4 papers · 1 filter
Balancing Specialization and Centralization: A Multi-Agent Reinforcement Learning Benchmark for Sequential Industrial Control
Tom Maus, Asma Atamna, Tobias Glasmachers
Autonomous control of multi-stage industrial processes requires both local specialization and global coordination. Reinforcement learning (RL) offers a promising approach, but its…
Cumulative Learning Rate Adaptation: Revisiting Path-Based Schedules for SGD and Adam
Asma Atamna, Tom Maus, Fabian Kievelitz +1
The learning rate is a crucial hyperparameter in deep learning, with its ideal value depending on the problem and potentially changing during training. In this paper, we investigat…
Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning Environments
Tom Maus, Asma Atamna, Tobias Glasmachers
Reinforcement Learning (RL) has demonstrated significant potential in certain real-world industrial applications, yet its broader deployment remains limited by inherent challenges…
SortingEnv: An Extendable RL-Environment for an Industrial Sorting Process
Tom Maus, Nico Zengeler, Tobias Glasmachers
We present a novel reinforcement learning (RL) environment designed to both optimize industrial sorting systems and study agent behavior in evolving spaces. In simulating material…