用可解释的KAN网络提升负载均衡的决策透明度。
Interpretable Reinforcement Learning for Load Balancing using Kolmogorov-Arnold Networks
- 用单层KAN作为策略网络，结合PPO算法优化负载均衡
- 在多种奖励函数下提升吞吐量并降低丢包与延迟
- 能提取出可读的控制公式，适合需要透明决策的场景
强化学习（RL）在网路控制问题中应用日益广泛，如负载均衡。然而现有方法常缺乏可解释性，难以提取控制器方程。本文提出使用柯尔莫哥洛夫-阿诺德网络（KAN）实现可解释的强化学习。我们采用带有单层策略KAN模型和MLP价值网络的PPO代理，学习最大化吞吐量效用、最小化丢包与延迟的负载均衡策略。该方法可从训练后的神经网络中提取出控制器方程，揭示决策过程。通过不同奖励函数的评估，验证了其在提升网络性能的同时提供可解释策略的有效性。
原文摘要 · Abstract (English)
Reinforcement learning (RL) has been increasingly applied to network control problems, such as load balancing. However, existing RL approaches often suffer from lack of interpretability and difficulty in extracting controller equations. In this paper, we propose the use of Kolmogorov-Arnold Networks (KAN) for interpretable RL in network control. We employ a PPO agent with a 1-layer actor KAN model and an MLP Critic network to learn load balancing policies that maximise throughput utility, minimize loss as well as delay. Our approach allows us to extract controller equations from the learned neural networks, providing insights into the decision-making process. We evaluate our approach using different reward functions demonstrating its effectiveness in improving network performance while providing interpretable policies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。