Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Quality Diversity for Multi-task Optimization

About

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.

Jean-Baptiste Mouret, Glenn Maguire• 2020

Related benchmarks

TaskDatasetResultRank
Control Task Performancecartpole
AUC978.4
4
Control TaskArchery
Final Mean Fitness1
4
Control TaskArm
Final Mean Fitness0.772
4
Control Task PerformanceArm
AUC760.1
4
Control Taskcartpole
Final Mean Fitness994.5
4
Control Task PerformanceArchery
AUC957.2
4
Control Task PerformanceHexapod
AUC450.2
4
Control TaskHexapod
Final Mean Fitness53
4
Showing 8 of 8 rows

Other info

Follow for update