Stuart Armstrong | DeepAI

DeepAI AI Chat

Featured Co-authors

Shane Legg
41 publications
Jan Leike
27 publications
Laurent Orseau
22 publications
Roman Yampolskiy
7 publications
Matija Franklin
7 publications
Hal Ashton
7 publications
Sören Mindermann
7 publications
Rebecca Gorman
5 publications
James D. Miller
2 publications
Olle Haggstrom
2 publications
Anders Sandberg
2 publications

∙ 06/19/2023

Concept Extrapolation: A Conceptual Primer

This article is a primer on concept extrapolation - the ability to take ...

0 Matija Franklin, et al. ∙

∙ 03/20/2022

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

As artificial intelligence becomes more powerful and a ubiquitous presen...

0 Matija Franklin, et al. ∙

∙ 02/28/2022

The dangers in algorithms learning humans' values and irrationalities

For an artificial intelligence (AI) to be aligned with human values (or ...

0 Rebecca Gorman, et al. ∙

∙ 09/09/2021

Sigmoids behaving badly: why they usually cannot predict the future as well as they seem to promise

Sigmoids (AKA s-curves or logistic curves) are commonly used in a divers...

0 Anders Sandberg, et al. ∙

∙ 10/06/2020

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

To reduce the danger of powerful super-intelligent AIs, we might make th...

0 James D. Miller, et al. ∙

∙ 04/28/2020

Pitfalls of learning a reward function online

In some agent designs like inverse reinforcement learning an agent needs...

6 Stuart Armstrong, et al. ∙

∙ 01/11/2018

Counterfactual equivalence for POMDPs, and underlying deterministic environments

Partially Observable Markov Decision Processes (POMDPs) are rich environ...

0 Stuart Armstrong, et al. ∙

∙ 12/18/2017

'Indifference' methods for managing agent rewards

Indifference is a class of methods that are used to control a reward bas...

0 Stuart Armstrong, et al. ∙

∙ 12/15/2017

Impossibility of deducing preferences and rationality from human policy

Inverse reinforcement learning (IRL) attempts to infer human rewards or ...

0 Stuart Armstrong, et al. ∙

∙ 11/15/2017

Good and safe uses of AI Oracles

An Oracle is a design for potentially high power artificial intelligence...

0 Stuart Armstrong, et al. ∙

∙ 05/30/2017

Low Impact Artificial Intelligences

There are many goals for an AI that could become dangerous if the AI bec...

0 Stuart Armstrong, et al. ∙

∙ 10/28/2011

Anthropic decision theory

This paper sets out to resolve how agents ought to act in the Sleeping B...

0 Stuart Armstrong, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world