Ian Goodfellow
Orcid: 0000-0002-9483-510X
According to our database1,
Ian Goodfellow
authored at least 3 papers
between 2017 and 2025.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2025
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking.
CoRR, January, 2025
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking.
Proceedings of the Forty-second International Conference on Machine Learning, 2025
2017
Nat., 2017