KAFQN: Kolmogorov-Arnold Fuzzy-guided Q-Network in Reinforcement Learning

Bo Zhao, Zhizhong Liu, Zhuo TangICASSP 2025 · OpenReview

Abstract

Conventional deep reinforcement learning approaches frequently struggle with large-scale parameter complexity and insufficient interpretability, particularly in safety-critical control signal processing tasks that demand transparency. While deep neural networks are highly effective, they typically function as "black-box" models, hindering insight into decision-making processes and requiring substantial computational resources, thus restricting their use in signal processing for resource-constrained environments. To address these challenges, we propose the Kolmogorov-Arnold Fuzzy-guided Q-Network, a novel framework that integrates the interpretability of fuzzy logic with the nonlinear approximation capabilities of Kolmogorov-Arnold Networks within a Deep Double Q-Network. Our approach leverages fuzzy rules during the initial training phase to accelerate convergence, improve stability, and reduce model complexity. Experimental results on dynamic control signal tasks, such as CartPole-v1, demonstrate that KAFQN achieves superior performance, a higher proposed Reward-Efficiency Index, and enhanced interpretability, making it highly appropriate for resource-constrained applications.
BibTeX
@inproceedings{zhao2025kafqn,
  author = {Bo Zhao and Zhizhong Liu and Zhuo Tang},
  title = {{KAFQN: Kolmogorov-Arnold Fuzzy-guided Q-Network in Reinforcement Learning}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2025},
  url = {https://openreview.net/forum?id=h1DzsxiiHo},
}

Loading related content...

Figure