👈 This Machine Learning Street Talk interview summarises my research,
Also available on Apple podcasts 👉
My group is developing an Agent Foundation Model – a general-purpose learning and reasoning agent that learns to understand novel environments through active exploration, by forming explanatory world-models and executing its own experiments to refine them.
Core Research Themes
• Universal modelling: Develop an increasingly expressive hypothesis space, enabling the agent to model anything from physical to social interactions (cf. core knowledge).
• Model discovery: Infer plausible models based on agent-environment interaction history, online, and under suitable priors (cf. compression-based).
• Active learning: Create planners that choose actions for maximal model information gain, testing hypotheses through active environment interaction.
Why This Matters
• Open-ended, fully adaptive, generalist AI agents.
• Extreme sample efficiency & generalisation.
• Uncertainty quantification, safety and robustness.
• AI for scientific discovery.
The successful completion of this research program may be equivalent to artificial general intelligence.
Opportunities for Students & Collaborators
We are looking for motivated students and researchers who enjoy working on theory, large-scale experiments or both. If you are interested in contributing to this research program do reach out.