New MIT Press textbook: Multi-Agent Reinforcement Learning: Foundations and Modern Approaches

Dr. Stefano V. Albrecht

I am a Reader (Associate Professor) in Artificial Intelligence in the School of Informatics, University of Edinburgh, where I lead the Autonomous Agents Research Group. In my role as RAEng Industrial Fellow, I work with Dematic/KION to develop machine learning technologies for multi-robot warehouse systems. In my previous role as Royal Society Industry Fellow, I worked with a team at Five AI/Bosch to develop AI technologies for autonomous driving in urban environments. I am also affiliated with the Alan Turing Institute where I lead the effort on multi-agent systems research.

My research interests are in the areas of autonomous agents, multi-agent interaction, reinforcement learning, and game theory, with a focus on sequential decision making under uncertainty. The long-term goal of my research is to create intelligent autonomous agents capable of robust interaction with other agents to accomplish tasks in complex environments.

Previously, I was a postdoctoral fellow at the University of Texas at Austin in Peter Stone's group. I 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. I received personal fellowships from the Royal Academy of Engineering, the Royal Society, the Alexander von Humboldt Foundation, and the German Academic Scholarship Foundation (Studienstiftung). In 2022, I was honoured to be nominated for the IJCAI Computers and Thought Award.

Google Scholar | Google Patents

How to pronounce my name

Teaching

I teach the MSc-level course on Reinforcement Learning (INFR11010).

I am co-author of the MIT Press textbook Multi-Agent Reinforcement Learning: Foundations and Modern Approaches with Filippos Christianos and Lukas Schäfer.

I am accredited as Fellow of the Higher Education Academy.

Students

I am always looking for talented students who have a deep interest in autonomous systems and want to work on challenging research problems. If you are looking for potential research topics, see our surveys on multi-agent reinforcement learning, agents modelling other agents, and ad hoc teamwork. Feel free to contact me if you would like to discuss research ideas. I am more likely to reply if your message includes concrete ideas for research projects.

PhD funding sources: here, here, here

We have several CDT PhD programmes: D2AIR CDT, MLSystems CDT, SPADS CDT

Handbook for PhD students in our group