English

Qualitative MDPs and POMDPs: An Order-Of-Magnitude Approximation

Artificial Intelligence 2013-01-07 v1

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 epsilon-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.

Keywords

Cite

@article{arxiv.1301.0557,
  title  = {Qualitative MDPs and POMDPs: An Order-Of-Magnitude Approximation},
  author = {Blai Bonet and Judea Pearl},
  journal= {arXiv preprint arXiv:1301.0557},
  year   = {2013}
}

Comments

Appears in Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI2002)