Qualitative MDPs and POMDPs: An Order-of-Magnitude Approximation
Abstract
We develop a qualitative theory of Markov Decision Processes (MDPS) and Partially Observable MDPS that can be used to model sequential decision making tasks when only qualitative information is available. Our approach is based upon an order-of-magnitude approximation of both probabilities and utilities, similar to e-semantics. The result is a qualitative theory that has close ties with the standard maximum-expected-utility theory and is amenable to general planning techniques.
Cite
Text
Bonet and Pearl. "Qualitative MDPs and POMDPs: An Order-of-Magnitude Approximation." Conference on Uncertainty in Artificial Intelligence, 2002.Markdown
[Bonet and Pearl. "Qualitative MDPs and POMDPs: An Order-of-Magnitude Approximation." Conference on Uncertainty in Artificial Intelligence, 2002.](https://mlanthology.org/uai/2002/bonet2002uai-qualitative/)BibTeX
@inproceedings{bonet2002uai-qualitative,
title = {{Qualitative MDPs and POMDPs: An Order-of-Magnitude Approximation}},
author = {Bonet, Blai and Pearl, Judea},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2002},
pages = {61-68},
url = {https://mlanthology.org/uai/2002/bonet2002uai-qualitative/}
}