Adaptive stochastic cellular automata: Applications

S. Qian, Y. C. Lee, R. D. Jones, C. W. Barnes, G. W. Flake, M. K. O'Rourke, K. Lee, H. H. Chen, G. Z. Sun, Y. Q. Zhang, D. Chen, C. L. Giles

Research output: Contribution to journalArticle

5 Scopus citations

Abstract

The stochastic learning cellular automata model has been applied to the problem of controlling unstable systems. Two example unstable systems studied are controlled by an adaptive stochastic cellular automata algorithm with an adaptive critic. The reinforcement learning algorithm and the architecture of the stochastic CA controller are presented. Learning to balance a single pole is discussed in detail. Balancing an inverted double pendulum highlights the power of the stochastic CA approach. The stochastic CA model is compared to conventional adaptive control and artificial neural network approaches.

Original languageEnglish (US)
Pages (from-to)181-188
Number of pages8
JournalPhysica D: Nonlinear Phenomena
Volume45
Issue number1-3
DOIs
StatePublished - Sep 2 1990

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Statistical and Nonlinear Physics
  • Mathematical Physics
  • Condensed Matter Physics
  • Applied Mathematics

Cite this

Qian, S., Lee, Y. C., Jones, R. D., Barnes, C. W., Flake, G. W., O'Rourke, M. K., Lee, K., Chen, H. H., Sun, G. Z., Zhang, Y. Q., Chen, D., & Giles, C. L. (1990). Adaptive stochastic cellular automata: Applications. Physica D: Nonlinear Phenomena, 45(1-3), 181-188. https://doi.org/10.1016/0167-2789(90)90181-N