James MacGlashan
Profile
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.
Publications
Value Function Decomposition for Iterative Design of Reinforcement Learning Agents
NEURIPS, 2022 | James MacGlashan, Evan Archer, Alisa Devlic, Takuma Seno, Craig Sherstan, Peter R. Wurman, Peter Stone
Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons and standard RL methods provide too few tools to provide insight into the exact cause. In this paper, we show ...
Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning
NATURE, 2022 | Pete 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...
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...
Blog Posts
The Race to Turn a World-class AI into a World Champion
October 4, 2022 | Game AI, GT Sophy, Thomas Walsh, James MacGlashan, Kaushik Subramanian
GT SOPHY TECHNICAL SERIES Starting in 2020, the research and engineering team at Sony AI set out to do something that had never been done before: ...
Don’t Cross That Line! How Our AI Agent Learned Sportsmanship
September 15, 2022 | Game AI, GT Sophy, Patrick MacAlpine, James MacGlashan, Alisa Devlic
GT SOPHY TECHNICAL SERIES Starting in 2020, the research and engineering team at Sony AI set out to do something that had never been done before: ...
Meet the Team #1: James, Guillem and Raphaela
October 12, 2021 | Life at Sony AI, James MacGlashan, Raphaela Kreiser, Guillem I Torrente
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 ...