Cooperation and Control in Delegation Games

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sourbut, Oliver, Hammond, Lewis, Wood, Harriet
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909280275267584
author Sourbut, Oliver
Hammond, Lewis
Wood, Harriet
author_facet Sourbut, Oliver
Hammond, Lewis
Wood, Harriet
contents Many settings of interest involving humans and machines -- from virtual personal assistants to autonomous vehicles -- can naturally be modelled as principals (humans) delegating to agents (machines), which then interact with each other on their principals' behalf. We refer to these multi-principal, multi-agent scenarios as delegation games. In such games, there are two important failure modes: problems of control (where an agent fails to act in line their principal's preferences) and problems of cooperation (where the agents fail to work well together). In this paper we formalise and analyse these problems, further breaking them down into issues of alignment (do the players have similar preferences?) and capabilities (how competent are the players at satisfying those preferences?). We show -- theoretically and empirically -- how these measures determine the principals' welfare, how they can be estimated using limited observations, and thus how they might be used to help us design more aligned and cooperative AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2402_15821
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cooperation and Control in Delegation Games
Sourbut, Oliver
Hammond, Lewis
Wood, Harriet
Computer Science and Game Theory
Artificial Intelligence
Multiagent Systems
Many settings of interest involving humans and machines -- from virtual personal assistants to autonomous vehicles -- can naturally be modelled as principals (humans) delegating to agents (machines), which then interact with each other on their principals' behalf. We refer to these multi-principal, multi-agent scenarios as delegation games. In such games, there are two important failure modes: problems of control (where an agent fails to act in line their principal's preferences) and problems of cooperation (where the agents fail to work well together). In this paper we formalise and analyse these problems, further breaking them down into issues of alignment (do the players have similar preferences?) and capabilities (how competent are the players at satisfying those preferences?). We show -- theoretically and empirically -- how these measures determine the principals' welfare, how they can be estimated using limited observations, and thus how they might be used to help us design more aligned and cooperative AI systems.
title Cooperation and Control in Delegation Games
topic Computer Science and Game Theory
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2402.15821