Emergence of linguistic conventions in multi-agent reinforcement learning

Abstract

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.

18 pages, PLOS ONE (accepted)

References in corpus (8)

• Statistical physics of social dynamics
• A survey of random processes with reinforcement
• Sharp transition towards shared vocabularies in multi-agent systems
• Consensus formation on adaptive networks
• The Emergence of Consensus: A Primer
• Effective surface-tension in the noise-reduced voter model
• Algebraic coarsening in voter models with intermediate states
• Language competition in a population of migrating agents

Cited by in corpus (5)

• A Bayesian Approach to the Naming Game Model
• Emergent Language: A Survey and Taxonomy
• Collective patterns and stable misunderstandings in networks striving for consensus without a common value system
• Stability and evolution of synonyms and homonyms in signaling game
• Evolution toward linguistic coherence in naming game with migrating agents