Multi-Value Alignment in Normative Multi-Agent System: Evolutionary Optimisation Approach
This addresses the challenge of ensuring consistent agent behavior with human values in autonomous systems, though it is incremental as it extends single-value alignment to multiple values using existing evolutionary methods.
The paper tackles the problem of aligning heterogeneous agents with multiple simultaneous values in normative multi-agent systems, proposing a multi-value promotion model using multi-objective evolutionary algorithms to optimize norm parameters, with results analyzed in toy tax scenarios involving two and five values.
Value-alignment in normative multi-agent systems is used to promote a certain value and to ensure the consistent behavior of agents in autonomous intelligent systems with human values. However, the current literature is limited to 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 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.