Andrew G. Barto and Richard S. Sutton have been named because the recipients of the 2024 ACM A.M. Turing Award for his or her contributions to the sphere of reinforcement studying starting within the Eighties.
Reinforcement studying is a coaching technique for AI techniques that teaches them how one can take advantage of optimum choices via a collection of indicators referred to as rewards. ChatGPT, as an example, was educated utilizing a way known as reinforcement studying from human suggestions (RLHF).
They wrote the textbook “Reinforcement Studying: An Introduction” in 1998, and it’s nonetheless a regular reference within the area, having been cited over 75,000 occasions.
Barto and Sutton had been answerable for growing lots of the primary algorithmic approaches utilized in reinforcement studying, together with temporal distinction studying, policy-gradient strategies, and utilizing neural networks to signify realized features.
Their work has additionally led to discoveries within the neuroscience area, particularly that sure reinforcement studying algorithms can clarify the dopamine system within the mind.
“Barto and Sutton’s work demonstrates the immense potential of making use of a multidisciplinary method to longstanding challenges in our area,” mentioned Yannis Ioannidis, president of ACM. “Analysis areas starting from cognitive science and psychology to neuroscience impressed the event of reinforcement studying, which has laid the foundations for a number of the most vital advances in AI and has given us better perception into how the mind works. Barto and Sutton’s work will not be a stepping stone that now we have now moved on from. Reinforcement studying continues to develop and affords nice potential for additional advances in computing and plenty of different disciplines. It’s becoming that we’re honoring them with probably the most prestigious award in our area.”
Barto is Professor Emeritus of Data and Laptop Sciences on the College of Massachusetts Amherst, and Sutton is a Professor of Laptop Science on the College of Alberta, a Analysis Scientist at Eager Applied sciences, and a Fellow at Alberta Machine Intelligence Institute.
