Login / Signup
Confronting Reward Model Overoptimization with Constrained RLHF.
Ted Moskovitz
Aaditya K. Singh
DJ Strouse
Tuomas Sandholm
Ruslan Salakhutdinov
Anca D. Dragan
Stephen Marcus McAleer
Published in:
ICLR (2024)
Keyphrases
</>
computational model
experimental data
high level
prediction model
case study
conceptual model
network model
database
machine learning
artificial neural networks
probabilistic model
probability distribution
least squares
theoretical framework
statistical model
formal model