VAIN:注意力多智能体预测建模
VAIN: Attentional Multi-agent Predictive Modeling
摘要:
多智能体预测建模是理解物理,社会和团队游戏系统的重要一步。最近,交互网络(INs)被提出用于建模多智能体物理系统的任务,INs的规模与系统中的交互数量(通常是二次或更高阶的智能体数量)。在本文中,我们介绍了VAIN,一种新的注意力架构的多代理预测建模,规模与代理的数量呈线性关系。我们表明,VAIN是有效的多智能体预测建模。我们的方法进行评估的任务,从具有挑战性的多智能体预测领域:国际象棋和足球,并优于竞争的多智能体方法。
英文摘要:
Multi-agent predictive modeling is an essential step for understanding physical, social and team-play systems. Recently, Interaction Networks (INs) were proposed for the task of modeling multi-agent physical systems, INs scale with the number of interactions in the system (typically quadratic or higher order in the number of agents). In this paper we introduce VAIN, a novel attentional architecture for multi-agent predictive modeling that scales linearly with the number of agents. We show that VAIN is effective for multi-agent predictive modeling. Our method is evaluated on tasks from challenging multi-agent prediction domains: chess and soccer, and outperforms competing multi-agent approaches.
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。