Managing multiple agents by automatically adjusting incentives

TL;DR

This paper introduces a framework where a manager agent automatically adjusts incentives to align self-interested agents' actions with societal benefits, demonstrated through improved rewards in a supply-chain scenario.

Contribution

It proposes a novel incentive management method with a manager agent to promote societal benefits in multi-agent systems, validated through empirical experiments.

Findings

Increases raw reward by 22.2%.

Boosts agents' reward by 23.8%.

Enhances manager’s reward by 20.1%.

Abstract

In the coming years, AI agents will be used for making more complex decisions, including in situations involving many different groups of people. One big challenge is that AI agent tends to act in its own interest, unlike humans who often think about what will be the best for everyone in the long run. In this paper, we explore a method to get self-interested agents to work towards goals that benefit society as a whole. We propose a method to add a manager agent to mediate agent interactions by assigning incentives to certain actions. We tested our method with a supply-chain management problem and showed that this framework (1) increases the raw reward by 22.2%, (2) increases the agents' reward by 23.8%, and (3) increases the manager's reward by 20.1%.