On High-Dimensional Action Selection for Deep Reinforcement Learning
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
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.
BibTeX
@misc{zhang2025high,
author = {Wenbo Zhang and Hengrui Cai},
title = {{On High-Dimensional Action Selection for Deep Reinforcement Learning}},
year = {2025},
url = {https://openreview.net/forum?id=rto6aU453A},
howpublished = {OpenReview},
note = {Submitted to ICLR 2025},
}