Decentralised Emergence of Robust and Adaptive Linguistic Conventions in Populations of Autonomous Agents Grounded in Continuous Worlds

TL;DR

This paper presents a decentralized method for autonomous agents to develop robust, adaptive, and interpretable linguistic conventions grounded in continuous feature spaces, enabling effective communication in dynamic environments.

Contribution

It introduces a novel decentralized approach for emergent linguistic conventions that are robust, adaptable, and grounded in continuous spaces, suitable for autonomous agent populations.

Findings

Converges on effective, human-interpretable conventions

Robust against sensor defects and noise

Adapts to environmental and communicative changes

Abstract

This paper introduces a methodology through which a population of autonomous agents can establish a linguistic convention that enables them to refer to arbitrary entities that they observe in their environment. The linguistic convention emerges in a decentralised manner through local communicative interactions between pairs of agents drawn from the population. The convention consists of symbolic labels (word forms) associated to concept representations (word meanings) that are grounded in a continuous feature space. The concept representations of each agent are individually constructed yet compatible on a communicative level. Through a range of experiments, we show (i) that the methodology enables a population to converge on a communicatively effective, coherent and human-interpretable linguistic convention, (ii) that it is naturally robust against sensor defects in individual agents, (iii) that it can effectively deal with noisy observations, uncalibrated sensors and heteromorphic populations, (iv) that the method is adequate for continual learning, and (v) that the convention self-adapts to changes in the environment and communicative needs of the agents.