arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.07150math.OCcs.MA
收藏

具有分散信息的多智能体系统中的最优对称策略

Optimal Symmetric Strategies in Multi-Agent Systems with Decentralized Information

Sagar Sudhakara, Ashutosh Nayyar

AI总结:

本文研究分散信息协作多智能体系统中的有限时域最优对称策略,改造公共信息方法形成单函数最小化动态规划,并给出私有信息可约简的专用模型。

摘要:

我们考虑一个由一组具有分散信息的智能体组成的协作多智能体系统。我们的重点是为智能体设计对称(即相同)策略,以优化有限时域团队目标。我们从一般信息结构开始,然后考虑一些特殊情况。使用对称策略的约束给团队问题带来了新的特征和复杂性。例如,我们在一个简单示例中表明,随机对称策略可能优于确定性对称策略。我们还讨论了为什么在对称策略约束下,一些已知的用于减少团队中智能体私有信息的方法可能不再有效。随后,我们针对该问题采用公共信息方法,并对其进行修改以适应对称策略的使用。这产生了一个基于公共信息的动态规划,其中每一步都涉及对单个函数的最小化,该函数从智能体的私有信息空间映射到动作上概率分布的空间。我们给出了一些专用模型,在这些模型中,可以使用基于简单动态规划的论证来约简私有信息。

英文摘要:

We consider a cooperative multi-agent system consisting of a team of agents with decentralized information. Our focus is on the design of symmetric (i.e. identical) strategies for the agents in order to optimize a finite horizon team objective. We start with a general information structure and then consider some special cases. The constraint of using symmetric strategies introduces new features and complications in the team problem. For example, we show in a simple example that randomized symmetric strategies may outperform deterministic symmetric strategies. We also discuss why some of the known approaches for reducing agents' private information in teams may not work under the constraint of symmetric strategies. We then adopt the common information approach for our problem and modify it to accommodate the use of symmetric strategies. This results in a common information based dynamic program where each step involves minimization over a single function from the space of an agent's private information to the space of probability distributions over actions. We present specialized models where private information can be reduced using simple dynamic program based arguments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑