Online Linear Regression and Its Application to Model-Based Reinforcement Learning
Abstract
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a model-based approach and show that a special type of online linear regression allows us to learn MDPs with (possibly kernalized) linearly parameterized dynamics. This result builds on Kearns and Singh's work that provides a provably efficient algorithm for finite state MDPs. Our approach is not restricted to the linear setting, and is applicable to other classes of continuous MDPs.
Cite
Text
Strehl and Littman. "Online Linear Regression and Its Application to Model-Based Reinforcement Learning." Neural Information Processing Systems, 2007.Markdown
[Strehl and Littman. "Online Linear Regression and Its Application to Model-Based Reinforcement Learning." Neural Information Processing Systems, 2007.](https://mlanthology.org/neurips/2007/strehl2007neurips-online/)BibTeX
@inproceedings{strehl2007neurips-online,
title = {{Online Linear Regression and Its Application to Model-Based Reinforcement Learning}},
author = {Strehl, Alexander L. and Littman, Michael L.},
booktitle = {Neural Information Processing Systems},
year = {2007},
pages = {1417-1424},
url = {https://mlanthology.org/neurips/2007/strehl2007neurips-online/}
}