ML Anthology

On-Line Estimation of the Optimal Value Function: HJB- Estimators

James K. Peterson
NeurIPS 1992 pp. 319-326
/neurips/1992/peterson1992neurips-online/

Abstract

In this paper, we discuss on-line estimation strategies that model the optimal value function of a typical optimal control problem. We present a general strategy that uses local corridor solutions obtained via dynamic programming to provide local optimal con(cid:173) trol sequence training data for a neural architecture model of the optimal value function.

PDF NeurIPS Semantic Scholar

Cite

Text

Peterson. "On-Line Estimation of the Optimal Value Function: HJB- Estimators." Neural Information Processing Systems, 1992.

Markdown

[Peterson. "On-Line Estimation of the Optimal Value Function: HJB- Estimators." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/peterson1992neurips-online/)

BibTeX

@inproceedings{peterson1992neurips-online,
  title     = {{On-Line Estimation of the Optimal Value Function: HJB- Estimators}},
  author    = {Peterson, James K.},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {319-326},
  url       = {https://mlanthology.org/neurips/1992/peterson1992neurips-online/}
}