Strategy Selection in Influence Diagrams using Imprecise Probabilities
This work addresses decision-making under uncertainty for domains like military planning, but it appears incremental as it builds on existing credal network algorithms.
The paper tackles decision-making in Influence Diagrams by introducing a new algorithm that uses imprecise probabilities to find global maximum strategies, with experiments on random diagrams and a military planning problem.
This paper describes a new algorithm to solve the decision making problem in Influence Diagrams based on algorithms for credal networks. Decision nodes are associated to imprecise probability distributions and a reformulation is introduced that finds the global maximum strategy with respect to the expected utility. We work with Limited Memory Influence Diagrams, which generalize most Influence Diagram proposals and handle simultaneous decisions. Besides the global optimum method, we explore an anytime approximate solution with a guaranteed maximum error and show that imprecise probabilities are handled in a straightforward way. Complexity issues and experiments with random diagrams and an effects-based military planning problem are discussed.