Dependable Decision-Making Under Uncertainty: Beyond Probabilities
- 11:00 16th May 2023 ( week 5, Trinity Term 2023 )Lecture Theatre B, Wolfson Building
This talk highlights our vision of foundational and application-driven research toward safety and dependability in artificial intelligence (AI). We take a neuro-symbolic stance on AI that combines formal methods, machine learning, and control theory. As part of this research line, we study problems inspired by autonomous systems, planning in robotics, and industrial applications. We present a collection of research highlights that range from online and offline reinforcement learning in safety-critical environments, planning and control of partially observable and uncertain dynamical systems, and sampling-based verification of Markov models under uncertainty.
Speaker bio
Nils Jansen is an associate professor with the Institute for Computing and Information Science (ICIS) at Radboud University, Nijmegen, The Netherlands. He received his Ph.D. with distinction from RWTH Aachen University, Germany, in 2015. After his Ph.D., he worked as a research associate at the University of Texas at Austin. His research is on intelligent decision-making under uncertainty, focusing on formal reasoning about the safety and dependability of artificial intelligence (AI). He holds several grants in academic and industrial settings, including an ERC starting grant titled: Data-Driven Verification and Learning Under Uncertainty (DEUCE).
Thom Badings is a PhD candidate with the Institute for Computing and Information Science (ICIS) at the Radboud University, Nijmegen, the Netherlands. He holds a master’s degree (cum laude) in Industrial Engineering with a specialization in Systems & Control at the University of Groningen. In 2022, he received a distinguished paper award at AAAI, one of the leading AI conferences. His research focuses on how to use formal verification and AI to solve complex control problems for dynamical systems under uncertainty.
Marnix Suilen is a PhD candidate with the Institute for Computing and Information Science (ICIS) at the Radboud University, Nijmegen, the Netherlands. He holds a master’s degree in Computer Science with a specialization in Mathematical Foundations from Radboud University, Nijmegen. His current research is on robust decision-making and learning under uncertainty and partial observability, with several papers accepted at leading AI conferences such as NeurIPS, IJCAI, and AAAI.
Share this:
