Past talk · AI/ML Seminar Series
Safe Reinforcement Learning: Building Agents You Can Trust
Postdoctoral Researcher, Department of Computer Science, University of California, Irvine
- Date & time
- Monday, May 5, 2025 · 4:00 PM
- Location
- Interdisciplinary Science & Engineering Building 1010
Abstract
Reinforcement learning is increasingly used to train robots for tasks where safety is critical, such as autonomous surgery and navigation. However, when combined with deep neural networks, these systems can become unpredictable and difficult to trust in contexts where even a single error is often unacceptable. This talk explores two complementary paths toward safer reinforcement learning: making agents more reliable through constrained training, and adding formal guarantees through techniques such as verification and shielding. In the second part of the talk, we will look at the growing role of world modeling in robotics and how this, together with the rise of large foundation models, opens up new challenges for ensuring safety in complex, real-world environments.
About the speaker
Davide Corsi is a postdoctoral researcher at the University of California, Irvine, where he works in the Intelligent Dynamics Lab led by Prof. Roy Fox. His research lies at the intersection of deep reinforcement learning and robotics, with a strong focus on ensuring that intelligent agents behave safely and reliably when deployed in real-world, safety-critical environments. He earned his PhD in Computer Science from the University of Verona under the supervision of Prof. Alessandro Farinelli. His research has been published at leading venues such as AAAI, IJCAI, ICLR, IROS, and RLC, where he was recently recognized with an Outstanding Paper Award for his work on autonomous underwater navigation.