论文标题
一个多代理的进化机器人框架，用于训练尖峰神经网络
A multi-agent evolutionary robotics framework to train spiking neural networks
论文作者
论文摘要
训练尖峰神经网络（SNN），证明了一个新型的基于多机构进化机器人技术（ER）的框架，灵感来自自然界的竞争进化环境。在ER环境中控制的SNN人群的重量以及它们控制的机器人的形态参数被视为表型。该框架的规则根据在竞争环境中捕获食物的功效，选择某些机器人及其SNN进行繁殖，而其他机器人则取消。尽管机器人及其SNN没有明确的奖励以通过任何损失功能生存或繁殖，但这些驱动器随着它们发展以狩猎食物并在这些规则中生存而隐含地出现。它们在捕获食物作为世代相传的效率表现出均衡状态的进化特征。证明了表型上的两种进化遗传算法，突变和突变的交叉。使用每种算法的100个实验的集合比较这些算法的性能。我们发现，突变的跨界比单纯的突变促进了40％的学习速度。
A novel multi-agent evolutionary robotics (ER) based framework, inspired by competitive evolutionary environments in nature, is demonstrated for training Spiking Neural Networks (SNN). The weights of a population of SNNs along with morphological parameters of bots they control in the ER environment are treated as phenotypes. Rules of the framework select certain bots and their SNNs for reproduction and others for elimination based on their efficacy in capturing food in a competitive environment. While the bots and their SNNs are given no explicit reward to survive or reproduce via any loss function, these drives emerge implicitly as they evolve to hunt food and survive within these rules. Their efficiency in capturing food as a function of generations exhibit the evolutionary signature of punctuated equilibria. Two evolutionary inheritance algorithms on the phenotypes, Mutation and Crossover with Mutation, are demonstrated. Performances of these algorithms are compared using ensembles of 100 experiments for each algorithm. We find that Crossover with Mutation promotes 40% faster learning in the SNN than mere Mutation with a statistically significant margin.
