University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Emergent Multi-Agent Communication: The story so far

Emergent Multi-Agent Communication: The story so far

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Mateja Jamnik.

Communication and coordination are central to the distinct effectiveness of humans. As the capabilities of artificial neural networks increase, researchers are studying whether these models can also learn to communicate and interact with the purpose of achieving a shared goal. In this talk, I review emergent communication studies starting from their pre-deep learning roots in game theory and philosophy of language. Next, I will talk about the most recent research at the intersection of modern multi-agent reinforcement learning and emergent languages. I will conclude with discussing open questions related to language compositionality.

Slides: https://www.dropbox.com/s/zb4wuz7ltcxcy9n/EmCom_ASlowik.pdf?dl=0

ONLINE link.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity