research
∙
06/19/2023
Concept Extrapolation: A Conceptual Primer
This article is a primer on concept extrapolation - the ability to take ...
share
research
∙
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...
research
∙
02/28/2022
The dangers in algorithms learning humans' values and irrationalities
For an artificial intelligence (AI) to be aligned with human values (or ...
research
∙
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...
research
∙
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...
research
∙
04/28/2020
Pitfalls of learning a reward function online
In some agent designs like inverse reinforcement learning an agent needs...
research
∙
01/11/2018
Counterfactual equivalence for POMDPs, and underlying deterministic environments
Partially Observable Markov Decision Processes (POMDPs) are rich environ...
research
∙
12/18/2017
'Indifference' methods for managing agent rewards
Indifference is a class of methods that are used to control a reward bas...
research
∙
12/15/2017
Impossibility of deducing preferences and rationality from human policy
Inverse reinforcement learning (IRL) attempts to infer human rewards or ...
research
∙
11/15/2017
Good and safe uses of AI Oracles
An Oracle is a design for potentially high power artificial intelligence...
research
∙
05/30/2017
Low Impact Artificial Intelligences
There are many goals for an AI that could become dangerous if the AI bec...
research
∙
10/28/2011