The Adaptive K-Meteorologists Problem and Its Application to Structure Learning and Feature Selection in Reinforcement Learning
Abstract
The purpose of this paper is three-fold. First, we formalize and study a problem of learning probabilistic concepts in the recently proposed KWIK framework. We give details of an algorithm, known as the Adaptive k-Meteorologists Algorithm, analyze its sample complexity upper bound, and give a matching lower bound. Second, this algorithm is used to create a new reinforcement learning algorithm for factoredstate problems that enjoys significant improvement over the previous state-of-the-art algorithm. Finally, we apply the Adaptive k-Meteorologists Algorithm to remove a limiting assumption in an existing reinforcement-learning algorithm. The effectiveness of our approaches are demonstrated empirically in a couple benchmark domains as well as a robotics navigation problem.
Cite
Text
Diuk et al. "The Adaptive K-Meteorologists Problem and Its Application to Structure Learning and Feature Selection in Reinforcement Learning." International Conference on Machine Learning, 2009. doi:10.1145/1553374.1553406Markdown
[Diuk et al. "The Adaptive K-Meteorologists Problem and Its Application to Structure Learning and Feature Selection in Reinforcement Learning." International Conference on Machine Learning, 2009.](https://mlanthology.org/icml/2009/diuk2009icml-adaptive/) doi:10.1145/1553374.1553406BibTeX
@inproceedings{diuk2009icml-adaptive,
title = {{The Adaptive K-Meteorologists Problem and Its Application to Structure Learning and Feature Selection in Reinforcement Learning}},
author = {Diuk, Carlos and Li, Lihong and Leffler, Bethany R.},
booktitle = {International Conference on Machine Learning},
year = {2009},
pages = {249-256},
doi = {10.1145/1553374.1553406},
url = {https://mlanthology.org/icml/2009/diuk2009icml-adaptive/}
}