SMS scnews item created by Catherine Meister at Thu 13 Nov 2025 1034
Type: Seminar
Distribution: World
Expiry: 4 Dec 2025
Calendar1: 14 Nov 2025 1000-1200
CalLoc1: SMRI Seminar Room (A12 Macleay Room 301)
CalTitle1: Informal Friday Seminar - Marcus Hutter
Auth: cmeister@ac02gr132pn7c.shared.sydney.edu.au (cmei0631) in SMS-SAML

Informal Friday Seminar: Hutter

Universal Algorithmic Intelligence


Marcus Hutter, Australian National University/ Google DeepMind


Informal Friday Seminar, 14th November 2025


10 am – 12 pm, (***Note: Unusual time***) SMRI Seminar Room (A12 Macleay Room 301)


Abstract: 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.

Mini biography: Marcus Hutter is Senior Researcher at DeepMind and Professor in the RSCS at the Australian National University. He received his PhD and BSc in physics from the LMU in Munich and a Habilitation, MSc, and BSc in informatics from the TU Munich. Since 2000, his research at IDSIA and ANU and DeepMind has centered around the information-theoretic foundations of inductive reasoning and reinforcement learning, which has resulted in 200+ publications and several awards. His books on “Universal Artificial Intelligence” develop the first sound and complete theory of super-intelligent machines (ASI). He also runs the Human Knowledge Compression Contest (500'000€ H-prize). See http://www.hutter1.net/ for further information.

The Informal Friday Seminar is a space where members of our research group can explain interesting things to each other in a casual setting. The rules of the seminar are the following:

  1. Any question/additional explanation from the audience is allowed.
  2. Ego out the window.
  3. Examples, examples, examples.

    4. The seminar is intended to be conversational, so come ready to engage. If you choose to give an IFS talk, it's important to know that part of the IFS philosophy is that learning is not linear. In other words, it if perfectly acceptable to give a talk that is a prerequisite for a talk that already happened. For IFS updates, please see the IFS website