On High-Dimensional Action Selection for Deep Reinforcement Learning

Wenbo Zhang, Hengrui Cai

Keywords: Deep Reinforcement Learning, False Discovery Control, High-Dimensional Action Space, Online Learning, Variable Selection

TL;DR: We address the high-dimensional action selection problem in online deep reinforcement learning by identifying the minimal sufficient actions with theoretical guarantees.

Abstract: With recent advances in deep reinforcement learning (RL), **high-dimensional action selection** has become an important yet challenging problem in many real applications, especially in unknown and complex environments. Existing works often require a sophisticated prior design to eliminate redundancy in the action space, relying heavily on domain expert experience or involving high computational complexity, which limits their generalizability across different RL tasks. In this paper, we address these challenges by proposing a general data-driven action selection approach with model-free and computational-friendly properties. Our method not only **selects minimal sufficient actions** but also **controls the false discovery rate** via knockoff sampling. More importantly, we seamlessly integrate the action selection into deep RL methods during online training. Empirical experiments validate the established theoretical guarantees, demonstrating that our method surpasses various alternative techniques in terms of both performances in variable selection and overall achieved rewards.

Primary Area: reinforcement learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 8971