向量量化-精英：无监督和问题无关的质量-多样性优化
Vector Quantized-Elites: Unsupervised and Problem-Agnostic Quality-Diversity Optimization
AI总结：
VQ-Elites通过无监督学习构建结构化行为空间，实现灵活且任务无关的质量-多样性优化。
摘要：
质量-多样性算法通过优先发现多样且高性能的解决方案而非单一最优结果，改变了优化领域。然而，传统质量-多样性方法，如MAP-Elites，依赖于预定义的行为描述符和完整的任务先验知识来定义行为空间网格，限制了其灵活性和适用性。在本工作中，我们引入了向量量化-精英（VQ-Elites），一种新的质量-多样性算法，通过无监督学习自主构建结构化的行为空间网格，消除了对任务特定知识的需求。VQ-Elites的核心是将向量量化变分自编码器整合进来，这使得能够动态学习行为描述符并生成结构化而非无结构的行为空间网格——这在现有无监督质量-多样性方法中是一个重大进步。这种设计使VQ-Elites成为灵活、稳健且任务无关的优化框架。为进一步提高无监督质量-多样性算法的性能，我们引入了行为空间边界和协作机制，显著提高了收敛性和性能，以及有效多样性比率和覆盖多样性分数，两个新的度量标准，用于量化无监督设置中的实际多样性。我们验证了VQ-Elites在机械臂姿态抓取、移动机器人空间覆盖和MiniGrid探索任务上的表现。结果展示了其高效生成多样、高质量解决方案的能力，突显了其适应性、可扩展性、对超参数的鲁棒性以及将其扩展到复杂、此前无法进入的领域的潜力。
英文摘要：
Quality-Diversity algorithms have transformed optimization by prioritizing the discovery of diverse, high-performing solutions over a single optimal result. However, traditional Quality-Diversity methods, such as MAP-Elites, rely heavily on predefined behavior descriptors and complete prior knowledge of the task to define the behavior space grid, limiting their flexibility and applicability. In this work, we introduce Vector Quantized-Elites (VQ-Elites), a novel Quality-Diversity algorithm that autonomously constructs a structured behavior space grid using unsupervised learning, eliminating the need for prior task-specific knowledge. At the core of VQ-Elites is the integration of Vector Quantized Variational Autoencoders, which enables the dynamic learning of behavior descriptors and the generation of a structured, rather than unstructured, behavior space grid -- a significant advancement over existing unsupervised Quality-Diversity approaches. This design establishes VQ-Elites as a flexible, robust, and task-agnostic optimization framework. To further enhance the performance of unsupervised Quality-Diversity algorithms, we introduce behavior space bounding and cooperation mechanisms, which significantly improve convergence and performance, as well as the Effective Diversity Ratio and Coverage Diversity Score, two novel metrics that quantify the actual diversity in the unsupervised setting. We validate VQ-Elites on robotic arm pose-reaching, mobile robot space-covering, and MiniGrid exploration tasks. The results demonstrate its ability to efficiently generate diverse, high-quality solutions, emphasizing its adaptability, scalability, robustness to hyperparameters, and potential to extend Quality-Diversity optimization to complex, previously inaccessible domains.
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。
