Approximately Optimal Approximate Reinforcement Learning

Kakade, Sham M.; Langford, John

Approximately Optimal Approximate Reinforcement Learning

ICML 2002 pp. 267-274

/icml/2002/kakade2002icml-approximately/

Abstract

In order to solve realistic reinforcement learning problems, it is critical that approximate algorithms be used. In this paper,

Semantic Scholar

Cite

Text

Kakade and Langford. "Approximately Optimal Approximate Reinforcement Learning." International Conference on Machine Learning, 2002.

Markdown

[Kakade and Langford. "Approximately Optimal Approximate Reinforcement Learning." International Conference on Machine Learning, 2002.](https://mlanthology.org/icml/2002/kakade2002icml-approximately/)

BibTeX

@inproceedings{kakade2002icml-approximately,
  title     = {{Approximately Optimal Approximate Reinforcement Learning}},
  author    = {Kakade, Sham M. and Langford, John},
  booktitle = {International Conference on Machine Learning},
  year      = {2002},
  pages     = {267-274},
  url       = {https://mlanthology.org/icml/2002/kakade2002icml-approximately/}
}