

, Volume 22, Issue 1, pp 11–32

Efficient reinforcement learning through symbiotic evolution

  • David E. Moriarty
  • Risto Miikkulainen
Article

DOI: 10.1007/BF00114722

Cite this article as:
Moriarty, D.E. & Miikkulainen, R. Mach Learn (1996) 22: 11. doi:10.1007/BF00114722

Abstract

This article presents a new reinforcement learning method called SANE (Symbiotic, Adaptive Neuro-Evolution), which evolves a population of neurons through genetic algorithms to form a neural network capable of performing a task. Symbiotic evolution promotes both cooperation and specialization, which results in a fast, efficient genetic search and discourages convergence to suboptimal solutions. In the inverted pendulum problem, SANE formed effective networks 9 to 16 times faster than the Adaptive Heuristic Critic and 2 times faster thanQ-learning and the GENITOR neuro-evolution approach without loss of generalization. Such efficient learning, combined with few domain assumptions, make SANE a promising approach to a broad range of reinforcement learning problems, including many real-world applications.

Keywords

Neuro-Evolution Reinforcement Learning Genetic Algorithms Neural Networks 
Download to read the full article text

Copyright information

© Kluwer Academic Publishers 1996

Authors and Affiliations

  • David E. Moriarty
    • 1
  • Risto Miikkulainen
    • 1
  1. 1.Department of Computer SciencesThe University of Texas at AustinAustin

Personalised recommendations