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：在众多真实世界的物理与社会系统中，学习基于数据的精确预测模型来建模遵循未知动力学的多智能体交互至关重要。许多场景下，动力学预测必须在观测不完整的情况下进行——即，仅能观测到更大拓扑系统中的一部分智能体，而未观测智能体的行为及其与可观测智能体的相互作用均未知。当动力系统仅能提供不完整观测数据（即存在隐状态）时，通常无法通过解析方法或数据驱动技术学习到这些变量的闭式模型。本文提出STEMFold——一种基于时空注意力的生成模型，通过仅观测可见智能体的数据，学习一个随机流形来预测多智能体系统中潜在的未测量动力学。我们的理论分析促使STEMFold设计采用带有时间锚点的时空图结构，使其能在无需交互图拓扑先验信息的条件下，将可见智能体的观测有效映射至随机流形。我们通过两个仿真数据集和两个真实世界数据集验证了该方法的有效性，结果表明即使在存在大量未观测智能体的场景下，STEMFold在预测复杂多智能体交互任务中的表现仍优于现有网络模型。