To Populate is To Regulate
This work addresses the challenge of improving emergent communication for AI agents, though it appears incremental as it builds on existing signaling game frameworks.
The paper tackles the problem of generating robust representations from unstructured pixel data by using population-based Lewis signaling games, finding that these outperform single speaker-listener pairs in representation quality.
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.