Disentangled (Un)Controllable Features
Abstract
In the context of MDPs with high-dimensional states, downstream tasks are predominantly applied on a compressed, low-dimensional representation of the original input space. A variety of learning objectives have therefore been used to attain useful representations. However, these representations usually lack interpretability of the different features. We present a novel approach that is able to disentangle latent features into a controllable and an uncontrollable partition. We illustrate that the resulting partitioned representations are easily interpretable on three types of environments and show that, in a distribution of procedurally generated maze environments, it is feasible to interpretably employ a planning algorithm in the isolated controllable latent partition.
Cite
@article{arxiv.2211.00086,
title = {Disentangled (Un)Controllable Features},
author = {Jacob E. Kooi and Mark Hoogendoorn and Vincent François-Lavet},
journal= {arXiv preprint arXiv:2211.00086},
year = {2024}
}
Comments
14 pages (8 main paper pages), 15 figures