Publication
The Challenges of Using Reinforcement Learning for Controlling Industrial Energy Systems
Tobias Lademann; Théo Vincent; Jan Peters; Matthias Weigold
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2605.31044, Pages 1-11, arXiv, 2026.
Abstract
Reinforcement learning has shown promising results for optimizing the control of in-
dustrial energy systems, yet most existing studies remain limited to the application in
simulation environments. We investigate the challenges of deploying reinforcement
learning in a real-world industrial energy system, considering a thermal heating net-
work as a use case. We formulate the task as a Markov Decision Process and system-
atically analyze the associated challenges along the structure of the formal description,
including partial observability, action space design, reward design, and the simulation-
to-reality gap. The challenges are grounded in an existing real-world deployment,
where reinforcement learning achieves operational stability but shows a significant per-
formance gap compared to simulation.