Universal Algorithmic Intelligence

Marcus Hutter, Australian National University/Google DeepMind There is great interest in understanding and constructing generally intelligent systems approaching and ultimately exceeding human intelligence. Universal AI is such a mathematical theory of machine super-intelligence. More precisely, AIXI is an elegant parameter-free theory of an optimal reinforcement learning agent embedded in an arbitrary unknown environment that possesses essentially all aspects of rational intelligence. The theory reduces all conceptual AI problems to pure computational questions. After a brief discussion of its philosophical, mathematical, and computational ingredients, I will give a formal definition and measure of intelligence, which is maximized by AIXI. AIXI can be viewed as the most powerful Bayes-optimal sequential decision maker, for which I will present general optimality results. This also motivates some variations such as knowledge-seeking and optimistic agents, and feature reinforcement learning. Finally I present some recent approximations, implementations, and applications of this modern top-down approach to AI. Note that the talk was longer than usual, and the recording cuts out into the second half. Marcus has directed us to the following talk, which covers a bit of the cut material: https://www.youtube.com/watch?v=vUUeHZJFN2Q Other talks and interviews featuring Marcus can be found here: https://www.youtube.com/playlist?list=PLvAl1s1syeUDvbL6UzT528f828h9fYCZ4 https://www.youtube.com/playlist?list=PLvAl1s1syeUDe4zpxA4ts4MM4HQ6TV8cK Friday 14th November, 2025