Incentivising cooperation by rewarding the weakest member

TL;DR

This paper proposes a novel reward mechanism based on the weakest member of a group to promote fairness and cooperation among autonomous agents in social domains, addressing challenges in designing equitable incentives.

Contribution

It introduces a simple reward scheme that enhances fairness and cooperation in multi-agent systems by focusing on the performance of the weakest member, inspired by biological theories.

Findings

Promotes equitable behavior in autonomous groups.

Maximizes individual and group outcomes.

Links to biological group selection theories.

Abstract

Autonomous agents that act with each other on behalf of humans are becoming more common in many social domains, such as customer service, transportation, and health care. In such social situations greedy strategies can reduce the positive outcome for all agents, such as leading to stop-and-go traffic on highways, or causing a denial of service on a communications channel. Instead, we desire autonomous decision-making for efficient performance while also considering equitability of the group to avoid these pitfalls. Unfortunately, in complex situations it is far easier to design machine learning objectives for selfish strategies than for equitable behaviors. Here we present a simple way to reward groups of agents in both evolution and reinforcement learning domains by the performance of their weakest member. We show how this yields ``fairer'' more equitable behavior, while also maximizing individual outcomes, and we show the relationship to biological selection mechanisms of group-level selection and inclusive fitness theory.