Projects per year
For effective decision support in scenarios with conflicting objectives, sets of potentially optimal solutions can be presented to the decision maker. We explore both what policies these sets should contain and how such sets can be computed efficiently. With this in mind, we take a distributional approach and introduce a novel dominance criterion relating return distributions of policies directly. Based on this criterion, we present the distributional undominated set and show that it contains optimal policies otherwise ignored by the Pareto front. In addition, we propose the convex distributional undominated set and prove that it comprises all policies that maximise expected utility for multivariate risk-averse decision makers. We propose a novel algorithm to learn the distributional undominated set and further contribute pruning operators to reduce the set to the convex distributional undominated set. Through experiments, we demonstrate the feasibility and effectiveness of these methods, making this a valuable new approach for decision support in real-world problems.
|Title of host publication||Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence|
|Subtitle of host publication||Main Track|
|Publisher||International Joint Conferences on Artificial Intelligence|
|Number of pages||9|
|Publication status||Published - 2023|
FingerprintDive into the research topics of 'Distributional multi-objective decision making'. Together they form a unique fingerprint.
- 1 Finished
1/11/21 → 31/10/23
- 1 Research and Teaching at External Organisation