Modeling multi-agent systems requires understanding how agents interact. Such systems are often difficult to model because they can involve a variety of types of interactions that layer together to drive rich social behavioral dynamics. Here we introduce a method for accurately modeling multi-agent systems. We present Interaction Modeling with Multiplex Attention (IMMA), a forward prediction model that uses a multiplex latent graph to represent multiple independent types of interactions and attention to account for relations of different strengths. We also introduce Progressive Layer Training, a training strategy for this architecture. We show that our approach outperforms state-of-the-art models in trajectory forecasting and relation inference, spanning three multi-agent scenarios: social navigation, cooperative task achievement, and team sports. We further demonstrate that our approach can improve zero-shot generalization and allows us to probe how different interactions impact agent behavior.

翻译：建模多试剂系统需要了解代理方如何互动。 这些系统往往难以建模, 因为它们可能涉及多种类型的互动, 从而共同驱动丰富的社会行为动态。 我们在这里引入了一种精确建模多试剂系统的方法。 我们展示了多倍关注的互动建模(IMMA), 这是一种前方预测模型, 使用多倍潜在图代表多种独立的互动类型, 并关注不同强项的关系。 我们还引入了渐进层培训, 这是一种用于这一架构的培训战略。 我们展示了我们的方法在轨迹预测和关系推论方面优于最先进的模型, 跨越了三种多试想情景: 社会导航、合作任务成就和团队体育。 我们还展示了我们的方法可以改进零光的概括, 并使我们能够探究不同互动如何影响代理方行为。