arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.00478cs.LGcs.AIcs.NEmath.OC
收藏

质量-多样性优化作为多目标优化

Quality-Diversity Optimization as Multi-Objective Optimization

Xi'an Jiaotong University(西安交通大学);City University of Hong Kong(香港城市大学)

Xi Lin, Ping Guo, Yilu Liu, Qingfu Zhang, Jianyong Sun

AI总结:

本文将质量-多样性优化重新表述为多目标优化问题,利用已有的多目标优化方法解决QD问题,并通过实验验证了其性能优势。

摘要:

质量-多样性(QD)优化旨在发现一组同时在用户定义的行为空间中表现出多样化行为的高性能解。这一范式激发了大量研究兴趣,并在机器人控制、创意设计和对抗样本生成等领域展示了实用价值。近年来,各种具有不同设计原则的QD算法已被提出。本文并未提出新的QD算法,而是通过将QD优化重新表述为具有大量优化目标的多目标优化(MOO)问题,引入了一种新的改写方法。通过建立这种联系,我们能够直接采用已建立的MOO方法,特别是基于集合的标量化技术,通过协作搜索过程来解决QD问题。我们进一步提供了理论分析,证明我们的方法继承了MOO的理论保证,并为QD优化提供了有吸引力的属性。在多个QD应用中的实验研究证实,我们的方法在性能上与最先进的QD算法相媲美。

英文摘要:

The Quality-Diversity (QD) optimization aims to discover a collection of high-performing solutions that simultaneously exhibit diverse behaviors within a user-defined behavior space. This paradigm has stimulated significant research interest and demonstrated practical utility in domains including robot control, creative design, and adversarial sample generation. A variety of QD algorithms with distinct design principles have been proposed in recent years. Instead of proposing a new QD algorithm, this work introduces a novel reformulation by casting the QD optimization as a multi-objective optimization (MOO) problem with a huge number of optimization objectives. By establishing this connection, we enable the direct adoption of well-established MOO methods, particularly set-based scalarization techniques, to solve QD problems through a collaborative search process. We further provide a theoretical analysis demonstrating that our approach inherits theoretical guarantees from MOO while providing desirable properties for the QD optimization. Experimental studies across several QD applications confirm that our method achieves performance competitive with state-of-the-art QD algorithms.

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。

↑