Faculty Recruiting Support CICS

Andrew G. Barto

emeritus
Position: 
Professor Emeritus

Interests

Learning in machines and animals; theories and models of motivation, reward, and addiction from psychology, neuroscience, and artificial intelligence; reinforcement learning theory and applications; fairness and safety of reinforcement learning applications.

Research

Professor Barto's research centers on learning in natural and artificial systems. His current research focuses on connections between reinforcement learning and neuroscience, with particular focus on the nature of reward signals in the brain and biologically plausible methods for artificial neural network learning. 

Biography

Ph.D., Computer Science, University of Michigan (1975), B.S., Mathematics, University of Michigan (1970). Emeritus Professor Barto joined what is now the Manning College of Information and Computer Sciences of the University of Massachusetts Amherst in 1977 as a Postdoctoral Research Associate, became an Associate Professor in 1982, and a Full Professor in 1991.  He co-founded the Autonomous Learning Laboratory and co-directed it until retiring in 2012. Professor Barto was Department Chair from 2007-2011. He is currently an Associate Member of the Neuroscience and Behavior Program of the University of Massachusetts.

Activities & Awards

Emeritus Professor Barto is an associate editor of Neural Computation, a member of the Advisory Board of the Journal of Machine Learning Research, and a member of the editorial board of Adaptive Behavior. He is a Fellow of the American Association for the Advancement of Science, a Fellow and Life Member of the IEEE, and a member of the Society for Neuroscience. He received the 2004 IEEE Neural Network Society Pioneer Award for contributions to the field of reinforcement learning, the IJCAI-17 Award for Research Excellence for groundbreaking and impactful research in both the theory and application of reinforcement learning, and a University of Massachusetts Neurosciences Lifetime Achievement Award in 2019. He has published over one hundred papers and chapters in journals, books, and conference and workshop proceedings. He is co-author with Richard Sutton of the book "Reinforcement Learning: An Introduction," MIT Press, 1998 -a much-expanded second edition of which was published in 2018. He was also co-editor with Jennie Si, Warren Powell, and Don Wunch II of the "Handbook of Learning and Approximate Dynamic Programming," Wiley-IEEE Press, 2004.