Practical Guidelines to Train Reinforcement Learning Based Control of Electrical Drives

Conference: PCIM Conference 2025 - International Exhibition and Conference for Power Electronics, Intelligent Motion, Renewable Energy and Energy Management
05/06/2025 - 05/08/2025 at Nürnberg, Germany

doi:10.30420/566541245

Proceedings: PCIM Conference 2025

Pages: Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Szecsenyi, Nandor; Stumpf, Peter

Abstract:
With the recent advancements made in Artificial Intelligence, it is possible that Reinforcement Learning based data driven methods can become a next generation technology to control electrical drives instead of the classical model-based techniques. However, providing the correct setup and hyperparameters for training the agent is usually not evident, so the paper aims to lay some practical guidelines on how to properly set the environmental parameters during training. These recommendations are backed up by a detailed comparison where the effect on the performance of each environmental aspect is evaluated.