ML Anthology

Action Refinement in Reinforcement Learning by Probability Smoothing

Thomas G. Dietterich, Dídac Busquets, Ramón López de Mántaras, Carles Sierra
ICML 2002 pp. 107-114
/icml/2002/dietterich2002icml-action/

Abstract

In many reinforcement learning applications, the set of possible actions can be partitioned by the programmer into subsets of similar actions.

Semantic Scholar

Cite

Text

Dietterich et al. "Action Refinement in Reinforcement Learning by Probability Smoothing." International Conference on Machine Learning, 2002.

Markdown

[Dietterich et al. "Action Refinement in Reinforcement Learning by Probability Smoothing." International Conference on Machine Learning, 2002.](https://mlanthology.org/icml/2002/dietterich2002icml-action/)

BibTeX

@inproceedings{dietterich2002icml-action,
  title     = {{Action Refinement in Reinforcement Learning by Probability Smoothing}},
  author    = {Dietterich, Thomas G. and Busquets, Dídac and de Mántaras, Ramón López and Sierra, Carles},
  booktitle = {International Conference on Machine Learning},
  year      = {2002},
  pages     = {107-114},
  url       = {https://mlanthology.org/icml/2002/dietterich2002icml-action/}
}