Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables

Mengdi Xu, Peide Huang, Yaru Niu, Visak Kumar, Jielin Qiu, Chao Fang, Kuan-Hui Lee, Xuewei Qi, Henry Lam, Bo Li, Ding Zhao

Keywords: Reinforcement Learning, Distributionally Robust Optimization

TL;DR: To handle task estimate uncertainties, we propose a novel group distributionally robust RL formulation and associated training algorithms that naturally model task subpopulations and balance robustness and performance.

Abstract: One key challenge for multi-task Reinforcement learning (RL) in practice is the absence of task specifications. Robust RL has been applied to deal with task ambiguity but may result in over-conservative policies. To balance the worst-case (robustness) and average performance, we propose Group Distributionally Robust Markov Decision Process (GDR-MDP), a flexible hierarchical MDP formulation that encodes task groups via a latent mixture model. GDR-MDP identifies the optimal policy that maximizes the expected return under the worst-possible qualified belief over task groups within an ambiguity set. We rigorously show that GDR-MDP's hierarchical structure improves distributional robustness by adding regularization to the worst possible outcomes. We then develop deep RL algorithms for GDR-MDP for both value-based and policy-based RL methods. Extensive experiments on Box2D control tasks, MuJoCo benchmarks, and Google football platforms show that our algorithms outperform classic robust training algorithms across diverse environments in terms of robustness under belief uncertainties. Demos are available on our project page (https://sites.google.com/view/gdr-rl/home).

Publication Venue: AISTATS 2023

Submission Number: 4