Marcus Hutter

Marcus Hutter (born April 14, 1967 in Munich) is a professor and artificial intelligence researcher. A Senior Scientist at DeepMind, he is researching the mathematical foundations of artificial general intelligence.[1] He is on leave from his professorship at the ANU College of Engineering and Computer Science of the Australian National University in Canberra, Australia.[2] Hutter studied physics and computer science at the Technical University of Munich. In 2000 he joined Jürgen Schmidhuber's group at the Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (Dalle Molle Institute for Artificial Intelligence Research) in Manno, Switzerland. He developed a mathematical theory of artificial general intelligence. His book Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability was published by Springer in 2005.[3]

Marcus Hutter
Portrait of Marcus Hutter
NationalityGerman
Alma materTechnical University Munich and Ludwig Maximilian University of Munich
Known forUniversal artificial intelligence
Artificial General Intelligence
AwardsIJCAI 2023
Alignment 2018
AGI 2016
UAI 2016
IJCAI-JAIR 2014
Kurzweil AGI 2009
Lindley 2006
Best Paper Prizes
Scientific career
Fields
InstitutionsDeepMind, Google, IDSIA, ANU, BrainLAB
ThesisInstantons in QCD (1996)
Doctoral advisorHarald Fritzsch
Other academic advisorsWilfried Brauer
Doctoral studentsShane Legg and Jan Leike and Tor Lattimore
Websitewww.hutter1.net

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.[4][5]: 399 

In 2005, Hutter and Legg published an intelligence test for artificial intelligence devices.[6]

In 2009, Hutter developed and published the theory of feature reinforcement learning.[7]

In 2014, Lattimore and Hutter published an asymptotically optimal extension of the AIXI agent.[8]

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.[9] In 2020, Hutter raised the prize money for the Hutter Prize to €500,000.[10]

See also

Published works
  • Marcus Hutter (2002). "The Fastest and Shortest Algorithm for All Well-Defined Problems". International Journal of Foundations of Computer Science. World Scientific. 13 (3): 431–443. arXiv:cs/0206022. Bibcode:2002cs........6022H. 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. AAAI Press. 40: 95–142. arXiv:0909.0801. doi:10.1613/jair.3125. S2CID 206618.{{cite journal}}: CS1 maint: multiple names: authors list (link)

References
  1. . DeepMind. Accessed February 2019.
  2. . The Australian National University, Canberra. Accessed December 2016.
  3. Marcus Hutter (2005). Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Berlin; Heidelberg; New York: Springer. ISBN 9783540221395.
  4. Marcus Hutter (2002). "The Fastest and Shortest Algorithm for All Well-Defined Problems". International Journal of Foundations of Computer Science. 13 (3): 431–443. arXiv:cs/0206022. Bibcode:2002cs........6022H. doi:10.1142/S0129054102001199. S2CID 5496821.
  5. Bill Hibbard (2008). Adversarial Sequence Prediction. In: Pei Wang (editor) (2008). Artificial General Intelligence, 2008: Proceedings of the First AGI Conference. IOS Press. ISBN 9781586038335. Pages 399–403
  6. Duncan Graham-Rowe (12 August 2005). IQ test for AI devices gets experts thinking. New Scientist.
  7. Marcus Hutter (2009). "Feature Reinforcement Learning: Part {I}: Unstructured {MDP}s" (PDF). Journal of Artificial General Intelligence. ISSN 1946-0163.
  8. Tor Lattimore and Marcus Hutter (2014). "Bayesian Reinforcement Learning with Exploration" (PDF). Algorithmic Learning Theory. Proc. 25th International Conf. on Algorithmic Learning Theory ({ALT'14}). Lecture Notes in Computer Science. Vol. 8776. pp. 170–184. doi:10.1007/978-3-319-11662-4_13. hdl:1885/14709. ISBN 978-3-319-11661-7.
  9. Marcus Hutter. "50'000€ Prize for Compressing Human Knowledge". hutter1.net. Retrieved 29 November 2016.
  10. Marcus Hutter. "500'000€ Prize for Compressing Human Knowledge". hutter1.net. Retrieved 25 February 2020.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.