Cite
Notes
Only stored in your browser.
Attribution
AssistanceZero: Scalably Solving Assistance Games
arXiv 2025
Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
arXiv 2024
The Effective Horizon Explains Deep RL Performance in Stochastic Environments
arXiv 2023
from 3 papers
Anca Dragan
Stuart Russell
professor
Banghua Zhu
Dylan Feng
Eli Bronstein
Justin Svegliato
Lukas Berglund
Shivam Singhal
Timothy Guo