2025-09-13 –, C120 - Art. 15 GDPR
Language: English
Machine learning in safety critical systems can be... ~a very dumb idea~ a challenge. In this talk I want to introduce a recent framework for a robust safety system for reinforcement learning in safety critical systems based on Model Predictive Control.
In short: How to train a system without blowing up the building in the process
Model Predictive Control is a recent compute heavy control strategy for autonomous systems. I want to explore its applications to reinforcement learning. A mathematical model of both the enviroment and the system-in-training acts as a supervisor during the training and provides mathematical guarantees for certain bahviour boundaries. To provide some insights I will present my own experiments from my bachelor thesis as well as the research done at University of Lübeck on the topic. If I have time I will try to demonstrate a simple version of the architecture.
Young being interested in all things robotic, digital or political. Avid enjoyer of caffeine and passionate despiser of generative AI. Talk to me about political theory or your infodump of the day.
Feel free to talk to me but be warned, the quality of jokes rapidly deteriorates through the evening
Any pronouns are fine.