The Reasons that Agents Act: Intention and Instrumental Goals

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ward, Francis Rhys, MacDermott, Matt, Belardinelli, Francesco, Toni, Francesca, Everitt, Tom
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916125886906368
author Ward, Francis Rhys
MacDermott, Matt
Belardinelli, Francesco
Toni, Francesca
Everitt, Tom
author_facet Ward, Francis Rhys
MacDermott, Matt
Belardinelli, Francesco
Toni, Francesca
Everitt, Tom
contents Intention is an important and challenging concept in AI. It is important because it underlies many other concepts we care about, such as agency, manipulation, legal responsibility, and blame. However, ascribing intent to AI systems is contentious, and there is no universally accepted theory of intention applicable to AI agents. We operationalise the intention with which an agent acts, relating to the reasons it chooses its decision. We introduce a formal definition of intention in structural causal influence models, grounded in the philosophy literature on intent and applicable to real-world machine learning systems. Through a number of examples and results, we show that our definition captures the intuitive notion of intent and satisfies desiderata set-out by past work. In addition, we show how our definition relates to past concepts, including actual causality, and the notion of instrumental goals, which is a core idea in the literature on safe AI agents. Finally, we demonstrate how our definition can be used to infer the intentions of reinforcement learning agents and language models from their behaviour.
format Preprint
id arxiv_https___arxiv_org_abs_2402_07221
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Reasons that Agents Act: Intention and Instrumental Goals
Ward, Francis Rhys
MacDermott, Matt
Belardinelli, Francesco
Toni, Francesca
Everitt, Tom
Artificial Intelligence
Intention is an important and challenging concept in AI. It is important because it underlies many other concepts we care about, such as agency, manipulation, legal responsibility, and blame. However, ascribing intent to AI systems is contentious, and there is no universally accepted theory of intention applicable to AI agents. We operationalise the intention with which an agent acts, relating to the reasons it chooses its decision. We introduce a formal definition of intention in structural causal influence models, grounded in the philosophy literature on intent and applicable to real-world machine learning systems. Through a number of examples and results, we show that our definition captures the intuitive notion of intent and satisfies desiderata set-out by past work. In addition, we show how our definition relates to past concepts, including actual causality, and the notion of instrumental goals, which is a core idea in the literature on safe AI agents. Finally, we demonstrate how our definition can be used to infer the intentions of reinforcement learning agents and language models from their behaviour.
title The Reasons that Agents Act: Intention and Instrumental Goals
topic Artificial Intelligence
url https://arxiv.org/abs/2402.07221