{"slug": "sample-efficiency-of-kolmogorov-arnold-networks", "title": "Sample-Efficiency of Kolmogorov-Arnold Networks", "summary": "A systematic study of Kolmogorov-Arnold Networks (KANs) found that the architecture can match Multi-Layer-Perceptron performance in reinforcement learning with 40% fewer samples, with relative performance improvements up to 50% during training, according to arXiv paper 2610.10627v1. The computational experiments covered the Feynman dataset and the Gymnasium RL benchmark, and the gains held across varying levels of reward noise. Code for the work is available at github.com/DerKevinRiehl/neurips26_kan_training.", "body_md": "arXiv:2610.10627v1 Announce Type: new \nAbstract: 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", "url": "https://wpnews.pro/news/sample-efficiency-of-kolmogorov-arnold-networks", "canonical_source": "https://arxiv.org/abs/2610.10627", "published_at": "2026-10-09 04:00:00+00:00", "updated_at": "2026-10-09 04:19:10.945487+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-research", "artificial-intelligence"], "entities": ["Kolmogorov-Arnold Networks", "Multi-Layer-Perceptron", "Feynman dataset", "Gymnasium", "arXiv", "Kevin Riehl"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/sample-efficiency-of-kolmogorov-arnold-networks", "markdown": "https://wpnews.pro/news/sample-efficiency-of-kolmogorov-arnold-networks.md", "text": "https://wpnews.pro/news/sample-efficiency-of-kolmogorov-arnold-networks.txt", "jsonld": "https://wpnews.pro/news/sample-efficiency-of-kolmogorov-arnold-networks.jsonld"}}