Multi Time Scale World Models

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/MT

Stats

• citations0
• S2 citations—
• github stars17
• HF likes0
• heat score2.51
• arxiv keyshaj2023multi

Code

• ALRhub/MT—

Related papers

• Episodic Memory For Learning Subjective-timescale Models (2020)0.00
• World Models As An Intermediary Between Agents And The Real World (2026)0.00
• Time-aware World Model For Adaptive Prediction And Control (2025)0.00
• MABL: Bi-level Latent-variable World Model For Sample-efficient Multi-agent Reinforcement Learning (2023)0.00
• Decentralized Transformers With Centralized Aggregation Are Sample-efficient Multi-agent World Models (2024)0.00
• Deep Reinforcement Learning With Time-scale Invariant Memory (2024)0.00
• Multi-timescale, Gradient Descent, Temporal Difference Learning With Linear Options (2017)0.00
• Simplifying Latent Dynamics With Softly State-invariant World Models (2024)0.00