ML Anthology

Learning by State Recurrence Detection

Bruce E. Rosen, James M. Goodwin, Jacques J. Vidal
NeurIPS 1987 pp. 642-651
/neurips/1987/rosen1987neurips-learning/

Abstract

This research investigates a new technique for unsupervised learning of nonlinear control problems. The approach is applied both to Michie and Chambers BOXES algorithm and to Barto, Sutton and Anderson's extension, the ASE/ACE system, and has significantly improved the convergence rate of stochastically based learning automata.

PDF NeurIPS Semantic Scholar

Cite

Text

Rosen et al. "Learning by State Recurrence Detection." Neural Information Processing Systems, 1987.

Markdown

[Rosen et al. "Learning by State Recurrence Detection." Neural Information Processing Systems, 1987.](https://mlanthology.org/neurips/1987/rosen1987neurips-learning/)

BibTeX

@inproceedings{rosen1987neurips-learning,
  title     = {{Learning by State Recurrence Detection}},
  author    = {Rosen, Bruce E. and Goodwin, James M. and Vidal, Jacques J.},
  booktitle = {Neural Information Processing Systems},
  year      = {1987},
  pages     = {642-651},
  url       = {https://mlanthology.org/neurips/1987/rosen1987neurips-learning/}
}