Effects of encodings and quality-diversity on evolving 2D virtual creatures
Effects of encodings and quality-diversity on evolving 2D virtual creatures
复制标题
编码和质量多样性对不断进化的 2D 虚拟生物的影响
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
K. Glette
中科院分区：
文献类型：
--
作者：
Frank Veenstra;Martin Herring Olsen;K. Glette
如何联合优化形态和控制器是进化机器人研究中的一个具有挑战性的问题。由于搜索空间很大，采用了质量多样性算法和编码类型相结合的方法来更有效地搜索解空间。在这里，我们比较了表型精英的多维档案(MAP-精英)和标准进化算法，以及使用直接编码和间接编码的效果。结果表明，MAP-Elites算法找到了不同的解，但编码方式造成了较大的性能差异。这表明，对于有效地创建机器人，表示至少与优化方法一样重要。
How to jointly optimize the morphology and controller is a challenging problem in evolutionary robotics. Due to the large search space, both quality diversity algorithms and types of encodings have been employed to search the solution space more effectively. Here we compare Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) and a standard evolutionary algorithm as well as the effect of using a direct versus an indirect encoding. The results showed that the MAP-Elites algorithm found diverse solutions, yet the encodings accounted for a larger performance discrepancy. This indicates that the representation is at least as important as the optimization method for effectively creating robots.