# Visual Hide and Seek

arXiv: https://arxiv.org/abs/1910.07882 · HTML: https://mlsanity.com/paper/1910.07882/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2019.

## Built on by (most cited first, 13 of 13)

- [Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots](https://mlsanity.com/paper/2310.13724/) (2023)
- [An Unbiased Look at Datasets for Visuo-Motor Pre-Training](https://mlsanity.com/paper/2310.09289/) (2023)
- [GridToPix: Training Embodied Agents with Minimal Supervision](https://mlsanity.com/paper/2105.00931/) (2021)
- [Adaptive Coordination in Social Embodied Rearrangement](https://mlsanity.com/paper/2306.00087/) (2023)
- [CREW: Facilitating Human-AI Teaming Research](https://mlsanity.com/paper/2408.00170/) (2024)
- [Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge](https://mlsanity.com/paper/2109.09531/) (2021)
- [Reinforcement learning for pursuit and evasion of microswimmers at low Reynolds number](https://mlsanity.com/paper/2106.08609/) (2021)
- [LEMMA: Learning Language-Conditioned Multi-Robot Manipulation](https://mlsanity.com/paper/2308.00937/) (2023)
- [CREW-WILDFIRE: Benchmarking Agentic Multi-Agent Collaborations at Scale](https://mlsanity.com/paper/2507.05178/) (2025)
- [Visual Perspective Taking for Opponent Behavior Modeling](https://mlsanity.com/paper/2105.05145/) (2021)
- [Enabling Multi-Robot Collaboration from Single-Human Guidance](https://mlsanity.com/paper/2409.19831/) (2024)
- [GUIDE: Real-Time Human-Shaped Agents](https://mlsanity.com/paper/2410.15181/) (2024)
- [Visual design intuition: Predicting dynamic properties of beams from raw cross-section images](https://mlsanity.com/paper/2111.09701/) (2021)

## Abstract (arXiv)

We train embodied agents to play Visual Hide and Seek where a prey must navigate in a simulated environment in order to avoid capture from a predator. We place a variety of obstacles in the environment for the prey to hide behind, and we only give the agents partial observations of their environment using an egocentric perspective. Although we train the model to play this game from scratch, experiments and visualizations suggest that the agent learns to predict its own visibility in the environment. Furthermore, we quantitatively analyze how agent weaknesses, such as slower speed, effect the learned policy. Our results suggest that, although agent weaknesses make the learning problem more challenging, they also cause more useful features to be learned. Our project website is available at: http://www.cs.columbia.edu/ ~bchen/visualhideseek/.