Evolutionary Warm-Starts for Reinforcement Learning in Industrial Continuous Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911548820160512 |
|---|---|
| author | Maus, Tom Frank, Stephan Glasmachers, Tobias |
| author_facet | Maus, Tom Frank, Stephan Glasmachers, Tobias |
| contents | Reinforcement learning (RL) is still rarely applied in industrial control, partly due to the difficulty of training reliable agents for real-world conditions. This work investigates how evolution strategies can support RL in such settings by introducing a continuous-control adaptation of an industrial sorting benchmark. The CMA-ES algorithm is used to generate high-quality demonstrations that warm-start RL agents. Results show that CMA-ES-guided initialization significantly improves stability and performance. Furthermore, the demonstration trajectories generated with the CMA-ES provide a strong oracle reference performance level, which is of interest in its own right. The study delivers a focused proof of concept for hybrid evolutionary-RL approaches and a basis for future, more complex industrial applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_26750 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evolutionary Warm-Starts for Reinforcement Learning in Industrial Continuous Control Maus, Tom Frank, Stephan Glasmachers, Tobias Neural and Evolutionary Computing Machine Learning Reinforcement learning (RL) is still rarely applied in industrial control, partly due to the difficulty of training reliable agents for real-world conditions. This work investigates how evolution strategies can support RL in such settings by introducing a continuous-control adaptation of an industrial sorting benchmark. The CMA-ES algorithm is used to generate high-quality demonstrations that warm-start RL agents. Results show that CMA-ES-guided initialization significantly improves stability and performance. Furthermore, the demonstration trajectories generated with the CMA-ES provide a strong oracle reference performance level, which is of interest in its own right. The study delivers a focused proof of concept for hybrid evolutionary-RL approaches and a basis for future, more complex industrial applications. |
| title | Evolutionary Warm-Starts for Reinforcement Learning in Industrial Continuous Control |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2603.26750 |