Pessimistic Off-Policy Multi-Objective Optimization
Abstract
Multi-objective optimization is a class of optimization problems with multiple conflicting objectives. We study offline optimization of multi-objective policies from data collected by a previously deployed policy. We propose a pessimistic estimator for policy values that can be easily plugged into existing formulas for hypervolume computation and optimized. The estimator is based on inverse propensity scores (IPS), and improves upon a naive IPS estimator in both theory and experiments. Our analysis is general, and applies beyond our IPS estimators and methods for optimizing them.
Cite
Text
Alizadeh et al. "Pessimistic Off-Policy Multi-Objective Optimization." Artificial Intelligence and Statistics, 2024.Markdown
[Alizadeh et al. "Pessimistic Off-Policy Multi-Objective Optimization." Artificial Intelligence and Statistics, 2024.](https://mlanthology.org/aistats/2024/alizadeh2024aistats-pessimistic/)BibTeX
@inproceedings{alizadeh2024aistats-pessimistic,
title = {{Pessimistic Off-Policy Multi-Objective Optimization}},
author = {Alizadeh, Shima and Bhargava, Aniruddha and Gopalswamy, Karthick and Jain, Lalit and Kveton, Branislav and Liu, Ge},
booktitle = {Artificial Intelligence and Statistics},
year = {2024},
pages = {2980-2988},
volume = {238},
url = {https://mlanthology.org/aistats/2024/alizadeh2024aistats-pessimistic/}
}