Richard S. Sutton

Richard S. Sutton

Fellow, Canada CIFAR AI Chair & Chief Scientific Advisor

Academic Affiliations

Professor – University of Alberta (Computing Science); Principal Investigator – Reinforcement Learning & Artificial Intelligence Lab (University of Alberta)

Industry and Research Affiliations

Associate Fellow – Learning in Machines and Brains Program (CIFAR); Fellow – Association for the Advancement of Artificial Intelligence (AAAI)

Areas of Expertise

Artificial intelligence; machine learning; reinforcement learning; model-free learning; off-policy learning; temporal-difference learning; knowledge representation; cognitive science

Richard S. Sutton is one of the pioneers of the field of reinforcement learning.

Learning from experience

Richard S. Sutton is one of the pioneers of reinforcement learning, an approach to artificial and natural intelligence that emphasizes learning and planning from sample experience, and a field in which he continues to lead the world. He is most interested in understanding what it means to be intelligent, to predict and influence the world, to learn, perceive, act, and think. He seeks to identify general computational principles underlying what we mean by intelligence and goal-directed behaviour. Over his career, he has made a number of significant contributions to the field, including the theory of temporal-difference learning, the actor-critic (policy gradient) class of algorithms, the Dyna architecture (integrating learning, planning and reacting), the Horde architecture, and gradient and emphatic temporal-difference algorithms – among other advancements. Richard currently seeks to extend reinforcement learning ideas to an empirically grounded approach to knowledge representation based on prediction.

Richard is Chief Scientific Advisor, a Fellow and Canada CIFAR AI Chair at Amii as well as a Professor of Computing Science at the University of Alberta and a Distinguished Research Scientist at DeepMind. He was the original founder of the Reinforcement Learning & Artificial Intelligence (RLAI) Lab at the University of Alberta, and he is co-author of Reinforcement Learning: An Introduction, the standard textbook on reinforcement learning, now in its second edition. Richard has been named a Fellow of the Royal Society of Canada, the Association for the Advancement of Artificial Intelligence (AAAI), and the Canadian Artificial Intelligence Association (CAIAC), where he also received a Life Time Achievement Award in 2018. Richard has been academic supervisor to almost 60 early-career researchers, and his publications have been cited more than 93,000 times. Richard has been featured in popular publications such as Science, the Economist, the New York Times, the Wallstreet Journal, and Bloomberg’s Hello World.