James is a senior research scientist at Sony AI. He received his PhD in computer science from the University of Maryland, Baltimore County. He went on to do postdoctoral research at Brown University from 2013-2016. He researches autonomous decision-making agents, focusing on Reinforcement Learning (RL), RL that involves interaction with people, and RL for robotics. He was the creator of the Brown-UMBC Reinforcement Learning and Planning (BURLAP) Java library, which was one of the largest early efforts to make an open-source RL library.


“My core goal at Sony AI is to apply reinforcement learning (RL) to real applications like games and robotics, and to research methods that make RL a more reliable tool that can be adopted by non-experts. As a consequence, I am interested in fundamental algorithmic innovations to improve the reliability of RL, methods that provide better insights into the outcomes of RL, and ways people can shape learning. Whenever possible, I like to ground my investigations into real-world applications to focus my research on the core issues with which RL methods currently struggle.”


Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning

Nature, 2022
Pete Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas J. 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…

Efficient Real-Time Inference in Temporal Convolution Networks

ICRA, 2021
Piyush Khandelwal, James MacGlashan, Pete Wurman, Peter Stone

It has been recently demonstrated that Temporal Convolution Networks (TCNs) provide state-of-the-art results in many problem domains where the input data is a time-series. TCNs typically incorporate information from a long history of inputs (the receptive field) into a singl…


October 12, 2021 | Sony AI

Meet the Team #1: James, Guillem and Raphaela

This is the first post in our new Sony AI Meet the Team series, which will shine a spotlight on the individuals that make up our very talented Sony AI team. Once a month, we will share highlights from our interviews with Sony AI …

This is the first post in our new Sony AI Meet the Team series, which will shine a spotlight on the individuals that make up our …


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.