DetH*: Approximate Hierarchical Solution of Large Markov Decision Processes
Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 1928-1934.
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.
@inproceedings{ijcai2011p323,
title = {DetH*: Approximate Hierarchical Solution of Large Markov Decision Processes},
author = {Barry, Jennifer L. and Kaelbling, Leslie Pack and Lozano-Perez, Tomas},
booktitle = {Proceedings of the Twenty-Second International Joint Conference on
Artificial Intelligence, {IJCAI-11}},
publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
editor = {Toby Walsh},
pages = {1928--1934},
year = {2011},
month = {7},
doi = {10.5591/978-1-57735-516-8/IJCAI11-323},
url = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-323},
}
TY - CPAPER TI - DetH*: Approximate Hierarchical Solution of Large Markov Decision Processes AU - Barry, Jennifer L. AU - Kaelbling, Leslie Pack AU - Lozano-Perez, Tomas T2 - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11 PB - AAAI Press/International Joint Conferences on Artificial Intelligence PY - 2011 SP - 1928 EP - 1934 DO - 10.5591/978-1-57735-516-8/IJCAI11-323 UR - https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-323 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
