HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916709570445312 |
|---|---|
| author | Gornet, Jonathan Kantaros, Yiannis Sinopoli, Bruno |
| author_facet | Gornet, Jonathan Kantaros, Yiannis Sinopoli, Bruno |
| contents | We introduce Hyperparameter Controller (HyperController), a computationally efficient algorithm for hyperparameter optimization during training of reinforcement learning neural networks. HyperController optimizes hyperparameters quickly while also maintaining improvement of the reinforcement learning neural network, resulting in faster training and deployment. It achieves this by modeling the hyperparameter optimization problem as an unknown Linear Gaussian Dynamical System, which is a system with a state that linearly changes. It then learns an efficient representation of the hyperparameter objective function using the Kalman filter, which is the optimal one-step predictor for a Linear Gaussian Dynamical System. To demonstrate the performance of HyperController, it is applied as a hyperparameter optimizer during training of reinforcement learning neural networks on a variety of OpenAI Gymnasium environments. In four out of the five Gymnasium environments, HyperController achieves highest median reward during evaluation compared to other algorithms. The results exhibit the potential of HyperController for efficient and stable training of reinforcement learning neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19382 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks Gornet, Jonathan Kantaros, Yiannis Sinopoli, Bruno Machine Learning Systems and Control We introduce Hyperparameter Controller (HyperController), a computationally efficient algorithm for hyperparameter optimization during training of reinforcement learning neural networks. HyperController optimizes hyperparameters quickly while also maintaining improvement of the reinforcement learning neural network, resulting in faster training and deployment. It achieves this by modeling the hyperparameter optimization problem as an unknown Linear Gaussian Dynamical System, which is a system with a state that linearly changes. It then learns an efficient representation of the hyperparameter objective function using the Kalman filter, which is the optimal one-step predictor for a Linear Gaussian Dynamical System. To demonstrate the performance of HyperController, it is applied as a hyperparameter optimizer during training of reinforcement learning neural networks on a variety of OpenAI Gymnasium environments. In four out of the five Gymnasium environments, HyperController achieves highest median reward during evaluation compared to other algorithms. The results exhibit the potential of HyperController for efficient and stable training of reinforcement learning neural networks. |
| title | HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2504.19382 |