Policy-regularized Offline Multi-objective Reinforcement Learning

In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach for single-objective offline RL problems, into the multi-objective setting in order to achieve the above goal. However, such methods face a new challenge in offline MORL settings, namely the preference-inconsistent demonstration problem. We propose two solutions to this problem: 1) filtering out preference-inconsistent demonstrations via approximating behavior preferences, and 2) adopting regularization techniques with high policy expressiveness. Moreover, we integrate the preferenceconditioned scalarized update method into policy-regularized offline RL, in order to simultaneously learn a set of policies using a single policy network, thus reducing the computational costs induced by the training of a large number of individual policies for various preferences. Finally, we introduce Regularization Weight Adaptation to dynamically determine appropriate regularization weights for arbitrary target preferences during deployment. Empirical results on various multi-objective datasets demonstrate the capability of our approach in solving offline MORL problems. 1

Authors

• Qian Lin Sun Yat-sen University
• Chao Yu Sun Yat-sen University & Pengcheng Laboratory
• Zongkai Liu Sun Yat-sen University Shanghai Innovation Institute
• Zifan Wu Sun Yat-sen University

Keywords

• Offline RL
• Multi-objective RL
• Policy regularization