DetH*: Approximate Hierarchical Solution of Large Markov Decision Processes
Abstract
This paper presents an algorithm for finding approximately optimal policies in very large Markov decision processes by constructing a hierarchical model and then solving it approximately. It exploits factored representations to achieve compactness and efficiency and to discover connectivity properties of the domain. We provide a bound on the quality of the solutions and give asymptotic analysis of the runtimes; in addition we demonstrate performance on a collection of very large domains. Results show that the quality of resulting policies is very good and the total running times, for both creating and solving the hierarchy, are significantly less than for an optimal factored MDP solver.
Cite
Text
Barry et al. "DetH*: Approximate Hierarchical Solution of Large Markov Decision Processes." International Joint Conference on Artificial Intelligence, 2011. doi:10.5591/978-1-57735-516-8/IJCAI11-323Markdown
[Barry et al. "DetH*: Approximate Hierarchical Solution of Large Markov Decision Processes." International Joint Conference on Artificial Intelligence, 2011.](https://mlanthology.org/ijcai/2011/barry2011ijcai-deth/) doi:10.5591/978-1-57735-516-8/IJCAI11-323BibTeX
@inproceedings{barry2011ijcai-deth,
title = {{DetH*: Approximate Hierarchical Solution of Large Markov Decision Processes}},
author = {Barry, Jennifer L. and Kaelbling, Leslie Pack and Lozano-Pérez, Tomás},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2011},
pages = {1928-1935},
doi = {10.5591/978-1-57735-516-8/IJCAI11-323},
url = {https://mlanthology.org/ijcai/2011/barry2011ijcai-deth/}
}