Learning accurate, data-driven predictive models for multiple interacting agents following unknown dynamics is crucial in many real-world physical and social systems. In many scenarios, dynamics prediction must be performed under incomplete observations, i.e., only a subset of agents are known and observable from a larger topological system while the behaviors of the unobserved agents and their interactions with the observed agents are not known. When only incomplete observations of a dynamical system are available, so that some states remain hidden, it is generally not possible to learn a closed-form model in these variables using either analytic or data-driven techniques. In this work, we propose STEMFold, a spatiotemporal attention-based generative model, to learn a stochastic manifold to predict the underlying unmeasured dynamics of the multi-agent system from observations of only visible agents. Our analytical results motivate STEMFold design using a spatiotemporal graph with time anchors to effectively map the observations of visible agents to a stochastic manifold with no prior information about interaction graph topology. We empirically evaluated our method on two simulations and two real-world datasets, where it outperformed existing networks in predicting complex multiagent interactions, even with many unobserved agents.

翻译：学习精确的、数据驱动的预测模型以模拟遵循未知动力学的多个相互作用智能体，在众多真实世界的物理与社会系统中至关重要。在许多场景中，动力学预测必须在观测不完整的情况下进行，即仅能从更大的拓扑系统中观测到部分已知的智能体子集，而未观测智能体的行为及其与观测智能体之间的交互未知。当动力系统仅提供不完整观测值导致部分状态隐藏时，通常无法通过解析或数据驱动技术学习这些变量的闭合形式模型。本文提出STEMFold——一种基于时空注意力的生成模型，通过学习随机流形，仅依据可见智能体的观测数据预测多智能体系统的潜在未测量动力学。我们的分析结果通过引入带有时间锚点的时空图，在不预设交互图拓扑先验信息的情况下，将可见智能体的观测值有效映射至随机流形，从而指导STEMFold的设计。我们在两个模拟数据集和两个真实数据集上进行了实证评估，结果表明，即使存在大量未观测智能体，该方法在预测复杂多智能体交互方面仍优于现有网络。