Guest Talk: Nils Jansen: Intelligent Decision-Making Under Uncertainty: Beyond Probabilities

Wednesday, January 11, 2023, 4:30pm

Location: RWTH Aachen University, Department of Computer Science - Ahornstr. 55, building E3, room 9222

Speaker: Nils Jansen

 

Abstract:

This talk highlights our vision of foundational and application-driven research toward safety in artificial intelligence (AI).
We take a broad stance on AI that combines machine learning, control theory, and formal methods, particularly formal verification.
As part of this research line, we study problems inspired by autonomous systems, planning in robotics, and direct industrial applications.

We consider reinforcement learning as a specific machine learning technique, which generally learns to behave optimally via trial and error.
Consequently, and despite its massive success in the past years, reinforcement learning lacks mechanisms to ensure safe and correct behavior.
Formal verification is a research area that provides formal guarantees of a system’s correctness and safety based on rigorous methods and precise specifications.
Yet, fundamental challenges obstruct the effective application of verification to reinforcement learning so far.
Our main objective is to devise novel, data-driven verification methods that tightly integrate with reinforcement learning. In particular, we develop techniques that address real-world challenges to the safety of AI systems in general: Scalability, expressiveness, and robustness against the uncertainty that occurs when operating in the real world. The overall goal is to advance the real-world deployment of reinforcement learning.