Kolmogorov-Arnold Network for Online Reinforcement Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914931282018304 |
|---|---|
| author | Kich, Victor Augusto Bottega, Jair Augusto Steinmetz, Raul Grando, Ricardo Bedin Yorozu, Ayano Ohya, Akihisa |
| author_facet | Kich, Victor Augusto Bottega, Jair Augusto Steinmetz, Raul Grando, Ricardo Bedin Yorozu, Ayano Ohya, Akihisa |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04841 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Kolmogorov-Arnold Network for Online Reinforcement Learning Kich, Victor Augusto Bottega, Jair Augusto Steinmetz, Raul Grando, Ricardo Bedin Yorozu, Ayano Ohya, Akihisa Machine Learning Artificial Intelligence 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. |
| title | Kolmogorov-Arnold Network for Online Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2408.04841 |