Model-Based Quality-Diversity Search for Efficient Robot Learning
This addresses the challenge of applying QD algorithms in real-world robot manipulation tasks, though it is incremental as it enhances an existing method.
The paper tackles the sample inefficiency of Quality-Diversity (QD) algorithms in robot learning by integrating a neural network to predict behavior and avoid unpromising actions, resulting in improved sample-efficiency and performance in evolutionary processes and skill adaptation.
Despite recent progress in robot learning, it still remains a challenge to program a robot to deal with open-ended object manipulation tasks. One approach that was recently used to autonomously generate a repertoire of diverse skills is a novelty based Quality-Diversity~(QD) algorithm. However, as most evolutionary algorithms, QD suffers from sample-inefficiency and, thus, it is challenging to apply it in real-world scenarios. This paper tackles this problem by integrating a neural network that predicts the behavior of the perturbed parameters into a novelty based QD algorithm. In the proposed Model-based Quality-Diversity search (M-QD), the network is trained concurrently to the repertoire and is used to avoid executing unpromising actions in the novelty search process. Furthermore, it is used to adapt the skills of the final repertoire in order to generalize the skills to different scenarios. Our experiments show that enhancing a QD algorithm with such a forward model improves the sample-efficiency and performance of the evolutionary process and the skill adaptation.