Multi-Value Alignment in Normative Multi-Agent System: An Evolutionary Optimisation Approach

TL;DR

This paper introduces a multi-value alignment model for normative multi-agent systems using multi-objective evolutionary algorithms to optimize norms that promote multiple values among heterogeneous agents.

Contribution

It presents a novel multi-value promotion model employing evolutionary algorithms and decentralized reasoning, addressing heterogeneity and simultaneous value alignment.

Findings

Different evolutionary algorithms impact solution quality.

Prioritizing values affects norm optimization.

Multiple values can be effectively aligned in heterogeneous systems.

Abstract

Value-alignment in normative multi-agent systems is used to promote a certain value and to ensure the consistent behaviour of agents in autonomous intelligent systems with human values. However, the current literature is limited to the incorporation of effective norms for single-value alignment with no consideration of agents' heterogeneity and the requirement of simultaneous promotion and alignment of multiple values. This research proposes a multi-value promotion model that uses multi-objective evolutionary algorithms and decentralised reasoning to produce the optimum parametric set of norms that is aligned with multiple simultaneous values of heterogeneous agents and the system. To understand various aspects of this complex problem, several evolutionary algorithms were used to find a set of optimised norm parameters considering two toy tax scenarios with two and five values are considered. The results are analysed from different perspectives to show the impact of a selected evolutionary algorithm on the solution, and the importance of understanding the relation between values when prioritising them.