James MacGlashan

Senior Research Scientist, Sony AI

Joined

July 2019

Names

James MacGlashan

Emails

****@gmail.com (Confirmed)

****@sony.com (Confirmed)

Personal Links

DBLP

Career & Education History

Senior Research Scientist

Sony AI (sony.com)

2019 – Present

Senior Research Scientist

Cogitai (cogitai.com)

2016 – 2019

Postdoc

Brown University (brown.edu)

2013 – 2016

PhD student

University of Maryland, Baltimore County (umbc.edu)

2007 – 2013

Undergrad student

University of Maryland, Baltimore County (umbc.edu)

2002 – 2007

Advisors, Relations & Conflicts

No relations added

Expertise

Robotics

2014 – Present

Reinforcement Learning

2009 – Present

Machine Learning

2007 – Present

Publications

How to Specify Reinforcement Learning Objectives
W. Bradley Knox, James MacGlashan
- Finding the Frame: RLC 2024 Poster
- Readers: Everyone
Gamma-Nets: Generalizing Value Estimation over Timescale
Craig Sherstan, Shibhansh Dohare, James MacGlashan, Johannes Günther, Patrick M. Pilarski
- 09 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Outracing champion Gran Turismo drivers with deep reinforcement learning
Peter R. Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani H. Gilpin, Piyush Khandelwal, Varun Raj Kompella, HaoChih Lin, Patrick MacAlpine, Declan Oller, Takuma Seno, Craig Sherstan, Michael D Thomure, Houmehr Aghabozorgi et al. (7 additional authors not shown)
- 09 May 2023 (modified: 09 May 2023)
- OpenReview Archive Direct Upload
- Readers: Everyone
Value Function Decomposition for Iterative Design of Reinforcement Learning Agents
James MacGlashan, Evan Archer, Alisa Devlic, Takuma Seno, Craig Sherstan, Peter R. Wurman, Peter Stone
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Interactive Learning from Policy-Dependent Human Feedback
James MacGlashan, Mark K. Ho, Robert Tyler Loftin, Bei Peng, Guan Wang, David L. Roberts, Matthew E. Taylor, Michael L. Littman
- 2017 (modified: 11 Nov 2022)
- ICML 2017
- Readers: Everyone
Reinforcement Learning as a Framework for Ethical Decision Making
David Abel, James MacGlashan, Michael L. Littman
- 2016 (modified: 16 Jul 2019)
- AAAI Workshop: AI, Ethics, and Society 2016
- Readers: Everyone
Showing versus doing: Teaching by demonstration
Mark K. Ho, Michael L. Littman, James MacGlashan, Fiery Cushman, Joseph L. Austerweil
- 2016 (modified: 11 Nov 2022)
- NIPS 2016
- Readers: Everyone
Portable Option Discovery for Automated Learning Transfer in Object-Oriented Markov Decision Processes
Nicholay Topin, Nicholas Haltmeyer, Shawn Squire, John Winder, Marie desJardins, James MacGlashan
- 2015 (modified: 16 Jul 2019)
- IJCAI 2015
- Readers: Everyone
Between Imitation and Intention Learning
James MacGlashan, Michael L. Littman
- 2015 (modified: 16 Jul 2019)
- IJCAI 2015
- Readers: Everyone
A Strategy-Aware Technique for Learning Behaviors from Discrete Human Feedback
Robert Tyler Loftin, James MacGlashan, Bei Peng, Matthew E. Taylor, Michael L. Littman, Jeff Huang, David L. Roberts
- 2014 (modified: 16 Jul 2019)
- AAAI 2014
- Readers: Everyone

View all 11 publications

Co-Authors

View all 47 co-authors