Follow
Charlie Griffin
Charlie Griffin
University of Oxford
Verified email at cs.ox.ac.uk
Title
Cited by
Cited by
Year
Lexicographic Multiobjective Reinforcement Learning
J Skalse, L Hammond, C Griffin, A Abate
International Joint Conferences on Artificial Intelligence Organization, 2022
272022
Goodhart's Law in Reinforcement Learning
J Karwowski, O Hayman, X Bai, K Kiendlhofer, C Griffin, J Skalse
arXiv preprint arXiv:2310.09144, 2023
112023
Privacy-preserving object detection
P He, C Griffin, K Kacprzyk, A Joosen, M Collyer, A Shtedritski, YM Asano
arXiv preprint arXiv:2103.06587, 2021
52021
On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning
R Subramani, M Williams, M Heitmann, H Holm, C Griffin, J Skalse
arXiv preprint arXiv:2310.11840, 2023
42023
Games for ai control: Models of safety evaluations of ai deployment protocols
C Griffin, L Thomson, B Shlegeris, A Abate
arXiv preprint arXiv:2409.07985, 2024
22024
All’s Well That Ends Well: Avoiding Side Effects with Distance-Impact Penalties
C Griffin, JMV Skalse, L Hammond, A Abate
NeurIPS ML Safety Workshop, 2022
22022
Subversion Strategy Eval: Evaluating AI's stateless strategic capabilities against control protocols
A Mallen, C Griffin, A Abate, B Shlegeris
arXiv preprint arXiv:2412.12480, 2024
2024
Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features
D Cruz, E Pona, A Holness-Tofts, E Schmied, VA Alonso, C Griffin, ...
arXiv preprint arXiv:2311.04046, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–8