Evolutionary Warm-Starts for Reinforcement Learning in Industrial Continuous Control

Tom Maus, Stephan Frank, Tobias Glasmachers
3/23/2026
cs.NEcs.LG

No official code found. Best implementation: Storm-131/EvoRL (0 stars, last commit 2026-04-20).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

Storm-131/EvoRLCommunity72%

Evolutionary Warm-Starts for Reinforcement Learning in Industrial Continuous Control

00PythonMar 23, 20266 months ago

Similar Papers

A Benchmark Environment Motivated by Industrial Control Problems

84% match1 repo1512017

Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning Environments

83% match2025

Balancing Specialization and Centralization: A Multi-Agent Reinforcement Learning Benchmark for Sequential Industrial Control

83% match2025

A Decade of Learning-Based Control: From Theoretic Foundations to Practical Deployment

83% match2026

Evolution-Guided Policy Gradient in Reinforcement Learning

83% match1 repo2532018

A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management

83% match1 repo492023

Cite this paper

@article{maus2026evolutionary,
  title  = {Evolutionary Warm-Starts for Reinforcement Learning in Industrial Continuous Control},
  author = {Tom Maus and Stephan Frank and Tobias Glasmachers},
  year   = {2026},
  eprint = {2603.26750},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.26750v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.26750.svg)](https://codeofpaper.com/paper/2603.26750)

Discussion