Andrew Barto is an American computer scientist and professor emeritus at the University of Massachusetts Amherst. He is universally recognized as one of the founding fathers of modern reinforcement learning.
Reinforcement Learning Foundations
Barto joined UMass Amherst in 1977 and established the Autonomous Learning Laboratory. Alongside his student Richard Sutton, he formulated the modern computational framework of reinforcement learning, which models how an artificial agent learns to make optimal decisions by interacting with an environment to maximize a scalar reward.
The Definitive Textbook and TD Learning
Barto and Sutton co-authored "Reinforcement Learning: An Introduction", which remains the definitive textbook and reference for the field. He pioneered temporal difference (TD) learning models, showing how they relate closely to dopamine reward prediction errors in the mammalian brain, bridging computer science and computational neuroscience.
