Quality Diversity for Multi-task Optimization
arXiv:2003.04407 · doi:10.1145/3377930.3390203
Abstract
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.
References in corpus (6)
- Robots that can adapt like animals
- Procedural Content Generation through Quality Diversity
- Reset-free Trial-and-Error Learning for Robot Damage Recovery
- Discovering the Elite Hypervolume by Leveraging Interspecies Correlation
- Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted Illumination
- Adaptive Prior Selection for Repertoire-based Online Adaptation in Robotics
Cited by in corpus (10)
- Multi-Objective Quality Diversity Optimization
- Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances
- Entropy-Based Evolutionary Diversity Optimisation for the Traveling Salesperson Problem
- Hierarchical Quality-Diversity for Online Damage Recovery
- Computing Diverse Sets of High Quality TSP Tours by EAX-Based Evolutionary Diversity Optimisation
- Preference-Learning Emitters for Mixed-Initiative Quality-Diversity Algorithms
- Learning to Walk Autonomously via Reset-Free Quality-Diversity
- Parametric-Task MAP-Elites
- Multi-Task Multi-Behavior MAP-Elites
- Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms