We propose Multi-Task Multi-Behavior MAP-Elites, a variant of MAP-Elites that finds a large number of high-quality solutions for a large set of tasks (optimization problems from a given family). It combines the original MAP-Elites for the search for diversity and Multi-Task MAP-Elites for leveraging similarity between tasks. It performs better than three baselines on a humanoid fault-recovery set of tasks, solving more tasks and finding twice as many solutions per solved task.

翻译：我们提出了多任务多行为MAP-Elites，这是MAP-Elites的一种变体，能够针对一大组任务（来自给定系列的优化问题）找到大量高质量解。它结合了原始MAP-Elites的多样性搜索与多任务MAP-Elites的任务间相似性利用。在仿人机器人故障恢复任务集上，该方法的性能优于三种基线方法，解决了更多任务，并且每个已解决任务找到的解数量是基线的两倍。