Saved in:
Bibliographic Details
Main Authors: Parker, Timothy, Grandi, Umberto, Lorini, Emiliano
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.17229
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910691758178304
author Parker, Timothy
Grandi, Umberto
Lorini, Emiliano
author_facet Parker, Timothy
Grandi, Umberto
Lorini, Emiliano
contents Responsibility is a key notion in multi-agent systems and in creating safe, reliable and ethical AI. However, most previous work on responsibility has only considered responsibility for single outcomes. In this paper we present a model for responsibility attribution in a multi-agent, multi-value setting. We also expand our model to cover responsibility anticipation, demonstrating how considerations of responsibility can help an agent to select strategies that are in line with its values. In particular we show that non-dominated regret-minimising strategies reliably minimise an agent's expected degree of responsibility.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17229
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Responsibility in a Multi-Value Strategic Setting
Parker, Timothy
Grandi, Umberto
Lorini, Emiliano
Artificial Intelligence
Responsibility is a key notion in multi-agent systems and in creating safe, reliable and ethical AI. However, most previous work on responsibility has only considered responsibility for single outcomes. In this paper we present a model for responsibility attribution in a multi-agent, multi-value setting. We also expand our model to cover responsibility anticipation, demonstrating how considerations of responsibility can help an agent to select strategies that are in line with its values. In particular we show that non-dominated regret-minimising strategies reliably minimise an agent's expected degree of responsibility.
title Responsibility in a Multi-Value Strategic Setting
topic Artificial Intelligence
url https://arxiv.org/abs/2410.17229