Intelligent agents use internal world models to reason and make predictions about different courses of their actions at many scales. Devising learning paradigms and architectures that allow machines to learn world models that operate at multiple levels of temporal abstractions while dealing with complex uncertainty predictions is a major technical hurdle. In this work, we propose a probabilistic formalism to learn multi-time scale world models which we call the Multi Time Scale State Space (MTS3) model. Our model uses a computationally efficient inference scheme on multiple time scales for highly accurate long-horizon predictions and uncertainty estimates over several seconds into the future. Our experiments, which focus on action conditional long horizon future predictions, show that MTS3 outperforms recent methods on several system identification benchmarks including complex simulated and real-world dynamical systems.

在这项工作中，我们提出了一种概率形式主义来学习多时间尺度世界模型，即Multi Time Scale State Space (MTS3) 模型。我们的模型使用多时间尺度上的计算有效推理方案，以对未来数秒的高准确性和不确定性进行预测。我们的实验集中于行动条件下的远期预测，结果显示 MTS3 在包括复杂模拟和真实世界动态系统的多个系统识别基准测试中胜过了最近的方法。