analiza aiqbench
This study demonstrates that Kolmogorov-Arnold Networks can significantly improve sample efficiency in deep reinforcement learning, achieving comparable performance with 40% fewer samples on standard benchmarks like Feynman and Gymnasium RL. The findings suggest these architectures offer a robust alternative to traditional Multi-Layer-Perceptrons for control problems where data acquisition is expensive or noisy.
Sample-Efficiency of Kolmogorov-Arnold Networks
arXiv:2610.10627v1 Announce Type: new Abstract: 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
Abstract: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: this https URL
Machine Learning (cs.LG)
arXiv:2610.10627 [cs.LG]
(or arXiv:2610.10627v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.10627 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 224 cuvinte
Subiecte conexe
Evaluation of Sampling Strategies and Physics-Informed Kolmogorov--Arnold Networks in Unbounded Domains
arXiv · 5 oct. 2026
Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline Networks
arXiv · 15 sept. 2026
Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning
arXiv · 17 aug. 2026
NObSP: Functional Decomposition of Neural Networks via Oblique Subspace Projections
arXiv · 17 sept. 2026