mlsanityData to 7 Oct 2026

Kolmogorov-Arnold Network for Online Reinforcement Learning

arXiv 2408.04841 ↗First posted 9 Aug 2024cs.LG cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Kolmogorov-Arnold Networks (KANs) have shown potential as an alternative to Multi-Layer Perceptrons (MLPs) in neural networks, providing universal function approximation with fewer parameters and reduced memory usage. In this paper, we explore the use of KANs as function approximators within the Proximal Policy Optimization (PPO) algorithm. We evaluate this approach by comparing its performance to the original MLP-based PPO using the DeepMind Control Proprio Robotics benchmark. Our results indicate that the KAN-based reinforcement learning algorithm can achieve comparable performance to its MLP-based counterpart, often with fewer parameters. These findings suggest that KANs may offer a more efficient option for reinforcement learning models.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 11 of its 23 references that are in the map. First posted on arXiv 9 Aug 2024.

Builds on

11 of 23 references.

References · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  3. 2023Mastering Diverse Domains through World Modelscited by 1,193
  4. 2018DeepMind Control Suitecited by 935
  5. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  6. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  7. 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 118
  8. 2024Kolmogorov-Arnold Networks (KANs) for Time Series Analysiscited by 97
  9. 2024TKAN: Temporal Kolmogorov-Arnold Networkscited by 70
  10. 2018PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptationcited by 14
  11. 2024Endowing Interpretability for Neural Cognitive Diagnosis by Efficient Kolmogorov-Arnold Networkscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 2.

9 papers.

  1. 2025AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learningcited by 3
  2. 2025KANITE: Kolmogorov-Arnold Networks for ITE estimationcited by 2
  3. 2025Low Tensor-Rank Adaptation of Kolmogorov--Arnold Networkscited by 1
  4. 2024On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networkscited by 0
  5. 2024Human-in-the-Loop Feature Selection Using Interpretable Kolmogorov-Arnold Network-based Double Deep Q-Networkcited by 0
  6. 2024CIKAN: Constraint Informed Kolmogorov-Arnold Networks for Autonomous Spacecraft Rendezvous using Time Shift Governorcited by 0
  7. 2025Enhancing Neural Function Approximation: The XNet Outperforming KANcited by 0
  8. 2026Kolmogorov Arnold networks (KAN) for aerodynamic prediction: a comparison with MLPs and GNNscited by 0
  9. 2026Safe Greenhouse Climate Control Using Lagrangian-Constrained PPO with Kolmogorov-Arnold Networkscited by 0