11 papers
Safe Reinforcement Learning using Ideas from Model Predictive Control
Georg Schäfer, Jakob Rehrl, Stefan Huber +1
Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics. A persi…
Sample-Efficient Pareto Front Modeling for Energy-Aware Reinforcement Learning Using Bayesian Optimization
Georg Schäfer, Jakob Rehrl, Stefan Huber +1
Industrial automation increasingly demands control strategies that balance operational performance with strict energy efficiency requirements. A common approach to solving this mul…
Anticipatory Reinforcement Learning for Trajectory Tracking
Georg Schäfer, Jakob Rehrl, Stefan Huber +1
Deep reinforcement learning (DRL) in industrial control often suffers from lag and overshoot due to purely reactive control based on the current tracking error. To achieve anticipa…
Integrating Physics-Informed Neural Networks for Safe Reinforcement Learning in a 1-DoF Helicopter System
Georg Schäfer, Jakob Rehrl, Stefan Huber
Deep reinforcement learning (DRL) offers powerful control for industrial cyber-physical systems (ICPSs), but its "black-box" exploration risks violating strict hardware safety limi…
Reinforcement Learning for Optimal Experiment Design in Parameter Identification of Mechatronic Systems
Julian Langschwert, Georg Schaefer, Jakob Rehrl +2
Informative excitation signals are critical for accurate system identification of mechatronic systems, yet classical system identification (SI) approaches require expert knowledge…
Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process
Elias Reich, Saverio Messineo, Stefan Huber
Discrete automated processes in industrial and cyber-physical systems often exhibit a repetitive structure in which successive repetitions follow a common trajectory while differin…
Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks
Stefan Huber, Hannes Unger, Georg Schäfer +1
We analytically solve the Mountain Car problem, a canonical benchmark in RL, and derive an optimal control solution, closing a gap after 36 years. This enables us to reveal two sur…
Multi-Objective Reinforcement Learning for Energy-Efficient Industrial Control
Georg Schäfer, Raphael Seliger, Jakob Rehrl +2
Industrial automation increasingly demands energy-efficient control strategies to balance performance with environmental and cost constraints. In this work, we present a multi-obje…
The Crucial Role of Problem Formulation in Real-World Reinforcement Learning
Georg Schäfer, Tatjana Krau, Jakob Rehrl +2
Reinforcement Learning (RL) offers promising solutions for control tasks in industrial cyber-physical systems (ICPSs), yet its real-world adoption remains limited. This paper demon…
Comparison of Model Predictive Control and Proximal Policy Optimization for a 1-DOF Helicopter System
Georg Schäfer, Jakob Rehrl, Stefan Huber +1
This study conducts a comparative analysis of Model Predictive Control (MPC) and Proximal Policy Optimization (PPO), a Deep Reinforcement Learning (DRL) algorithm, applied to a 1-D…
Python-Based Reinforcement Learning on Simulink Models
Georg Schäfer, Max Schirl, Jakob Rehrl +2
This paper proposes a framework for training Reinforcement Learning agents using Python in conjunction with Simulink models. Leveraging Python's superior customization options and…