Talk Title
Open-Endedness and General Intelligence
Talk Summary
In this talk, Tim Rocktäschel will speak about his work towards developing increasingly capable and general AI. Central to this research direction is Open-Endedness: the attempt to create an AI that endlessly improves and expands 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.
Speaker’s Bio
Tim Rocktäschel is a Professor of Artificial Intelligence at the Centre for Artificial Intelligence in the Department of Computer Science at University College London (UCL) where he is PI of the UCL Deciding, Acting, and Reasoning with Knowledge (DARK) Lab, as well as a Fellow of the European Laboratory for Learning and Intelligent Systems (ELLIS). He is also a Director / Principal Scientist and the Open-Endedness Team Lead at Google DeepMind. Before, he was managing the Reinforcement Learning Team at Meta AI (FAIR) London. He was a Postdoctoral Researcher in Reinforcement Learning at the Whiteson Research Lab at the University of Oxford, a Junior Research Fellow in Computer Science at Jesus College, and a Stipendiary Lecturer in Computer Science at Hertford College. He obtained his Ph.D. from UCL under the supervision of Sebastian Riedel, where he was awarded a Microsoft Research Ph.D. Scholarship in 2013 and a Google Ph.D. Fellowship in 2017. His work focuses on Artificial General Intelligence, Open-Endedness, and Self-Improvement, and it has received Best Paper Awards at ICML.