research
∙
07/27/2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) is a technique for tra...
share
research
∙
02/20/2023
Harms from Increasingly Agentic Algorithmic Systems
Research in Fairness, Accountability, Transparency, and Ethics (FATE) ha...
research
∙
09/27/2022
Defining and Characterizing Reward Hacking
We provide the first formal definition of reward hacking, a phenomenon w...
research
∙
03/22/2021
Combining Reward Information from Multiple Sources
Given two sources of evidence about a latent variable, one can combine t...
research
∙
02/12/2019