Ordered Preference Elicitation Strategies for Supporting Multi-Objective Decision Making
This work addresses a gap in multi-objective decision support for users needing to choose policies based on preferences, but it is incremental as it builds on existing Gaussian process and preference modelling methods.
The paper tackled the problem of selecting the best policy from a set of optimal solutions in multi-objective decision making by proposing new ordered preference elicitation strategies, showing that these strategies outperform existing pairwise methods and that users prefer ranking, with performance improvements demonstrated in computer and human experiments.
In multi-objective decision planning and learning, much attention is paid to producing optimal solution sets that contain an optimal policy for every possible user preference profile. We argue that the step that follows, i.e, determining which policy to execute by maximising the user's intrinsic utility function over this (possibly infinite) set, is under-studied. This paper aims to fill this gap. We build on previous work on Gaussian processes and pairwise comparisons for preference modelling, extend it to the multi-objective decision support scenario, and propose new ordered preference elicitation strategies based on ranking and clustering. Our main contribution is an in-depth evaluation of these strategies using computer and human-based experiments. We show that our proposed elicitation strategies outperform the currently used pairwise methods, and found that users prefer ranking most. Our experiments further show that utilising monotonicity information in GPs by using a linear prior mean at the start and virtual comparisons to the nadir and ideal points, increases performance. We demonstrate our decision support framework in a real-world study on traffic regulation, conducted with the city of Amsterdam.