Model-Free Robust Average-Reward Reinforcement Learning
Abstract
Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs. In this paper, we focus on the robust average-reward MDPs under the model-free setting. We first theoretically characterize the structure of solutions to the robust average-reward Bellman equation, which is essential for our later convergence analysis. We then design two model-free algorithms, robust relative value iteration (RVI) TD and robust RVI Q-learning, and theoretically prove their convergence to the optimal solution. We provide several widely used uncertainty sets as examples, including those defined by the contamination model, total variation, Chi-squared divergence, Kullback-Leibler (KL) divergence and Wasserstein distance.
Cite
@article{arxiv.2305.10504,
title = {Model-Free Robust Average-Reward Reinforcement Learning},
author = {Yue Wang and Alvaro Velasquez and George Atia and Ashley Prater-Bennette and Shaofeng Zou},
journal= {arXiv preprint arXiv:2305.10504},
year = {2023}
}
Comments
ICML 2023