Intelligent Agents

[Deep Thought]

Mathematically defining intelligence is not only possible, it is also crucial to understanding and developing super-intelligent machines. The equation that we have developed is below and formalises the informal definition of intelligence, namely an agent’s ability to succeed or achieve goals in a wide range of environments.


In a nutshell, AIXI has a planning component and a learning component. Imagine a robot that initially has no knowledge about the world. It acquires information from the world from its sensors and constructs an approximate model of how the world works. New observations allow AIXI to improve its world model. AIXI uses this model to predict future events and bases its decisions on these tentative forecasts. The goal of AIXI is to maximise its reward over its lifetime.

Since AIXI is incomputable, it needs to be simplified in practice. Our work is in the early experimental phase: the approximation can learn to play Pac-Man, Tic-Tac-Toe and other games from scratch. Ultimately, we are developing rigorous foundations for intelligent agent systems, which are prerequisites for the creation of more flexible, adaptive, robust, reliable and secure software that our modern society needs.

Our interdisciplinary research on intelligent agents involves machine learning, reinforcement learning, artificial intelligence, information theory and statistics. AIXI integrates numerous philosophical, computational and statistical principles including Ockham’s razor, Bayes rule and Bellman equations

Explore our available student research projects below and if you’d like to discuss opportunities for collaboration or funding, please email us.

Academic staff

Portrait of Marcus Hutter

Professor Marcus Hutter »


Professor John Lloyd

Professor John Lloyd »

Emeritus Professor

Dr Yoshihiro Maruyama »


Dr Kee Siong NG »

Translational Fellow, Senior Lecturer


Mr Mark Burgess »

PhD Student

Mr Elliot Catt »

PhD Candidate

Tom Everitt

Mr Tom Everitt »

PhD student

Mr Iain Guilliard »

PhD Student

Mr Sean Lamont »


Mr Liyuan (Joe) Zhou »

PhD Student


Dr Dan Popescu »

Campus Visitor



  1. Baum, E., Hutter, M., Kitzelmann, E., (2010). Artificial General Intelligence: Third Conference on Artificial General Intelligence, AGI 2010 in Memoriam Ray Solomonoff, Eric Baum, Marcus Hutter & Emanuel Kitzelmann (eds.). Atlantis Press, ISBN: 9789078677369.
  2. Hutter, M., Stephan, F., Vovk, V., Zeugmann, T., (2010). Algorithmic Learning Theory, Randy Goebel, University of Alberta, Edmonton, Canada (eds.). Springer, ISBN: 3642161073

Book Chapters

  1. Hutter, M., (2010). Universal Learning Theory. In Claude Sammut & Geoffrey I.Webb (eds.), Encyclopedia of Machine Learning, Springer, ISBN: 9780387307688.

Journal Articles

  1. Hutter, M., (2010). A Complete Theory of Everything (will be subjective). Algorithms, 3(4):329–350.
  2. Hutter, M., Tran, M.-N., (2010). Model selection with the Loss Rank Principle. Computational Statistics and Data Analysis, 54:1288–1306.
  3. Rancoita, P.M.V., Hutter, M., Bertoni, F., Kwee, I., (2010). An integrated Bayesian analysis of LOH and copy number data. BMC Bioinformatics, 11(321):18 .
  4. Sunehag, P., Hutter, M., (2010). Consistency of Feature Markov Processes. In International Conference on Algorithmic Learning Theory 2010, pp. 15, Canberra Australia.
  5. Sunehag, P., Hutter, M., (2010). Consistency of Feature Markov Processes. In International Conference on Algorithmic Learning Theory 2010, pp. 15, Canberra Australia.

Updated:  1 June 2019/Responsible Officer:  Head of School/Page Contact:  CECS Webmaster