Hierarchize Pareto Dominance in Multi-Objective Stochastic Linear Bandits

Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2024

This paper studies bandit algorithms under mixed Pareto-lexicographic orders, which can reflect decision makers’ preferences in multi-objective stochastic linear bandits.

Recommended citation: Cheng, J., Xue, B., Yi, J., & Zhang, Q. (2024). Hierarchize Pareto Dominance in Multi-Objective Stochastic Linear Bandits. Proceedings of the AAAI Conference on Artificial Intelligence, 38, 11489-11497.
Download Paper | Download Bibtex