Expected Utility Networks
This foundational work addresses the integration of probability and utility modeling for AI and economic theory, offering a novel framework for decision-making under uncertainty.
The paper introduces expected utility networks (EUNs), a new graphical representation that modularly models both probabilities and utilities, and shows that node separation in these networks implies conditional expected utility independence, enabling strategic inference for alternative action plans.
We introduce a new class of graphical representations, expected utility networks (EUNs), and discuss some of its properties and potential applications to artificial intelligence and economic theory. In EUNs not only probabilities, but also utilities enjoy a modular representation. EUNs are undirected graphs with two types of arc, representing probability and utility dependencies respectively. The representation of utilities is based on a novel notion of conditional utility independence, which we introduce and discuss in the context of other existing proposals. Just as probabilistic inference involves the computation of conditional probabilities, strategic inference involves the computation of conditional expected utilities for alternative plans of action. We define a new notion of conditional expected utility (EU) independence, and show that in EUNs node separation with respect to the probability and utility subgraphs implies conditional EU independence.