Rat big, cat eaten! Ideas for a useful deep-agent protolanguage

03/17/2020
by   Marco Baroni, et al.
0

Deep-agent communities developing their own language-like communication protocol are a hot (or at least warm) topic in AI. Such agents could be very useful in machine-machine and human-machine interaction scenarios long before they have evolved a protocol as complex as human language. Here, I propose a small set of priorities we should focus on, if we want to get as fast as possible to a stage where deep agents speak a useful protolanguage.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/28/2019

Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances

Recent research studies communication emergence in communities of deep n...
research
03/03/2014

Extending Agents by Transmitting Protocols in Open Systems

Agents in an open system communicate using interaction protocols. Suppos...
research
12/29/2020

Modeling Social Interaction for Baby in Simulated Environment for Developmental Robotics

Task-specific AI agents are showing remarkable performance across differ...
research
06/03/2020

Emergent Multi-Agent Communication in the Deep Learning Era

The ability to cooperate through language is a defining feature of human...
research
05/02/2018

AI safety via debate

To make AI systems broadly useful for challenging real-world tasks, we n...
research
01/25/2019

Emergent Linguistic Phenomena in Multi-Agent Communication Games

In this work, we propose a computational framework in which agents equip...
research
09/01/2020

AI solutions for drafting in Magic: the Gathering

Drafting in Magic: the Gathering is a sub-game of a larger trading card ...

Please sign up or login with your details

Forgot password? Click here to reset