# Multi Time Scale World Models

arXiv: https://arxiv.org/abs/2310.18534 · HTML: https://mlsanity.com/paper/2310.18534/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 27 Oct 2023.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https://mlsanity.com/paper/2205.14415/) (2022)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Structured Inference Networks for Nonlinear State Space Models](https://mlsanity.com/paper/1609.09869/) (2016)
- [Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data](https://mlsanity.com/paper/1605.06432/) (2016)
- [Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces](https://mlsanity.com/paper/1905.07357/) (2019)
- [Abstraction for Deep Reinforcement Learning](https://mlsanity.com/paper/2202.05839/) (2022)
- [Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning](https://mlsanity.com/paper/2010.10201/) (2020)
- [Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios](https://mlsanity.com/paper/2206.14697/) (2022)

## Built on by (most cited first, 8 of 8)

- [Four Principles for Physically Interpretable World Models](https://mlsanity.com/paper/2503.02143/) (2025)
- [Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Tracking](https://mlsanity.com/paper/2602.10743/) (2026)
- [Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/2409.16824/) (2024)
- [Time-Aware World Model for Adaptive Prediction and Control](https://mlsanity.com/paper/2506.08441/) (2025)
- [SUNTA: Hierarchical Video Prediction with Surprise-based Chunking](https://mlsanity.com/paper/2607.02087/) (2026)
- [Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity](https://mlsanity.com/paper/2411.01342/) (2024)
- [Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning](https://mlsanity.com/paper/2605.17058/) (2026)
- [MHWA: Multi-timescale Hierarchical World-Action Model](https://mlsanity.com/paper/2610.14727/) (2026)

## Abstract (arXiv)

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.