Darwinian embodied evolution of the learning ability for survival

摘要

In this article we propose a framework for performing embodied evolution with a limited number of robots, by utilizing time-sharing in subpopulations of virtual agents hosted in each robot. Within this framework, we explore the combination of within-generation learning of basic survival behaviors by reinforcement learning, and evolutionary adaptations over the generations of the basic behavior selection policy, the reward functions, and meta-parameters for reinforcement learning. We apply a biologically inspired selection scheme, in which there is no explicit communication of the individuals' fitness information. The individuals can only reproduce offspring by mating-a pair-wise exchange of genotypes-and the probability that an individual reproduces offspring in its own subpopulation is dependent on the individual's "health," that is, energy level, at the mating occasion. We validate the proposed method by comparing it with evolution using standard centralized selection, in simulation, and by transferring the obtained solutions to hardware using two real robots.