Richard S. Sutton

from Wikipedia, the free encyclopedia
Richard S. Sutton 2016

Richard S. Sutton (* before 1978 in Ohio ) is an American computer scientist .

Sutton studied psychology at Stanford University with a bachelor's degree in 1978 and computer science at the University of Massachusetts at Amherst with a master's degree in 1980 and a doctorate in 1984 with Andrew Barto (Temporal Credit Assignment in Reinforcement Learning). He then worked at GTE Laboratories until 1995, moved back to the University of Massachusetts at Amherst and from 1998 worked at ATT Shannon Laboratories. From 2003 he was a professor at the University of Alberta , where he heads the Reinforcement Learning and Artificial Intelligence Laboratory (RLAI). He has also been running a Google DeepMind branch in Alberta since 2017 .

He developed the TD-Lambda-Algorithm for Temporal Difference Learning , which was used for example by Gerald Tesauro for his backgammon program (TD-Gammon). With Barto he wrote a standard work on reinforcement learning .

In 2001 he became a Fellow of the AAAI . According to his personal website (2017) he supports the Boycott, Divestment and Sanctions , BDS, campaign against Israel.

Fonts (selection)

  • with A. Barto: Toward a modern theory of adaptive networks: Expectation and prediction, Psychological Review, Volume 88, 1981, p. 135
  • with A. Barto, CW Anderson: Neuronlike adaptive elements that can solve difficult learning control problems, IEEE transactions on systems, man, and cybernetics, 1983, pp. 834-846
  • Learning to predict by the methods of temporal differences, in: Machine Learning, Volume 3, 1988, pp. 9-44
  • with A. Barto: Time Derivative Models of Pavlovian Reinforcement, in: Learning and Computational Neuroscience: Foundations of Adaptive Networks, 1990, pp. 497-537.
  • Editor with WT Miller, PJ Werbos: Neural Networks for Control, MIT Press 1991
  • with D. Precup, S. Singh: Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning, Artificial intelligence, Volume 112, 1999, pp. 181-211
  • with A. Barto: Reinforcement Learning. An Introduction, MIT Press 1998

Web links

Individual evidence

  1. ↑ Richard S. Sutton in the Mathematics Genealogy Project (English)Template: MathGenealogyProject / Maintenance / id used
personal data
SURNAME Sutton, Richard S.
BRIEF DESCRIPTION American computer scientist
DATE OF BIRTH before 1978
PLACE OF BIRTH Ohio