Willem Röpke, Conor F. Hayes, Patrick Mannion, Enda Howley, Ann Nowe, Diederik M. Roijers
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.
Röpke, W, Hayes, CF, Mannion, P, Howley, E, Nowe, A & Roijers, DM 2023, Distributional multi-objective decision making. in Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence: Main Track. International Joint Conferences on Artificial Intelligence, pp. 5711–5719, 32nd International Joint Conference on Artificial Intelligence, Macao, China, 19/08/23. https://doi.org/10.24963/ijcai.2023/634
Röpke, W., Hayes, C. F., Mannion, P., Howley, E., Nowe, A., & Roijers, D. M. (2023). Distributional multi-objective decision making. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence: Main Track (pp. 5711–5719). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2023/634
@inproceedings{6b0f4056a87c4521b1bdb94eb5b6eab7,
title = "Distributional multi-objective decision making",
abstract = "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.",
author = "Willem R{\"o}pke and Hayes, {Conor F.} and Patrick Mannion and Enda Howley and Ann Nowe and Roijers, {Diederik M.}",
note = "Funding Information: WR is supported by the Research Foundation – Flanders (FWO), grant numbers 1197622N. CH is funded by the University of Galway Hardiman Scholarship. This research was supported by funding from the Flemish Government under the “Onderzoeksprogramma Artifici{\"e}le Intelligentie (AI) Vlaanderen” program. Publisher Copyright: {\textcopyright} 2023 International Joint Conferences on Artificial Intelligence. All rights reserved.; 32nd International Joint Conference on Artificial Intelligence ; Conference date: 19-08-2023 Through 25-08-2023",
year = "2023",
doi = "10.24963/ijcai.2023/634",
language = "English",
pages = "5711–5719",
booktitle = "Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence",
publisher = "International Joint Conferences on Artificial Intelligence",
url = "https://ijcai-23.org/",
}