S
Stuart Armstrong
Researcher at University of Oxford
Publications - 57
Citations - 1163
Stuart Armstrong is an academic researcher from University of Oxford. The author has contributed to research in topics: Holonomy & Parallel transport. The author has an hindex of 18, co-authored 53 publications receiving 1003 citations. Previous affiliations of Stuart Armstrong include Schrödinger & Machine Intelligence Research Institute.
Papers
More filters
Journal ArticleDOI
Thinking Inside the Box: Controlling and Using an Oracle AI
TL;DR: This paper analyzes and critique various methods of controlling the AI, and suggests that an Oracle AI might be safer than unrestricted AI, but still remains potentially dangerous.
Proceedings Article
Safely interruptible agents
Laurent Orseau,Stuart Armstrong +1 more
TL;DR: This paper explores a way to make sure a learning agent will not learn to prevent being interrupted by the environment or a human operator, and provides a formal definition of safe interruptibility and exploit the off-policy learning property to prove that either some agents are already safely interruptible, like Q-learning, or can be made so, like Sarsa.
Journal ArticleDOI
Racing to the precipice: a model of artificial intelligence development
TL;DR: The Nash equilibrium of this process, where each team takes the correct amount of safety precautions in the arms race, points the way to methods of increasing the chance of the safe development of AI.
Journal ArticleDOI
Eternity in six hours: Intergalactic spreading of intelligent life and sharpening the Fermi paradox
Stuart Armstrong,Anders Sandberg +1 more
TL;DR: The Fermi paradox is the discrepancy between the strong likelihood of alien intelligent life emerging (under a wide variety of assumptions) and the absence of any visible evidence for such emergence as discussed by the authors.