Approximate Predictive Representations of Partially Observable Systems
Abstract
We provide a novel view of learning an approximate model of a partially observable environment from data and present a simple implementation of the idea. The learned model abstracts away unnecessary details of the agent's experience and focuses only on making certain predictions of interest. We illustrate our approach empirically in small computational examples, demonstrating the data efficiency of the algorithm.
Cite
Text
Dinculescu and Precup. "Approximate Predictive Representations of Partially Observable Systems." International Conference on Machine Learning, 2010.Markdown
[Dinculescu and Precup. "Approximate Predictive Representations of Partially Observable Systems." International Conference on Machine Learning, 2010.](https://mlanthology.org/icml/2010/dinculescu2010icml-approximate/)BibTeX
@inproceedings{dinculescu2010icml-approximate,
title = {{Approximate Predictive Representations of Partially Observable Systems}},
author = {Dinculescu, Monica and Precup, Doina},
booktitle = {International Conference on Machine Learning},
year = {2010},
pages = {895-902},
url = {https://mlanthology.org/icml/2010/dinculescu2010icml-approximate/}
}