31 citations · 67 across the 9 of their papers we have counts for
10 papers
Model-Free RL Agents Demonstrate System 1-Like Intentionality
Hal Ashton, Matija Franklin
This paper argues that model-free reinforcement learning (RL) agents, while lacking explicit planning mechanisms, exhibit behaviours that can be analogised to System 1 ("thinking f…
Beyond Preferences in AI Alignment
Tan Zhi-Xuan, Micah Carroll, Matija Franklin +1
The dominant practice of AI alignment assumes (1) that preferences are an adequate representation of human values, (2) that human rationality can be understood in terms of maximizi…
Concept Extrapolation: A Conceptual Primer
Matija Franklin, Rebecca Gorman, Hal Ashton +1
This article is a primer on concept extrapolation - the ability to take a concept, a feature, or a goal that is defined in one context and extrapolate it safely to a more general c…
Characterizing Manipulation from AI Systems
Micah Carroll, Alan Chan, Henry Ashton +1
Manipulation is a common concern in many domains, such as social media, advertising, and chatbots. As AI systems mediate more of our interactions with the world, it is important to…
Solutions to preference manipulation in recommender systems require knowledge of meta-preferences
Hal Ashton, Matija Franklin
Iterative machine learning algorithms used to power recommender systems often change people's preferences by trying to learn them. Further a recommender can better predict what a u…
Preference Change in Persuasive Robotics
Matija Franklin, Hal Ashton
Human-robot interaction exerts influence towards the human, which often changes behavior. This article explores an externality of this changed behavior - preference change. It expa…
Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI
Matija Franklin, Hal Ashton, Rebecca Gorman +1
As artificial intelligence becomes more powerful and a ubiquitous presence in daily life, it is imperative to understand and manage the impact of AI systems on our lives and decisi…
Definitions of intent suitable for algorithms
Hal Ashton
Intent modifies an actor's culpability of many types wrongdoing. Autonomous Algorithmic Agents have the capability of causing harm, and whilst their current lack of legal personhoo…
Extending counterfactual accounts of intent to include oblique intent
Hal Ashton
One approach to defining Intention is to use the counterfactual tools developed to define Causality. Direct Intention is considered the highest level of intent in the common law, a…
Causal Campbell-Goodhart's law and Reinforcement Learning
Hal Ashton
Campbell-Goodhart's law relates to the causal inference error whereby decision-making agents aim to influence variables which are correlated to their goal objective but do not reli…