Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Stephane Hatgis-Kessell
Observed name:
Hatgis-Kessell, Stephane
Institution:
Stanford University
Observed institutions:
The University of Texas at Austin,
Stanford University
OpenAlex ID:
A5068136137
Models of human preference for learning reward functions
2022
·
Knox, W. Bradley
, Hatgis-Kessell, Stephane
, et al.
·
arXiv (Cornell University)
·
57
PDF
Learning Optimal Advantage from Preferences and Mistaking It for Reward
2024
·
W. Bradley Knox
, Stephane Hatgis-Kessell
, et al.
·
Proceedings of the AAAI Conference on Artificial Intelligence
·
8
PDF
Economic Evaluations of Language Models
2026
·
Wan, Alexander
, Hatgis-Kessell, Stephane
, et al.
·
arXiv (Cornell University)
·
2
PDF
Mitigating Social Sycophancy via Pluralistic Preference Optimization
2026
·
Hatgis-Kessell, Stephane
, Cheng, Myra
, et al.
·
arXiv (Cornell University)
PDF
Specifying Reward Functions for RL Without Environment Sampling
2026
·
Hatgis-Kessell, Stephane
, Knox, W. Bradley
, et al.
·
arXiv (Cornell University)
PDF
Estimating time spent on work tasks
2026
·
Hatgis-Kessell, Stephane
, Aguirre, Tomás
, et al.
·
arXiv (Cornell University)
PDF
When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
2026
·
Hatgis-Kessell, Stephane
, Brunskill, Emma
·
arXiv (Cornell University)
PDF
Repairing Reward Functions with Feedback to Mitigate Reward Hacking
2025
·
Hatgis-Kessell, Stephane
, Bhamidipaty, Logan Mondal
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
12
Citation count:
76
H-index:
3
I10-index:
1
Year
Topic
Type
