Selfish Emergent Communication

Michael Noukhovitch, Travis LaCroix, Aaron Courville

TL;DR: We manage to emerge communication with selfish agents, contrary to the current view in ML

Abstract: Current literature in machine learning holds that unaligned, self-interested agents do not learn to use an emergent communication channel. We introduce a new sender-receiver game to study emergent communication for this spectrum of partially-competitive scenarios and put special care into evaluation. We find that communication can indeed emerge in partially-competitive scenarios, and we discover three things that are tied to improving it. First, that selfish communication is proportional to cooperation, and it naturally occurs for situations that are more cooperative than competitive. Second, that stability and performance are improved by using LOLA (Foerster et al, 2018), especially in more competitive scenarios. And third, that discrete protocols lend themselves better to learning cooperative communication than continuous ones.

Code: https://anonymous.4open.science/r/bb115cbe-1bb8-4c43-bf70-eff6c449db77/

Keywords: multi agent reinforcement learning, emergent communication, game theory