Stuart Russell

UC Berkeley

Publications

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

Alignment

This paper introduces Guaranteed Safe (GS) AI, an approach to AI safety that ensures high-assurance quantitative safety guarantees. It relies on three core components—a world model, a safety specification, and a verifier—to mathematically verify that AI systems meet safety requirements.

May 9, 2024
Date Range

Adversarial Policies Beat Superhuman Go AIs

Robustness

We describe an attack on the state-of-the-art Go-playing AI system, KataGo. The adversaries do not win by learning to play Go better than KataGo but instead by tricking KataGo into making serious blunders, demonstrating that even superhuman AI systems may harbor surprising failure modes.

January 8, 2023
Date Range

imitation: Clean Imitation Learning Implementations

Alignment

We describe a software package called "imitation" which provides PyTorch implementations of several imitation and reward learning algorithms, including three inverse reinforcement learning algorithms, three imitation learning algorithms, and a preference comparison algorithm.

September 21, 2022
Date Range

News

No items found.

Research

Our research explores a portfolio of high-potential agendas.

Events

Our events bring together global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI