Unsupervised Learning of Temporal Abstractions with Slot-based Transformers

TL;DR

SloTTAr introduces a parallel Transformer-based method with Slot Attention for unsupervised discovery of temporal sub-routines in reinforcement learning, outperforming existing methods in accuracy and speed.

Contribution

The paper presents SloTTAr, a novel parallel approach combining Transformers and Slot Attention for unsupervised learning of temporal abstractions, allowing adaptive sub-routine discovery.

Findings

Outperforms strong baselines in boundary point discovery

Up to 7x faster training on benchmarks

Effective with variable sub-routine sequences

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.