arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.04407cs.NEcs.RO
收藏

多任务优化的质量多样性

Quality Diversity for Multi-task Optimization

Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Université de Lorraine(洛林大学)

Jean-Baptiste Mouret, Glenn Maguire

摘要:

质量多样性(QD)算法是一个最近的家庭的优化算法,搜索一个大的集合的多样性,但高性能的解决方案。在某些特定情况下,他们可以同时解决多个任务。例如,他们可以找到机器人手臂到达一组点所需的关节位置,这也可以通过为每个目标点运行经典优化器来解决。然而,当需要针对每个任务独立地评估适应度时,它们不能解决多个任务(例如,优化策略以掌握许多不同的对象)。在本文中,我们提出了一个扩展的MAP-Elites算法,称为多任务MAP-Elites,解决多个任务时,适应度函数依赖于任务。我们在模拟的参数化平面臂(10维搜索空间; 5000个任务)和具有不同长度腿的模拟6足式机器人(36维搜索空间; 2000个任务)上对其进行了评估。结果表明,在这两种情况下,我们的算法优于每个任务的优化分别与CMA-ES算法。

英文摘要:

Quality Diversity (QD) algorithms are a recent family of optimization algorithms that search for a large set of diverse but high-performing solutions. In some specific situations, they can solve multiple tasks at once. For instance, they can find the joint positions required for a robotic arm to reach a set of points, which can also be solved by running a classic optimizer for each target point. However, they cannot solve multiple tasks when the fitness needs to be evaluated independently for each task (e.g., optimizing policies to grasp many different objects). In this paper, we propose an extension of the MAP-Elites algorithm, called Multi-task MAP-Elites, that solves multiple tasks when the fitness function depends on the task. We evaluate it on a simulated parameterized planar arm (10-dimensional search space; 5000 tasks) and on a simulated 6-legged robot with legs of different lengths (36-dimensional search space; 2000 tasks). The results show that in both cases our algorithm outperforms the optimization of each task separately with the CMA-ES algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑