Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.22794 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913171809239040 |
|---|---|
| author | Nilsen, Marcus Binder Quick, Julian Göçmen, Tuhfe Dimitrov, Nikolay Réthoré, Pierre-Elouan |
| author_facet | Nilsen, Marcus Binder Quick, Julian Göçmen, Tuhfe Dimitrov, Nikolay Réthoré, Pierre-Elouan |
| contents | Reinforcement learning (RL) offers a promising approach for adaptive wind farm flow control, yet its practical deployment is hindered by slow training convergence and poor initial performance, factors that could translate to years of reduced power output if an untrained agent were deployed directly. This work investigates whether domain knowledge from steady-state wake models can accelerate RL training and improve initial controller performance. We propose a pretraining methodology in which expert demonstrations are generated by deploying a PyWake-based steady-state optimizer within a dynamic wake simulation (WindGym), then used to initialize both the actor and critic networks of a Soft Actor-Critic agent via behavior cloning. Experiments on a 2x2 wind farm show that pretraining eliminates the costly initial learning phase: while an untrained agent underperforms the greedy zero-yaw baseline by approximately 12%, pretraining raises initial performance to near-baseline levels. During online fine-tuning, all configurations converge within 250,000 environment steps to achieve similar performance, ultimately exceeding that of a lookup-table controller, which reaches approximately 7% power gain after 500,000 steps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22794 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Accelerating Reinforcement Learning for Wind Farm Control via Expert Demonstrations Nilsen, Marcus Binder Quick, Julian Göçmen, Tuhfe Dimitrov, Nikolay Réthoré, Pierre-Elouan Systems and Control Machine Learning Reinforcement learning (RL) offers a promising approach for adaptive wind farm flow control, yet its practical deployment is hindered by slow training convergence and poor initial performance, factors that could translate to years of reduced power output if an untrained agent were deployed directly. This work investigates whether domain knowledge from steady-state wake models can accelerate RL training and improve initial controller performance. We propose a pretraining methodology in which expert demonstrations are generated by deploying a PyWake-based steady-state optimizer within a dynamic wake simulation (WindGym), then used to initialize both the actor and critic networks of a Soft Actor-Critic agent via behavior cloning. Experiments on a 2x2 wind farm show that pretraining eliminates the costly initial learning phase: while an untrained agent underperforms the greedy zero-yaw baseline by approximately 12%, pretraining raises initial performance to near-baseline levels. During online fine-tuning, all configurations converge within 250,000 environment steps to achieve similar performance, ultimately exceeding that of a lookup-table controller, which reaches approximately 7% power gain after 500,000 steps. |
| title | Accelerating Reinforcement Learning for Wind Farm Control via Expert Demonstrations |
| topic | Systems and Control Machine Learning |
| url | https://arxiv.org/abs/2604.22794 |