Dr. Andrew G. Barto
Dept. of Computer Science, University of Massachuestts - Amherst
Articles sponsored or reviewed
Featured Author: Andrew Barto
Andrew Barto is Professor and Chair of Computer Science at the University of Massachusetts, Amherst, US. He graduated with distinction in mathematics from the University of Michigan in 1970 and obtained his Ph.D. in Computer Science in 1975 at the same institution. He joined the Computer Science Department of the University of Massachusetts in 1977 as a Postdoc, became an Associate Professor in 1982 and has been a Full Professor since 1991. He is Co-Director of the Autonomous Learning Laboratory and a core faculty member of the Neuroscience and Behavior Program of the University of Massachusetts.
Professor Barto is a fellow of the American Association for the Advancement of Science, a fellow and senior member of the IEEE, a member of the American Association for Artificial Intelligence and the Society for Neuroscience. He received the 2004 IEEE Neural Network Society Pioneer Award for his contributions to the field of reinforcement learning. He currently serves as an associate editor of Neural Computation, as a member of the editorial boards on numerous journals such as the Journal of Machine Learning Research and Adaptive Behavior. Together with Richard Sutton he is co-author of the book "Reinforcement Learning: An Introduction," MIT Press. Additionally he is co-editor of the "Handbook of Learning and Approximate Dynamic Programming," Wiley-IEEE Press.
Prof. Barto's research interests center on learning in animals and machines. He has been working on developing learning algorithms that are useful for engineering applications but that also make contact with learning as studied by psychologists and neuroscientists. He has contributed substantially to the field of reinforcement learning. He has studied machine learning algorithms since 1977, contributing to the development of the computational theory and practice of reinforcement learning. His recent work focuses on extending reinforcement learning methods so that they can work in real-time with real experience.
- Temporal difference learning , Scholarpedia, 2(11):1604. (2007)
For more information, visit http://www-all.cs.umass.edu/~barto/.
(Author profile by Nikos Green)
List of previous featured authors