Philip S. Thomas
Scholar

Philip S. Thomas

Google Scholar ID: e8Gzgo4AAAAJ
University of Massachusetts
Artificial IntelligenceReinforcement LearningQualia OptimizationAI Safety
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
5,541
 
H-index
35
 
i10-index
63
 
Publications
20
 
Co-authors
53
list available
Contact
No contact links provided.
Publications
6 items
Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference
2025
Cited
0
Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited Feedback
2025
Cited
0
Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints
2025
Cited
0
Qualia Optimization
2025
Cited
0
Are Deep Speech Denoising Models Robust to Adversarial Noise?
2025
Cited
0
Supervised Reward Inference
2025
Cited
0
Resume (English only)
Co-authors
53 total
Co-author 1
Co-author 1
Emma Brunskill
Emma Brunskill
Associate Professor of Computer Science, Stanford University
Yash Chandak
Yash Chandak
Postdoctoral Scholar, Stanford University
Bruno Castro da Silva
Bruno Castro da Silva
University of Massachusetts
Mohammad Ghavamzadeh
Mohammad Ghavamzadeh
Amazon AGI
Scott Niekum
Scott Niekum
Associate Professor, University of Massachusetts Amherst
Co-author 7
Co-author 7
Co-author 8
Co-author 8