Accelerating Reinforcement Learning for Wind Farm Control via Expert Demonstrations
Abstract
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.
Cite
@article{arxiv.2604.22794,
title = {Accelerating Reinforcement Learning for Wind Farm Control via Expert Demonstrations},
author = {Marcus Binder Nilsen and Julian Quick and Tuhfe Göçmen and Nikolay Dimitrov and Pierre-Elouan Réthoré},
journal= {arXiv preprint arXiv:2604.22794},
year = {2026}
}
Comments
Submitted to Journal of Physics: Conference Series (Torque 2026). This is the Accepted Manuscript version of an article accepted for publication in Journal of Physics: Conference Series. IOP Publishing Ltd is not responsible for any errors or omissions in this version of the manuscript or any version derived from it. This Accepted Manuscript is published under a CC BY licence