To Populate is To Regulate

11/06/2019
by   Nicole Fitzgerald, et al.
0

We examine the effects of instantiating Lewis signaling games within a population of speaker and listener agents with the aim of producing a set of general and robust representations of unstructured pixel data. Preliminary experiments suggest that the set of representations associated with languages generated within a population outperform those generated between a single speaker-listener pair on this objective, making a case for the adoption of population-based approaches in emergent communication studies. Furthermore, post-hoc analysis reveals that population-based learning induces a number of novel factors to the conventional emergent communication setup, inviting a wide range of future research questions regarding communication dynamics and the flow of information within them.

READ FULL TEXT
research
04/27/2022

On the role of population heterogeneity in emergent communication

Populations have often been perceived as a structuring component for lan...
research
10/10/2019

Modeling Conceptual Understanding in Image Reference Games

An agent who interacts with a wide population of other agents needs to b...
research
09/20/2021

Learning to Improve Representations by Communicating About Perspectives

Effective latent representations need to capture abstract features of th...
research
02/10/2020

An empirical analysis of information encoded in disentangled neural speaker representations

The primary characteristic of robust speaker representations is that the...
research
02/26/2019

Population protocols with unreliable communication

Population protocols are a model of distributed computation intended for...
research
06/17/2022

Fast Population-Based Reinforcement Learning on a Single Machine

Training populations of agents has demonstrated great promise in Reinfor...

Please sign up or login with your details

Forgot password? Click here to reset