The evolutionary advantage of guilt: co-evolution of social and non-social guilt in structured populations

TL;DR

This study explores how social and non-social guilt evolve in structured populations using game theory, revealing that structured networks promote guilt-driven cooperation and ethical AI development.

Contribution

It introduces a co-evolution model of social and non-social guilt, analyzing their dynamics in different network structures through analytical and simulation methods.

Findings

Structured populations favor guilt strategies over well-mixed populations.

Both guilt types can cluster and protect against exploitation.

Guilt promotes higher cooperation levels in networks.

Abstract

Building ethical machines may involve bestowing upon them the emotional capacity to self-evaluate and repent on their actions. While apologies represent potential strategic interactions, the explicit evolution of guilt as a behavioural trait remains poorly understood. Our study delves into the co-evolution of two forms of emotional guilt: social guilt entails a cost, requiring agents to exert efforts to understand others' internal states and behaviours; and non-social guilt, which only involves awareness of one's own state, incurs no social cost. Resorting to methods from evolutionary game theory, we study analytically, and through extensive numerical and agent-based simulations, whether and how guilt can evolve and deploy, depending on the underlying structure of the systems of agents. Our findings reveal that in lattice and scale-free networks, strategies favouring emotional guilt dominate a broader range of guilt and social costs compared to non-structured well-mixed populations, so leading to higher levels of cooperation. In structured populations, both social and non-social guilt can thrive through clustering with emotionally inclined strategies, thereby providing protection against exploiters, particularly for less costly non-social strategies. These insights shed light on the complex interplay of guilt and cooperation, enhancing our understanding of ethical artificial intelligence.