Region-Based Approximations for Planning in Stochastic Domains
Artificial Intelligence
2013-02-08 v1
Abstract
This paper is concerned with planning in stochastic domains by means of partially observable Markov decision processes (POMDPs). POMDPs are difficult to solve. This paper identifies a subclass of POMDPs called region observable POMDPs, which are easier to solve and can be used to approximate general POMDPs to arbitrary accuracy.
Cite
@article{arxiv.1302.1573,
title = {Region-Based Approximations for Planning in Stochastic Domains},
author = {Nevin Lianwen Zhang and Wenju Liu},
journal= {arXiv preprint arXiv:1302.1573},
year = {2013}
}
Comments
Appears in Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence (UAI1997)