Risk Sensitive Reinforcement Learning

Abstract

A directed generative model for binary data using a small number of hidden continuous units is investigated. A clipping nonlinear(cid:173) ity distinguishes the model from conventional principal components analysis. The relationships between the correlations of the underly(cid:173) ing continuous Gaussian variables and the binary output variables are utilized to learn the appropriate weights of the network. The advantages of this approach are illustrated on a translationally in(cid:173) variant binary distribution and on handwritten digit images.

Cite

Text

Neuneier and Mihatsch. "Risk Sensitive Reinforcement Learning." Neural Information Processing Systems, 1998.

Markdown

[Neuneier and Mihatsch. "Risk Sensitive Reinforcement Learning." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/neuneier1998neurips-risk/)

BibTeX

@inproceedings{neuneier1998neurips-risk,
  title     = {{Risk Sensitive Reinforcement Learning}},
  author    = {Neuneier, Ralph and Mihatsch, Oliver},
  booktitle = {Neural Information Processing Systems},
  year      = {1998},
  pages     = {1031-1037},
  url       = {https://mlanthology.org/neurips/1998/neuneier1998neurips-risk/}
}