Skip to content
Back to skills

Unsupervised Learning Of Temporal Abstractions With Slotbased Transformers

ASecurity

**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 t...

  • 3 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 11, 2026
toolsgo

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill unsupervised-learning-of-temporal-abstractions-with-slotbased-transformers --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Unsupervised Learning Of Temporal Abstractions With Slotbased Transformers?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Unsupervised Learning Of Temporal Abstractions With Slotbased Transformers
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-unsupervised-learning-of-temporal-abstractions-wit/badge)](https://www.skillsdirectory.com/skills/hiyenwong-unsupervised-learning-of-temporal-abstractions-wit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# 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)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.