Creating Interactive Agents with Imitation Learning

      We show that imitation learning of human-human interactions in a simulated world, in conjunction with self-supervised learning, is sufficient to produce a multimodal interactive agent, which we call MIA, that successfully interacts with non-adversarial humans 75% of the time. We further identify architectural and algorithmic techniques that improve performance, such as hierarchical action selection. Read More Google DeepMind Blog 

​  


Posted

in

by

Tags:

Comments

Leave a Reply

Your email address will not be published.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