arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.02607cs.MA
收藏

认知规划下的多Agent协作系统通信建模

Modeling Communication of Collaborative Multi-Agent System under Epistemic Planning

Abeer Alshehri, Tim Miller, Liz Sonenberg

摘要:

在大多数多智能体应用中,智能体之间的通信是必不可少的,以协调他们的行动,从而实现他们的目标。然而,通信通常具有影响整体系统性能的相关成本。在本文中,我们从认知规划的研究中得到启发,开发了一个通信模型的代理,使他们能够合作,并有效地在规划任务中进行沟通决策。该模型将沟通过程视为一个行动,修改团队的认知状态。在两个模拟任务中,我们评估代理是否可以有效地合作,并实现更高的性能,使用我们的认知规划框架中建模的通信协议。基于使用搜索和救援任务与不同的情况下进行的实证研究,我们的研究结果表明,该模型在所有情况下,提高团队绩效与基线模型相比。

英文摘要:

In most multiagent applications, communication is essential among agents to coordinate their actions, and thus achieve their goal. However, communication often has a related cost that affects overall system performance. In this paper, we draw inspiration from studies of epistemic planning to develop a communication model for agents that allows them to cooperate and make communication decisions effectively within a planning task. The proposed model treats a communication process as an action that modifies the epistemic state of the team. In two simulated tasks, we evaluate whether agents can cooperate effectively and achieve higher performance using communication protocol modeled in our epistemic planning framework. Based on an empirical study conducted using search and rescue tasks with different scenarios, our results show that the proposed model improved team performance across all scenarios compared with baseline models.

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。

↑