Segui
Sumeet Motwani
Sumeet Motwani
Email verificata su berkeley.edu - Home page
Titolo
Citata da
Citata da
Anno
STARC: A General Framework For Quantifying Differences Between Reward Functions
J Skalse, L Farnik, SR Motwani, E Jenner, A Gleave, A Abate
The Twelfth International Conference on Learning Representations, 2023
32023
Secret Collusion Among Generative AI Agents
SR Motwani, M Baranchuk, M Strohmeier, V Bolina, PHS Torr, ...
arXiv preprint arXiv:2402.07510, 2024
12024
A Perfect Collusion Benchmark: How can AI agents be prevented from colluding with information-theoretic undetectability?
SR Motwani, M Baranchuk, L Hammond, CS de Witt
Multi-Agent Security Workshop@ NeurIPS 2023, 2023
2023
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–3