Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
Abstract
Hierarchical world models can significantly improve model-based reinforcement learning (MBRL) and planning by enabling reasoning across multiple time scales. Nonetheless, the majority of state-of-the-art MBRL methods employ flat, non-hierarchical models. We propose Temporal Hierarchies from Invariant Context Kernels (THICK), an algorithm that learns a world model hierarchy via discrete latent dynamics. The lower level of THICK updates parts of its latent state sparsely in time, forming invariant contexts. The higher level exclusively predicts situations involving context changes. Our experiments demonstrate that THICK learns categorical, interpretable, temporal abstractions on the high level, while maintaining precise low-level predictions. Furthermore, we show that the emergent hierarchical predictive model seamlessly enhances the abilities of MBRL or planning methods. We believe that THICK contributes to the further development of hierarchical agents capable of more sophisticated planning and reasoning abilities.
Cite
Text
Gumbsch et al. "Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics." International Conference on Learning Representations, 2024.Markdown
[Gumbsch et al. "Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics." International Conference on Learning Representations, 2024.](https://mlanthology.org/iclr/2024/gumbsch2024iclr-learning/)BibTeX
@inproceedings{gumbsch2024iclr-learning,
title = {{Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics}},
author = {Gumbsch, Christian and Sajid, Noor and Martius, Georg and Butz, Martin V.},
booktitle = {International Conference on Learning Representations},
year = {2024},
url = {https://mlanthology.org/iclr/2024/gumbsch2024iclr-learning/}
}