- TL;DR: We train an agent to hide from a predator, and experiments suggest useful representations emerge.
- Abstract: 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 without any prior knowledge of its visual world, experiments and visualizations show that a representation of other agents automatically emerges in the learned representation. 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 useful features to emerge in the representation.
- Keywords: Embodied Learning, Self-supervised Learning, Reinforcement Learning
- Original Pdf: pdf