Philip Thomas

Philip Thomas Photo
Assistant Professor
262 CS Building


Reinforcement learning, decision making, and AI safety.


Professor Thomas's research interests are in reinforcement learning, decision making, and AI safety. He is most interested in designing reinforcement learning algorithms that are more biologically plausible than existing algorithms, or which provide various forms of safety guarantees that make them viable for high-risk applications (e.g., medical applications). Towards these goals he has performed extensive work on (high-confidence) off-policy policy evaluation methods, with preliminary experiments for both digital marketing and medical applications. He has also studied methods for performing deep reinforcement learning without the need for the biologically implausible propagation of information backwards through the neural network.  


Ph.D., Computer Science, University of Massachusetts Amherst (2015). M.Sc. Computer Science, Case Western Reserve University (2009), B.Sc. Computer Science, Case Western Reserve University (2008). Philip spent 2015-2017 as a postdoctoral researcher at Carnegie Mellon University. Philip will join the College of Information and Computer Sciences at the University of Massachusetts, Amherst in Fall 2017 as an Assistant Professor.

Activities & Awards

Professor Thomas received an honorable mention for the National Science Foundation Graduate Research Fellowship in 2009. He also received the Outstanding Teaching Assistant Award and Dissertation Writing Fellowship from the University of Massachusetts Amherst in 2012 and 2015 respectively.