Skip to main content

Reinforcement learning via kernel temporal difference.

Publication ,  Conference
Bae, J; Chhatbar, P; Francis, JT; Sanchez, JC; Principe, JC
Published in: Annu Int Conf IEEE Eng Med Biol Soc
2011

This paper introduces a kernel adaptive filter implemented with stochastic gradient on temporal differences, kernel Temporal Difference (TD)(λ), to estimate the state-action value function in reinforcement learning. The case λ=0 will be studied in this paper. Experimental results show the method's applicability for learning motor state decoding during a center-out reaching task performed by a monkey. The results are compared to the implementation of a time delay neural network (TDNN) trained with backpropagation of the temporal difference error. From the experiments, it is observed that kernel TD(0) allows faster convergence and a better solution than the neural network.

Duke Scholars

Published In

Annu Int Conf IEEE Eng Med Biol Soc

DOI

EISSN

2694-0604

Publication Date

2011

Volume

2011

Start / End Page

5662 / 5665

Location

United States

Related Subject Headings

  • User-Computer Interface
  • Reinforcement, Psychology
  • Pattern Recognition, Automated
  • Humans
  • Electroencephalography
  • Brain
  • Biomimetics
  • Artificial Intelligence
  • Algorithms
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Bae, J., Chhatbar, P., Francis, J. T., Sanchez, J. C., & Principe, J. C. (2011). Reinforcement learning via kernel temporal difference. In Annu Int Conf IEEE Eng Med Biol Soc (Vol. 2011, pp. 5662–5665). United States. https://doi.org/10.1109/IEMBS.2011.6091370
Bae, Jihye, Pratik Chhatbar, Joseph T. Francis, Justin C. Sanchez, and Jose C. Principe. “Reinforcement learning via kernel temporal difference.” In Annu Int Conf IEEE Eng Med Biol Soc, 2011:5662–65, 2011. https://doi.org/10.1109/IEMBS.2011.6091370.
Bae J, Chhatbar P, Francis JT, Sanchez JC, Principe JC. Reinforcement learning via kernel temporal difference. In: Annu Int Conf IEEE Eng Med Biol Soc. 2011. p. 5662–5.
Bae, Jihye, et al. “Reinforcement learning via kernel temporal difference.Annu Int Conf IEEE Eng Med Biol Soc, vol. 2011, 2011, pp. 5662–65. Pubmed, doi:10.1109/IEMBS.2011.6091370.
Bae J, Chhatbar P, Francis JT, Sanchez JC, Principe JC. Reinforcement learning via kernel temporal difference. Annu Int Conf IEEE Eng Med Biol Soc. 2011. p. 5662–5665.

Published In

Annu Int Conf IEEE Eng Med Biol Soc

DOI

EISSN

2694-0604

Publication Date

2011

Volume

2011

Start / End Page

5662 / 5665

Location

United States

Related Subject Headings

  • User-Computer Interface
  • Reinforcement, Psychology
  • Pattern Recognition, Automated
  • Humans
  • Electroencephalography
  • Brain
  • Biomimetics
  • Artificial Intelligence
  • Algorithms