Unsupervised Learning Of Temporal Abstractions With Slotbased Transformers

# Unsupervised Learning of Temporal Abstractions with Slot-based Transformers

**arXiv ID:** 2203.13573
**Authors:** Anand Gopalakrishnan, Kazuki Irie, Jürgen Schmidhuber, Sjoerd van Steenkiste
**Published:** 2022-03-25T10:59:46Z
**Abstract:**
The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstractions in a purely unsupervised fashion through observing state-action trajectories gathered from executing a policy. However, a current limitation is that they process each trajectory in an entirely sequential manner, which prevents them from revising earlier decisions about sub-routine boundary points in light of new incoming information. In this work we propose SloTTAr, a fully parallel approach that integrates sequence processing Transformers with a Slot Attention module and adaptive computation for learning about the number of such sub-routines in an unsupervised fashion. We demonstrate how SloTTAr is capable of outperforming strong baselines in terms of boundary point discovery, even for sequences containing variable amounts of sub-routines, while being up to 7x faster to train on existing benchmarks.

## Skill Description

This skill is generated from the arXiv paper: Unsupervised Learning of Temporal Abstractions with Slot-based Transformers (2203.13573).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2203.13573](http://arxiv.org/abs/2203.13573v2)