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

Research output: Contribution to journalConference articlepeer-review


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 (

Original languageEnglish (US)
Pages (from-to)2677-2703
Number of pages27
JournalProceedings of Machine Learning Research
StatePublished - 2023
Event26th International Conference on Artificial Intelligence and Statistics, AISTATS 2023 - Valencia, Spain
Duration: Apr 25 2023Apr 27 2023

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


Dive into the research topics of 'Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables'. Together they form a unique fingerprint.

Cite this