Richard S. Sutton

From Wikipedia, the free encyclopedia
Jump to: navigation, search
Richard S. Sutton
Residence Canada
Fields Artificial Intelligence
Reinforcement Learning
Institutions University of Alberta
Alma mater University of Massachusetts at Amherst
Stanford University
Thesis Temporal credit assignment in reinforcement learning (1984)
Doctoral advisor Andrew Barto
Doctoral students Doina Precup
David Silver
Hamid Maei
Adam White
Known for Temporal difference learning, Dyna, Options, GQ(λ)
Notable awards AAAI Fellow (2001)
President's Award (INNS) (2003)
Royal Society of Canada Fellow (2016)
Website
incompleteideas.net/sutton/

Richard S. Sutton is a Canadian computer scientist. Currently he is professor of Computer Science and iCORE chair at the University of Alberta. Dr. Sutton is considered one of the founding fathers of modern computational reinforcement learning, having several significant contributions to the field, including temporal difference learning, policy gradient methods, the Dyna architecture.

Education[edit]

Sutton received his B.A. degree at the Stanford University in Psychology in 1978, M.Sc. and Ph.D in computer science from University of Massachusetts at Amherst in 1980 and 1984, respectively, under the supervision of Andrew Barto. His doctoral dissertation was entitled "Temporal Credit Assignment in Reinforcement Learning", where he introduced actor-critic architectures and "temporal credit assignment".

Career[edit]

In 1984 Dr. Sutton held a postdoctoral position at University of Massachusetts at Amherst. From 1985 to 1994 he was a Principal Member of Technical Staff in the Computer and Intelligent Systems Laboratory at GTE Laboratories. In 1995 he returned to University of Massachusetts at Amherst as a Senior Research Scientist, position he held until 1998, when he joined the AT&T Shannon Laboratory as Principal Technical Staff Member in the Artificial Intelligence Department. Since 2003 he is Professor and iCORE Chair in the Department of Computing Science at the University of Alberta, where he leads the Reinforcement Learning and Artificial Intelligence Laboratory (RLAI).

Books[edit]

Sutton, R. S., Barto, A. G., Reinforcement Learning: An Introduction. MIT Press, 1998. Also translated into Japanese and Russian. Second edition in progress.

Miller, W. T., Sutton, R. S., Werbos, P. J. (Eds.), Neural Networks for Control. MIT Press, 1991.

Sutton, R. S. (Ed.), Reinforcement Learning. Reprinting of a special issue of Machine Learning Journal. Kluwer Academic Press, 1992

Awards and honors[edit]

Sutton is fellow of the Association for the Advancement of Artificial Intelligence (AAAI). In 2003 he received the President's Award from the International Neural Network Society and in 2013, the Outstanding Achievement in Research award from the University of Massachusetts Amherst.

Sutton's nomination as a AAAI fellow reads:

References[edit]

External links[edit]