# Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks

arXiv: https://arxiv.org/abs/2402.12067 · HTML: https://mlsanity.com/paper/2402.12067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Builds on (most cited first, 10 of 10)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [Cognitive Mapping and Planning for Visual Navigation](https://mlsanity.com/paper/1702.03920/) (2017)
- [Visual Representations for Semantic Target Driven Navigation](https://mlsanity.com/paper/1805.06066/) (2018)
- [Auxiliary Tasks and Exploration Enable ObjectNav](https://mlsanity.com/paper/2104.04112/) (2021)
- [Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents](https://mlsanity.com/paper/2009.03231/) (2020)
- [Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening](https://mlsanity.com/paper/1808.08833/) (2018)
- [Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison](https://mlsanity.com/paper/2310.04241/) (2023)

## Abstract (arXiv)

Visual navigation requires a whole range of capabilities. A crucial one of these is the ability of an agent to determine its own location and heading in an environment. Prior works commonly assume this information as given, or use methods which lack a suitable inductive bias and accumulate error over time. In this work, we show how the method of slow feature analysis (SFA), inspired by neuroscience research, overcomes both limitations by generating interpretable representations of visual data that encode location and heading of an agent. We employ SFA in a modern reinforcement learning context, analyse and compare representations and illustrate where hierarchical SFA can outperform other feature extractors on navigation tasks.