# Disentangling Controllable and Uncontrollable Factors of Variation by Interacting with the World

arXiv: https://arxiv.org/abs/1804.06955 · HTML: https://mlsanity.com/paper/1804.06955/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2018.

## Built on by (most cited first, 3 of 3)

- [A Complexity-Based Theory of Compositionality](https://mlsanity.com/paper/2410.14817/) (2024)
- [Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection](https://mlsanity.com/paper/2608.06706/) (2026)
- [Open Problem: Active Representation Learning](https://mlsanity.com/paper/2406.03845/) (2024)

## Abstract (arXiv)

We introduce a method to disentangle controllable and uncontrollable factors of variation by interacting with the world. Disentanglement leads to good representations and is important when applying deep neural networks (DNNs) in fields where explanations are required. This study attempts to improve an existing reinforcement learning (RL) approach to disentangle controllable and uncontrollable factors of variation, because the method lacks a mechanism to represent uncontrollable obstacles. To address this problem, we train two DNNs simultaneously: one that represents the controllable object and another that represents uncontrollable obstacles. For stable training, we applied a pretraining approach using a model robust against uncontrollable obstacles. Simulation experiments demonstrate that the proposed model can disentangle independently controllable and uncontrollable factors without annotated data.