Deterministic POMDPs Revisited
Artificial Intelligence
2012-05-14 v1
Abstract
We study a subclass of POMDPs, called Deterministic POMDPs, that is characterized by deterministic actions and observations. These models do not provide the same generality of POMDPs yet they capture a number of interesting and challenging problems, and permit more efficient algorithms. Indeed, some of the recent work in planning is built around such assumptions mainly by the quest of amenable models more expressive than the classical deterministic models. We provide results about the fundamental properties of Deterministic POMDPs, their relation with AND/OR search problems and algorithms, and their computational complexity.
Cite
@article{arxiv.1205.2659,
title = {Deterministic POMDPs Revisited},
author = {Blai Bonet},
journal= {arXiv preprint arXiv:1205.2659},
year = {2012}
}
Comments
Appears in Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI2009)