Qualitative MDPs and POMDPs: an order-of-magnitude approximation

Authors:
Blai Bonet;Judea Pearl
Affiliations:
Cognitive Systems Laboratory, Department of Computer Science, University of California, Los Angeles, Los Angeles, CA;Cognitive Systems Laboratory, Department of Computer Science, University of California, Los Angeles, Los Angeles, CA
Venue:
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
Year:
2002

Citing 17
Cited 5

Acting optimally in partially observable stochastic domains

AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
From Adams' conditionals to default expressions, causal conditionals, and counterfactuals

Probability and conditionals
Dynamic Programming and Optimal Control, Two Volume Set

Dynamic Programming and Optimal Control, Two Volume Set
Default Reasoning: Causal and Conditional Theories

Default Reasoning: Causal and Conditional Theories
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
A general non-probabilistic theory of inductive reasoning

UAI '88 Proceedings of the Fourth Annual Conference on Uncertainty in Artificial Intelligence
A Qualitative Linear Utility Theory for Spohn's Theory of Epistemic Beliefs

UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
Value-function approximations for partially observable Markov decision processes

Journal of Artificial Intelligence Research
Conformant planning via symbolic model checking

Journal of Artificial Intelligence Research
Heuristic search + symbolic model checking = efficient conformant planning

IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
Possibility theory as a basis for qualitative decision theory

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Planning and acting in partially observable stochastic domains

Artificial Intelligence
Pushing the envelope: planning, propositional logic, and stochastic search

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
System-Z+: a formalism for reasoning with variable-strength defaults

AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 1
Planning with deadlines in stochastic domains

AAAI'93 Proceedings of the eleventh national conference on Artificial intelligence
A possibilistic model for qualitative sequential decision problems under uncertainty in partially observable environments

UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
An order of magnitude calculus

UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence

Qualitative decision under uncertainty: back to expected utility

Artificial Intelligence
Qualitative reinforcement learning

ICML '06 Proceedings of the 23rd international conference on Machine learning
Algebraic Markov decision processes

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Qualitative decision under uncertainty: back to expected utility

Artificial Intelligence
Graphical models for imprecise probabilities

International Journal of Approximate Reasoning

Quantified Score

Hi-index	0.00

Visualization

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 ε-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.