Emergence of linguistic conventions in multi-agent reinforcement learning
This work addresses the problem of understanding language emergence for researchers in AI, linguistics, and multi-agent systems, but it is incremental as it builds on existing models to explore network effects.
The study investigated how linguistic conventions emerge in multi-agent reinforcement learning, finding that global consensus with nearly unique object-word mappings occurs on complete or dense random graphs, while finite-dimensional lattices trap the system in disordered configurations unless population renewal is introduced, which restores coarsening and enhances efficient signaling.
Recently, emergence of signaling conventions, among which language is a prime example, draws a considerable interdisciplinary interest ranging from game theory, to robotics to evolutionary linguistics. Such a wide spectrum of research is based on much different assumptions and methodologies, but complexity of the problem precludes formulation of a unifying and commonly accepted explanation. We examine formation of signaling conventions in a framework of a multi-agent reinforcement learning model. When the network of interactions between agents is a complete graph or a sufficiently dense random graph, a global consensus is typically reached with the emerging language being a nearly unique object-word mapping or containing some synonyms and homonyms. On finite-dimensional lattices, the model gets trapped in disordered configurations with a local consensus only. Such a trapping can be avoided by introducing a population renewal, which in the presence of superlinear reinforcement restores an ordinary surface-tension driven coarsening and considerably enhances formation of efficient signaling.