Evolution of Basic Communication Strategies in Artificial Agents
Communication and signaling processes are ubiquitous in biological organisms, having evolved throughout the evolutionary tree whenever transmission and receiving mechanisms are present. The work presented in this article addresses, from an evolutionary robotics approach, how a basic communication strategy can emerge in artificial agents through the co-evolution of signalers and perceivers. Although there are many works that model the evolution of the communication processes using autonomous robots, the work presented here attempts to tackle the problem using a different approach. Here, the emphasis is put on the perspective of the perceiver, by examining how the meaning of a signal emerges during the evolutionary process starting from a meaningless cue. This leads to effectively changing the behavior of the perceiver whenever the signal is present. All this is achieved without directly codifying any behavior related to perception in the fitness function of the evolutionary algorithm.
Copyright (c) 2021 International Journal of Combinatorial Optimization Problems and Informatics
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.