Efficient Structure Learning in Factored-State MDPs
Abstract
We consider the problem of reinforcement learning in factored-state MDPs in the setting in which learning is conducted in one long trial with no resets allowed. We show how to extend existing efficient algorithms that learn the conditional probability tables of dynamic Bayesian networks (DBNs) given their structure to the case in which DBN structure is not known in advance. Our method learns the DBN structures as part of the reinforcement-learning process and provably provides an efficient learning algorithm when combined with factored Rmax.
Cite
Text
Strehl et al. "Efficient Structure Learning in Factored-State MDPs." AAAI Conference on Artificial Intelligence, 2007.Markdown
[Strehl et al. "Efficient Structure Learning in Factored-State MDPs." AAAI Conference on Artificial Intelligence, 2007.](https://mlanthology.org/aaai/2007/strehl2007aaai-efficient/)BibTeX
@inproceedings{strehl2007aaai-efficient,
title = {{Efficient Structure Learning in Factored-State MDPs}},
author = {Strehl, Alexander L. and Diuk, Carlos and Littman, Michael L.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2007},
pages = {645-650},
url = {https://mlanthology.org/aaai/2007/strehl2007aaai-efficient/}
}