Scholar
Robert Loftin
Google Scholar ID: ttJ9AWAAAAAJ
Lecturer, University of Sheffield
Citations & Impact
Citations
1,023
H-index
11
i10-index
12
Publications
20
Co-authors
15
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- - Paper: 'On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games', International Conference on Machine Learning, 2022
- - Paper: 'Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning', the 37th Conference on Uncertainty in Artificial Intelligence, 2021
- - Paper: 'Learning Behaviors via Human-Delivered Discrete Feedback: Modeling Implicit Feedback Strategies to Speed Up Learning', Autonomous Agents and Multi-Agent Systems, 2016
- - Paper: 'A Strategy-Aware Technique for Learning Behaviors from Discrete Human Feedback', the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2014
Research Experience
- - Currently a Lecturer in Machine Learning at the University of Sheffield
- - Two-year post-doc at Microsoft Research Cambridge, exploring the use of Reinforcement Learning and Interactive Learning in commercial game development
- - Post-doc at TU Delft with Dr. Frans Oliehoek, applying game theory to human-AI cooperation
Education
- - Ph.D. in Computer Science from North Carolina State University, 2019, supervised by Dave Roberts
- - B.S. in Computer Science from Georgia Tech, 2011
Background
- Research Interests: How AI can learn through interaction with humans. The goal is to allow humans and artificial agents to work together to build a shared understanding of tasks, enabling AI that leverages human knowledge, and ensuring that learned behaviors are truly aligned with human intentions. Research areas include (Deep) Reinforcement Learning, Game Theory and Multi-Agent Systems, and Cognitive Science.
