I will talk about our research towards developing increasingly capable and general AI. Central to this research direction is Open-Endedness: the attempt to create an AI that can endlessly improve and expand its capabilities. In particular, this talk will focus on three areas: training autonomous and robust agents that can set themselves problems and goals, training large-scale world models which can provide AIs with endless environments to learn in, and lastly, the connection of Open-Endedness methods to Large Language Models to develop AI that can improve itself with applications in automated prompt engineering and AI safety.
Bio: I'm a Professor of Artificial Intelligence at the Centre for Artificial Intelligence in the Department of Computer Science at University College London (UCL) where I'm a PI of the UCL Deciding, Acting, and Reasoning with Knowledge (DARK) Lab. I'm also the Open-Endedness Team Lead at Google DeepMind, and a Scholar of the European Laboratory for Learning and Intelligent Systems (ELLIS).
