Search Results for author: Joe Halpern

Found 2 papers, 0 papers with code

Paying to Do Better: Games with Payments between Learning Agents

no code implementations31 May 2024 Yoav Kolumbus, Joe Halpern, Éva Tardos

Our results on general games show that in a broad class of games, players benefit from letting their learning agents make payments to other learners during the game dynamics, and that in many cases, this kind of behavior improves welfare for all players.

Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

no code implementations10 May 2024 David "davidad" Dalrymple, Joar Skalse, Yoshua Bengio, Stuart Russell, Max Tegmark, Sanjit Seshia, Steve Omohundro, Christian Szegedy, Ben Goldhaber, Nora Ammann, Alessandro Abate, Joe Halpern, Clark Barrett, Ding Zhao, Tan Zhi-Xuan, Jeannette Wing, Joshua Tenenbaum

Ensuring that AI systems reliably and robustly avoid harmful or dangerous behaviours is a crucial challenge, especially for AI systems with a high degree of autonomy and general intelligence, or systems used in safety-critical contexts.

Cannot find the paper you are looking for? You can Submit a new open access paper.