Do deep reinforcement learning agents model intentions?

Our latest paper shows that deep reinforcement learning agents seem to model intentions of other agents in a cooperative task. Also that trained agents tend to overfit to each other and do not generalize to unseen partners. Short read: https://arxiv.org/abs/1805.06020.

Generalization gap video (featuring Sheldon agents!):

Intention reading video:

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>