Andrew Barto facts for kids
Quick facts for kids
Andrew G. Barto
|
|
---|---|
![]() |
|
Born |
Andrew Gehret Barto
1948 (age 76–77) |
Nationality | American |
Alma mater | University of Michigan |
Awards | IEEE Neural Networks Society Pioneer Award, IJCAI Award for Research Excellence, Turing Award (2024) |
Scientific career | |
Fields | Computer science |
Institutions | University of Massachusetts Amherst |
Thesis | Cellular automata as models of natural systems (1975) |
Doctoral students |
|
Andrew Gehret Barto (born 1948) is an American computer scientist. He is a Professor Emeritus of computer science at the University of Massachusetts Amherst. Barto is famous for his important work in a field called reinforcement learning. This is a key part of modern artificial intelligence (AI).
Early Life and Education
Andrew Barto was born in 1948. He first studied naval architecture and engineering. But then he became very interested in mathematics. In 1970, he earned a special degree in math from the University of Michigan.
He then started to think about how computers and math could help us understand the human brain. In 1975, he earned his PhD in computer science. His research was about "cellular automata." These are like simple computer models that can show complex patterns.
Career
In 1977, Barto joined the University of Massachusetts Amherst. He started as a researcher after getting his PhD. Over the years, he became a full professor in 1991. He also led the computer science department from 2007 to 2011.
At UMass, Barto helped lead a special lab. It was called the Autonomous Learning Laboratory. This lab created many important ideas in reinforcement learning. Richard Sutton was his first PhD student. Together, they wrote a very important book. It was called Reinforcement Learning: An Introduction. Barto guided 27 students to get their PhDs. Many of them later became professors themselves.
What is Reinforcement Learning?
When Barto first started at UMass, he joined a group. They were trying to understand how neurons (brain cells) work. They wanted to see if this could explain human intelligence. Barto and his student, Richard Sutton, used math to explore this idea. They wanted to use it to build artificial intelligence. This new idea became known as reinforcement learning.
Reinforcement learning is a way for computers to learn by trying things out. Imagine a computer program (called an "agent") in a new environment. It doesn't know what to do. It tries an action, and then it gets a "reward" or a "penalty." If it gets a reward, it learns that action was good. If it gets a penalty, it learns that action was bad. Over time, the agent learns which actions lead to the biggest rewards. It learns even if it doesn't know all the rules of the environment beforehand.
Barto and Sutton's work made it possible for these computer programs to learn in unknown situations. This made reinforcement learning useful for many different problems.
Andrew Barto built a lab at UMass Amherst. There, he continued to develop ideas about reinforcement learning. This field grew in academic circles. Then, it had a huge real-world success. Google's AlphaGo program used reinforcement learning. AlphaGo famously beat the world champion in the game of Go. Barto and Sutton are seen as the pioneers of modern reinforcement learning. Their work is a key part of today's AI boom.
Barto has written over one hundred papers and book chapters. He co-authored the book Reinforcement Learning: An Introduction with Richard Sutton.
Awards and Honors
Andrew Barto has received many honors for his work. He is a Fellow of the American Association for the Advancement of Science. He is also a Fellow and Senior Member of the IEEE.
He received the UMass Neurosciences Lifetime Achievement Award in 2019. In 2004, he got the IEEE Neural Network Society Pioneer Award. He also received the IJCAI Award for Research Excellence in 2017. This award recognized his "groundbreaking and impactful research" in reinforcement learning.
In 2025, he received the Turing Award. This is one of the highest honors in computer science. He shared it with his former student, Richard S. Sutton. They received the award for creating the main ideas and methods behind reinforcement learning.