Samuel Barrett

Contact Info

Samuel Barrett Samuel Barrett

Location: Somerville, MA

Email: thesambarrett at gmail (dot) com


About Me

I am currently a research scientist at Cogitai, Inc., where I work to create artificial intelligence that continually learns from its interactions. Previously, I worked as a research scientist at Amazon Robotics. At AR, I worked on AI that improves the performance of the robotics system that helps to run some of Amazon's warehouses. Before that, I defended my Ph.D. thesis at the University of Texas at Austin on October 29, 2014. My dissertation examined the problem of ad hoc teamwork, cooperating with unknown teammates. Specifically, I looked into how robots and other agents could reuse knowledge learned about previous teammates in order to quickly adapt to new teammates. My advisor was Peter Stone, and I was a member of the Learning Agents Research Group (LARG). While at UT, I also helped the UT Austin Villa team win the 2012 international RoboCup competition in the standard platform league (SPL). Before joining UT, I obtained my B.S. in Computer Science from Stevens Institute of Technology in May 2008. You can find out more about my background through my CV.


My research interests are in artificial intelligence, machine learning, and robotics. I'm primarily interested in reinforcement learning and how to build knowledge from experience in decision making tasks. My dissertation focused on ad hoc teams: how agents should learn to deal with unknown teammates to accomplish shared goals. My goal was to create agents that can cooperate with any other teammates in a new environment and can still learn to perform effectively. I used techniques in the areas of transfer learning and reinforcement learning to allow agents to quickly learn and adapt to new teammates. You can find out more about my research through my publications.