From Preference-Based to Multiobjective Sequential Decision-Making
This work provides a theoretical foundation for applying multiobjective techniques to preference-based problems, particularly when rewards are unknown, but it is incremental as it builds on existing utility and expectation frameworks.
The paper establishes a formal connection between preference-based and multiobjective sequential decision-making, showing how to transform preference-based problems into multiobjective ones under conditions of additively decomposable utilities and expectation-based policy evaluation, enabling cross-application of solving methods.
In this paper, we present a link between preference-based and multiobjective sequential decision-making. While transforming a multiobjective problem to a preference-based one is quite natural, the other direction is a bit less obvious. We present how this transformation (from preference-based to multiobjective) can be done under the classic condition that preferences over histories can be represented by additively decomposable utilities and that the decision criterion to evaluate policies in a state is based on expectation. This link yields a new source of multiobjective sequential decision-making problems (i.e., when reward values are unknown) and justifies the use of solving methods developed in one setting in the other one.