Social Laws for Multi-agent Coordination in Stochastic Environments

2026-09-16

AI Summary

本文针对随机环境中多智能体协调问题，提出了一种基于奖励的社会法则形式化方法，并通过解决一系列马尔可夫决策过程来验证其鲁棒性。

Abstract

In multi-agent environments, coordinating agents to prevent interference and ensure robust individual performance is a critical challenge. Previous research on social laws for multi-agent systems has primarily focused on deterministic, goal-based settings. This paper extends the concept of social laws to stochastic, reward-based environments, proposing a formalism for defining and verifying their robustness under various conditions. We introduce the notion of $α$-robustness, a measure of the guaranteed utility each agent retains while pursuing its optimal single agent policy, assuming all agents obey the social law. We then present an approach for robustness verification of social laws in stochastic settings, based on a reduction to solving a series of Markov decision processes. Empirical evaluations on toy environments illustrate the potential of our framework.

Problem

• multi-agent coordination
• stochastic environments
• social laws
• robustness

Innovation

• social laws
• stochastic environments
• α-robustness
• Markov decision processes