Anca Dragan
- Papers
- 6
Cite
Notes
Only stored in your browser.
6papers
Authored papers
6AssistanceZero: Scalably Solving Assistance Games
arXiv 2025
Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
arXiv 2024
Learning to Assist Humans without Inferring Rewards
arXiv 2024
The Effective Horizon Explains Deep RL Performance in Stochastic Environments
arXiv 2023
Learning Optimal Advantage from Preferences and Mistaking it for Reward
arXiv 2023
Inferring Rewards from Language in Context
ACL 2022 5
Affiliations
No known affiliations.
Frequent co-authors
10from 6 papers