Visual Hide and Seek. (arXiv:1910.07882v1 [cs.AI])

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: this http URL

Source link

Related posts

Lookup Table-Based Consensus Algorithm for Real-Time Longitudinal Motion Control of Connected and Automated Vehicles. (arXiv:1902.07747v1 [cs.SY])


The WAF backed by artificial intelligence (AI) – Network World


Prediction of HIV-associated neurocognitive disorder (HAND) from three genetic features of envelope gp120 glycoprotein.


This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More

Privacy & Cookies Policy