Marcus Hutter

Marcus Hutter (born 14 April 1967 in Munich) is a computer scientist, professor and artificial intelligence researcher. As a senior researcher at DeepMind, he studies the mathematical foundations of artificial general intelligence.^[1][2]

Marcus Hutter
Nationality	German
Alma mater	Technical University Munich and Ludwig Maximilian University of Munich
Known for	Universal artificial intelligence Artificial General Intelligence
Awards	IJCAI 2023 Alignment 2018 AGI 2016 UAI 2016 IJCAI-JAIR 2014 Kurzweil AGI 2009 Lindley 2006 Best Paper Prizes
Scientific career
Fields	Artificial Intelligence Bayesian Statistics Information Theory Particle Physics
Institutions	DeepMind, Google, IDSIA, ANU, BrainLAB
Thesis	Instantons in QCD (1996)
Doctoral advisor	Harald Fritzsch
Other academic advisors	Wilfried Brauer
Doctoral students	Shane Legg, Jan Leike and Tor Lattimore
Website	www.hutter1.net

Hutter studied physics and computer science at the Technical University of Munich. In 2000 he joined Jürgen Schmidhuber's group at the Dalle Molle Institute for Artificial Intelligence Research in Manno, Switzerland.^[3][4] He developed a mathematical formalism of artificial general intelligence named AIXI. He has served as a professor at the College of Engineering, Computing and Cybernetics of the Australian National University in Canberra, Australia.^[5]

Research

Starting in 2000, Hutter developed and published a mathematical theory of artificial general intelligence, AIXI, based on idealised intelligent agents and reward-motivated reinforcement learning.^[6][7][4] His first book Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability was published in 2005 by Springer.^[8] Also in 2005, Hutter published with his doctoral student Shane Legg an intelligence test for artificial intelligence devices.^[9] In 2009, Hutter developed and published the theory of feature reinforcement learning.^[10] In 2014, Lattimore and Hutter published an asymptotically optimal extension of the AIXI agent.^[11]

An accessible podcast with Lex Fridman about his theory of Universal AI appeared in 2021^[12] and a more technical follow-up with Tim Nguyen in 2024 in the Cartesian Cafe.^[13] His new (2024) book^[14] also gives a more accessible introduction to Universal AI and progress in the 20 years since his first book, including a chapter on ASI safety, which featured as a keynote at the inaugural workshop on AI safety in Sydney.^[15]

Hutter Prize

Main article: Hutter Prize

In 2006, Hutter announced the Hutter Prize for Lossless Compression of Human Knowledge, with a total of €50,000 in prize money.^[16][17] In 2020, Hutter raised the prize money for the Hutter Prize to €500,000.^[4]

See also

• Solomonoff induction

Published works

• Marcus Hutter (2002). "The Fastest and Shortest Algorithm for All Well-Defined Problems". International Journal of Foundations of Computer Science. 13 (3). World Scientific: 431–443. arXiv:cs/0206022. doi:10.1142/S0129054102001199. S2CID 5496821.
• Marcus Hutter (2005). Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Springer. ISBN 9783540221395.
• Joel Veness, Kee Siong Ng, Marcus Hutter, William Uther and David Silver (2011). "A Monte-Carlo AIXI Approximation". Journal of Artificial Intelligence Research. 40. AAAI Press: 95–142. arXiv:0909.0801. doi:10.1613/jair.3125. S2CID 206618.{{cite journal}}: CS1 maint: multiple names: authors list (link)
• Shane Legg and Marcus Hutter (2007). "Universal Intelligence: A Definition of Machine Intelligence". Minds and Machines. 17 (4): 391–444. arXiv:0712.3329. doi:10.1007/s11023-007-9079-x.
• Marcus Hutter (2010). "A Complete Theory of Everything (will be subjective)". Algorithms. 3 (4): 329–350. arXiv:0912.5434. doi:10.3390/a3040329.
• Samuel Rathmanner and Marcus Hutter (2011). "A Philosophical Treatise of Universal Induction". Entropy. 13 (6). MDPI: 1076–1136. arXiv:1105.5721. doi:10.3390/e13061076.
• Marcus Hutter (2012). "Can Intelligence Explode?". Journal of Consciousness Studies. 19 (1–2): 143–166. arXiv:1202.6177.
• Peter Sunehag and Marcus Hutter (2015). "Rationality, Optimism and Guarantees in General Reinforcement Learning". Journal of Machine Learning Research. 16: 1345–1390.
• Reinhard Hutter and Marcus Hutter (2021). "Chances and Risks of Artificial Intelligence – A Concept of Developing and Exploiting Machine Intelligence for Future Societies". Applied System Innovation. 4 (2): 1–19.
• Marcus Hutter (2024). An Introduction to Universal Artificial Intelligence. Taylor & Francis. ISBN 9781032607023.