Visual Hide and Seek

V ISUAL HIDE AND SEEK Boyuan Chen Columbia University Shuran Song Columbia University Hod Lipson Columbia University Carl V ondrick Columbia University A BSTRACT 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/ We designed this game to mimic the typical dynamics between predator and prey. For example, we place a variety of obstacles inside the environment, which create occlusions that the agent can leverage to hide behind. We also only give the agents access to the first-person perspective of their three-dimensional environment. Consequently, this task is a substantial challenge for reinforcement learning because the state is both visual (pixel input) and partially observable (due to occlusions).