柯尔莫哥洛夫-阿诺德网络的样本效率
Sample-Efficiency of Kolmogorov-Arnold Networks
- ETH Zürich（苏黎世联邦理工学院）
- Agentic Systems Lab (ASL)（代理系统实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究通过实验对比柯尔莫哥洛夫-阿诺德网络与多层感知机，发现前者在费曼数据集和Gymnasium基准上可减少40%样本量达到相似性能，训练中相对性能提升最高50%，对奖励噪声鲁棒，凸显其样本效率优势。
AI中文摘要：
深度强化学习相比经典控制方法已取得显著性能提升，但现实应用中学习的核心挑战是获取成本高昂的样本。柯尔莫哥洛夫-阿诺德网络（Kolmogorov-Arnold Networks）是近期提出的架构，能有效学习控制问题中的物理关系，相比多层感知机（Multi-Layer-Perceptron）架构具有显著更高的参数效率和可解释性。本研究通过计算实验系统研究样本效率，涵盖费曼数据集（Feynman dataset）和Gymnasium强化学习基准。结果显示，使用柯尔莫哥洛夫-阿诺德架构可减少40%的样本量达到相似性能，训练过程中相对性能提升最高达50%，且观测到的增益对奖励的不同噪声水平具有鲁棒性。这些结果凸显柯尔莫哥洛夫-阿诺德架构在实现更具样本效率的强化学习方面的潜力。代码：this https URL
英文摘要：
Deep reinforcement learning has achieved substantial performance gains over classical control approaches. Yet, a central challenge to learning in real-world applications is acquiring costly samples. Kolmogorov-Arnold Networks are a recently proposed architecture that can learn physical relationships in control problems effectively, with significantly higher parameter efficiency and interpretability when compared to Multi-Layer-Perceptron architectures. In this work, we systematically study sample-efficiency using computational experiments, covering the Feynman dataset and the Gymnasium RL benchmark. The results show that similar performance can be achieved with 40% fewer samples using the Kolmogorov-Arnold architecture, and that relative performance improvements up to 50% occur during the training process. The observed gains are robust to varying levels of noise in rewards. These results highlight the potential of the Kolmogorov-Arnold architectures for more sample-efficient reinforcement learning. Code: https://github.com/DerKevinRiehl/neurips26_kan_training
