Skip to yearly menu bar Skip to main content


Poster

The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm

Giseung Park · woohyeon Byeon · Seongmin Kim · Elad Havakuk · Amir Leshem · Youngchul Sung

Hall C 4-9 #1106

Abstract:

In this paper, we consider multi-objective reinforcement learning, which arises in many real-world problems with multiple optimization goals. We approach the problem with a max-min framework focusing on fairness among the multiple goals and develop a relevant theory and a practical model-free algorithm under the max-min framework. The developed theory provides a theoretical advance in multi-objective reinforcement learning, and the proposed algorithm demonstrates a notable performance improvement over existing baseline methods.

Chat is not available.