Skip to main content
Journal cover image

Constrained attractor selection using deep reinforcement learning

Publication ,  Journal Article
Wang, XS; Turner, JD; Mann, BP
Published in: JVC/Journal of Vibration and Control
March 1, 2021

This study describes an approach for attractor selection (or multistability control) in nonlinear dynamical systems with constrained actuation. Attractor selection is obtained using two different deep reinforcement learning methods: (1) the cross-entropy method and (2) the deep deterministic policy gradient method. The framework and algorithms for applying these control methods are presented. Experiments were performed on a Duffing oscillator, as it is a classic nonlinear dynamical system with multiple attractors. Both methods achieve attractor selection under various control constraints. Although these methods have nearly identical success rates, the deep deterministic policy gradient method has the advantages of a high learning rate, low performance variance, and a smooth control approach. This study demonstrates the ability of two reinforcement learning approaches to achieve constrained attractor selection.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

JVC/Journal of Vibration and Control

DOI

EISSN

1741-2986

ISSN

1077-5463

Publication Date

March 1, 2021

Volume

27

Issue

5-6

Start / End Page

502 / 514

Related Subject Headings

  • Acoustics
  • 4017 Mechanical engineering
  • 4005 Civil engineering
  • 0913 Mechanical Engineering
  • 0906 Electrical and Electronic Engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Wang, X. S., Turner, J. D., & Mann, B. P. (2021). Constrained attractor selection using deep reinforcement learning. JVC/Journal of Vibration and Control, 27(5–6), 502–514. https://doi.org/10.1177/1077546320930144
Wang, X. S., J. D. Turner, and B. P. Mann. “Constrained attractor selection using deep reinforcement learning.” JVC/Journal of Vibration and Control 27, no. 5–6 (March 1, 2021): 502–14. https://doi.org/10.1177/1077546320930144.
Wang XS, Turner JD, Mann BP. Constrained attractor selection using deep reinforcement learning. JVC/Journal of Vibration and Control. 2021 Mar 1;27(5–6):502–14.
Wang, X. S., et al. “Constrained attractor selection using deep reinforcement learning.” JVC/Journal of Vibration and Control, vol. 27, no. 5–6, Mar. 2021, pp. 502–14. Scopus, doi:10.1177/1077546320930144.
Wang XS, Turner JD, Mann BP. Constrained attractor selection using deep reinforcement learning. JVC/Journal of Vibration and Control. 2021 Mar 1;27(5–6):502–514.
Journal cover image

Published In

JVC/Journal of Vibration and Control

DOI

EISSN

1741-2986

ISSN

1077-5463

Publication Date

March 1, 2021

Volume

27

Issue

5-6

Start / End Page

502 / 514

Related Subject Headings

  • Acoustics
  • 4017 Mechanical engineering
  • 4005 Civil engineering
  • 0913 Mechanical Engineering
  • 0906 Electrical and Electronic Engineering