Samuel
Barrett

Profile

Samuel joined Sony AI in 2019 as a senior research scientist, when Sony AI acquired Cogitai. He previously worked at Amazon Robotics using AI to improve the performance of the robotics system inside Amazon's warehouses. He received his Ph.D. thesis at the University of Texas at Austin in October 2014. His dissertation examined the problem of ad hoc teamwork and cooperating with unknown teammates by exploiting previously learned knowledge. In addition, he helped the UT Austin Villa team win the 2012 international RoboCup competition in the standard platform league (SPL). Before joining UT, Sam received his B.S. in computer science from Stevens Institute of Technology in May 2008.

Message

“At Sony AI, I work on combining artificial intelligence and video games. My work includes advancements on reinforcement learning and deep learning, especially as applied to difficult problems. I am interested in how it is possible to speed up learning approaches, including by including more human information. I am also interested in how artificial agents interact with humans.”

Publications

Event Tables for Efficient Experience Replay

CoLLAs, 2023
Varun Kompella, Thomas Walsh, Samuel Barrett, Peter R. Wurman, Peter Stone

Experience replay (ER) is a crucial component of many deep reinforcement learning (RL) systems. However, uniform sampling from an ER buffer can lead to slow convergence and unstable asymptotic behaviors. This paper introduces Stratified Sampling from Event Tables (SSET), whi…

Event Tables for Efficient Experience Replay

TMLR, 2023
Varun Kompella, Thomas Walsh, Samuel Barrett, Peter R. Wurman, Peter Stone

Experience replay (ER) is a crucial component of many deep reinforcement learning (RL) systems. However, uniform sampling from an ER buffer can lead to slow convergence and unstable asymptotic behaviors. This paper introduces Stratified Sampling from Event Tables (SSET), whi…

Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning

Nature, 2022
Peter Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani Gilpin, Piyush Khandelwal, Varun Kompella, Hao Chih Lin, Patrick MacAlpine, Declan Oller, Takuma Seno, Craig Sherstan, Michael D. Thomure, Houmehr Aghabozorgi, Leon Barrett, Rory Douglas, Dion Whitehead Amago, Peter Dürr, Peter Stone, Michael Spranger, Hiroaki Kitano

Many potential applications of artificial intelligence involve making real-time decisions in physical systems while interacting with humans. Automobile racing represents an extreme example of these conditions; drivers must execute complex tactical manoeuvres to pass or block…

Blog

May 30, 2022 | Sony AI

Meet the Team #5: Craig, Piyush, and Samuel

The fifth installment of our Meet the Team series features members of the global Sony AI team who contributed to the groundbreaking research, Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning, and created th…

The fifth installment of our Meet the Team series features members of the global Sony AI team who contributed to the groundbreakin…

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.