# To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments

arXiv: https://arxiv.org/abs/1907.11770 · HTML: https://mlsanity.com/paper/1907.11770/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [Zero-shot object goal visual navigation](https://mlsanity.com/paper/2206.07423/) (2022)
- [Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation](https://mlsanity.com/paper/2107.06011/) (2021)
- [Modality-invariant Visual Odometry for Embodied Vision](https://mlsanity.com/paper/2305.00348/) (2023)
- [Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision](https://mlsanity.com/paper/2207.01136/) (2022)
- [Good Actions Succeed, Bad Actions Generalize: A Case Study on Why RL Generalizes Better](https://mlsanity.com/paper/2503.15693/) (2025)

## Abstract (arXiv)

In this paper we compare learning-based methods and classical methods for navigation in virtual environments. We construct classical navigation agents and demonstrate that they outperform state-of-the-art learning-based agents on two standard benchmarks: MINOS and Stanford Large-Scale 3D Indoor Spaces. We perform detailed analysis to study the strengths and weaknesses of learned agents and classical agents, as well as how characteristics of the virtual environment impact navigation performance. Our results show that learned agents have inferior collision avoidance and memory management, but are superior in handling ambiguity and noise. These results can inform future design of navigation agents.