随机环境下多智能体协调的社会法则
Social Laws for Multi-agent Coordination in Stochastic Environments
浏览论文内容
中文总结 AI 辅助
本文提出随机环境下多智能体社会法则的形式化框架，引入α-稳健性度量，并通过化简为马尔可夫决策过程进行验证，在玩具环境中展示其潜力。
中文摘要 AI 辅助
在多智能体环境中，协调智能体以防止干扰并确保稳健的个人性能是一个关键挑战。以往关于多智能体系统社会法则的研究主要集中在确定性、基于目标的环境中。本文将社会法则的概念扩展到随机、基于奖励的环境中，提出了一种形式化方法，用于在各种条件下定义和验证其稳健性。我们引入了α-稳健性的概念，即假设所有智能体遵守社会法则，每个智能体在追求其最优单智能体策略时所能保证的效用度量。然后，我们提出了一种在随机环境中对社会法则进行稳健性验证的方法，该方法基于将问题化简为求解一系列马尔可夫决策过程。在玩具环境上的实证评估展示了我们框架的潜力。
英文摘要
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.
发表机构
- The University of Texas at Austin（德克萨斯大学奥斯汀分校）
- Technion Israel Institute of Technology（以色列理工学院）
机构由 AI 辅助整理，请以论文原文为准。
