Stuart Armstrong

According to our database, Stuart Armstrong authored at least 23 papers between 2011 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

CoinRun: Solving Goal Misgeneralisation.

Stuart Armstrong, Alexandre Maranhão, Oliver Daniels-Koch, Patrick Leask, Rebecca Gormann

CoRR, 2023

Concept Extrapolation: A Conceptual Primer.

Matija Franklin, Rebecca Gormann, Hal Ashton, Stuart Armstrong

CoRR, 2023

2022

Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI.

Matija Franklin, Hal Ashton, Rebecca Gormann, Stuart Armstrong

CoRR, 2022

The dangers in algorithms learning humans' values and irrationalities.

Rebecca Gormann, Stuart Armstrong

CoRR, 2022

Missing Mechanisms of Manipulation in the EU AI Act.

Matija Franklin, Hal Ashton, Rebecca Gormann, Stuart Armstrong

Proceedings of the Thirty-Fifth International Florida Artificial Intelligence Research Society Conference, 2022

2021

Chess as a Testing Grounds for the Oracle Approach to AI Safety.

James D. Miller, Roman Yampolskiy, Olle Häggström, Stuart Armstrong

Proceedings of the Workshop on Artificial Intelligence Safety 2021 co-located with the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI 2021), 2021

2020

Pitfalls of Learning a Reward Function Online.

Stuart Armstrong, Jan Leike, Laurent Orseau, Shane Legg

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020

2018

Counterfactual equivalence for POMDPs, and underlying deterministic environments.

Stuart Armstrong

CoRR, 2018

Occam's razor is insufficient to infer the preferences of irrational agents.

Stuart Armstrong, Sören Mindermann

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2017

'Indifference' methods for managing agent rewards.

Stuart Armstrong

CoRR, 2017

Impossibility of deducing preferences and rationality from human policy.

Stuart Armstrong, Sören Mindermann

CoRR, 2017

Good and safe uses of AI Oracles.

Stuart Armstrong

CoRR, 2017

Low Impact Artificial Intelligences.

Stuart Armstrong, Benjamin Levinstein

CoRR, 2017

2016

Racing to the precipice: a model of artificial intelligence development.

Stuart Armstrong, Nick Bostrom, Carl Shulman

AI Soc., 2016

Safely Interruptible Agents.

Laurent Orseau, Stuart Armstrong

Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, 2016

Ghost Hunter - An Augmented Reality Ghost Busting Game.

Stuart Armstrong, Kyle Morrand

Proceedings of the Virtual, Augmented and Mixed Reality, 2016

2015

Corrigibility.

Nate Soares, Benja Fallenstein, Stuart Armstrong, Eliezer Yudkowsky

Proceedings of the Artificial Intelligence and Ethics, 2015

Motivated Value Selection for Artificial Agents.

Stuart Armstrong

Proceedings of the Artificial Intelligence and Ethics, 2015

2014

The errors, insights and lessons of famous AI predictions - and what they mean for the future.

Stuart Armstrong, Kaj Sotala, Seán Sáirséal Ó hÉigeartaigh

J. Exp. Theor. Artif. Intell., 2014

2012

Thinking Inside the Box: Controlling and Using an Oracle AI.

Stuart Armstrong, Anders Sandberg, Nick Bostrom

Minds Mach., 2012

2011

Risks and Mitigation Strategies for Oracle AI.

Stuart Armstrong

Proceedings of the Philosophy and Theory of Artificial Intelligence, 2011

Training and learning for crisis management using a virtual simulation/gaming environment.

Warren E. Walker, Jordan Giddings, Stuart Armstrong

Cogn. Technol. Work., 2011

Anthropic decision theory

Stuart Armstrong

CoRR, 2011