Kolmogorov-Arnold Network for Online Reinforcement Learning
This work addresses efficiency for reinforcement learning practitioners, but it is incremental as it applies an existing network type to a new domain.
The paper tackled the problem of improving efficiency in reinforcement learning by using Kolmogorov-Arnold Networks (KANs) as function approximators in Proximal Policy Optimization (PPO), achieving comparable performance to MLP-based PPO with fewer parameters on the DeepMind Control Proprio Robotics benchmark.
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.