VAIN: Attentional Multi-agent Predictive Modeling
This work addresses scalability issues in multi-agent systems for domains like physical, social, and team-play applications, offering a more efficient alternative to quadratic-scaling methods.
The paper tackled the problem of scaling multi-agent predictive modeling by introducing VAIN, an attentional architecture that scales linearly with the number of agents, and demonstrated its effectiveness by outperforming competing approaches on chess and soccer tasks.
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.