Multi Time Scale World Models

Vaisakh Shaj, Saleh GHOLAM ZADEH, Ozan Demir, Luiz Ricardo Douat, Gerhard Neumann

Keywords: Hierarchical Models; Multi Time Scale Learning; World Models

TL;DR: Propose a principled framework for learing world models at multiple time scales/temporal abstractions.

Abstract:

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. Code is available at this repository:
https://github.com/ALRhub/MTS3.

Submission Number: 11430