Date: Tuesday 19 October 2021 – 13:00 (Europe/London)
Speaker: Dr Stefano V. Albrecht, Head of the Autonomous Agents Research Group, University of Edinburgh
Abstract
Our group specialises in developing deep reinforcement learning algorithms applied to problems in which multiple agents interact (e.g. cooperate or compete) to solve a given task. I will give an overview of some of the recent work that has taken place in our group, which includes problems such as (a) scalable multi-agent reinforcement learning in which multiple agents learning together how to solve a given task; and (b) learning robust decision policies for a single agent when other agents may have diverse types and may enter/leave at any time. I will also give a brief glimpse into the research done at UK-based company Five AI on developing safe, interpretable planning and prediction algorithms for autonomous vehicles.
Biography
Dr Stefano V. Albrecht is Lecturer (Assistant Professor) in Artificial Intelligence in the School of Informatics at the University of Edinburgh. He leads the Autonomous Agents Research Group (https://agents.inf.ed.ac.uk) which currently consists of 14 members that conduct research into developing machine learning algorithms for autonomous systems, with a focus on reinforcement learning and multi-agent interaction problems. Dr. Albrecht is a Royal Society Industry Fellow working with a team at UK-based company Five AI to develop AI technologies for autonomous vehicles. His research has been published in leading AI/ML/robotics conferences and journals, including NeurIPS, ICML, IJCAI, AAAI, UAI, AAMAS, AIJ, JAIR, ICRA, IROS, T-RO. Previously, Dr. Albrecht was a postdoctoral fellow at the University of Texas at Austin where he was supported by a Humboldt Foundation fellowship. He obtained PhD and MSc degrees in Artificial Intelligence from the University of Edinburgh and a BSc degree in Computer Science from Technical University of Darmstadt.
