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

Log in

University Account

External (via Google)

Information on

Subscribing to talks details

Finding a talk details

Adding a talk details

Disseminating talks details

Help and Documentation details

Emergent Multi-Agent Communication: The story so far

Download to your calendar using vCal

Agnieszka Slowik (University of Cambridge)
Tuesday 30 June 2020, 13:15-14:15
Online on Teams.

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.