ML Anthology

Analyzing Feature Generation for Value-Function Approximation

Ronald Parr, Christopher Painter-Wakefield, Lihong Li, Michael L. Littman
ICML 2007 pp. 737-744
doi:10.1145/1273496.1273589 /icml/2007/parr2007icml-analyzing/

Abstract

We analyze a simple, Bellman-error-based approach to generating basis functions for valuefunction approximation. We show that it generates orthogonal basis functions that provably tighten approximation error bounds. We also illustrate the use of this approach in the presence of noise on some sample problems.

PDF ICML Semantic Scholar

Cite

Text

Parr et al. "Analyzing Feature Generation for Value-Function Approximation." International Conference on Machine Learning, 2007. doi:10.1145/1273496.1273589

Markdown

[Parr et al. "Analyzing Feature Generation for Value-Function Approximation." International Conference on Machine Learning, 2007.](https://mlanthology.org/icml/2007/parr2007icml-analyzing/) doi:10.1145/1273496.1273589

BibTeX

@inproceedings{parr2007icml-analyzing,
  title     = {{Analyzing Feature Generation for Value-Function Approximation}},
  author    = {Parr, Ronald and Painter-Wakefield, Christopher and Li, Lihong and Littman, Michael L.},
  booktitle = {International Conference on Machine Learning},
  year      = {2007},
  pages     = {737-744},
  doi       = {10.1145/1273496.1273589},
  url       = {https://mlanthology.org/icml/2007/parr2007icml-analyzing/}
}