质量-多样性算法可被证明对优化有帮助
Quality-Diversity Algorithms Can Provably Be Helpful for Optimization
AI总结:
本文通过运行时间分析证明,在单调近似子模最大化和集合覆盖两类 NP 难问题上,质量-多样性算法 MAP-Elites 可达渐近最优多项式近似比,而传统 $(\mu+1)$-EA 在某些实例上需指数时间,从而为 QD 算法有助于优化提供了理论依据。
摘要:
质量-多样性(Quality-Diversity, QD)算法是一类新型的进化算法(Evolutionary Algorithms, EAs),旨在找到一组高性能且多样化的解。它们在强化学习和机器人学中已有许多成功应用,有助于提升复杂环境下的鲁棒性。此外,与传统上显式搜索单一最高性能解的搜索算法相比,QD 算法在经验上往往能找到更好的整体解。然而,其理论分析远远滞后,许多基本问题尚未被探索。本文尝试通过严格的运行时间分析来揭示 QD 算法的优化能力。通过将流行的 QD 算法 MAP-Elites 与 $(\mu+1)$-EA(一种仅专注于寻找更好目标值的典型 EA)进行比较,我们证明在两类具有广泛应用的 NP 难问题上,即带规模约束的单调近似子模最大化问题和集合覆盖问题,MAP-Elites 能够达到(渐近)最优的多项式时间近似比,而 $(\mu+1)$-EA 在某些实例上需要指数级期望时间。这为 QD 算法有助于优化提供了理论依据,并揭示了同时搜索具有多样行为的高性能解可以为获得良好整体解提供垫脚石,并有助于避免局部最优。
英文摘要:
Quality-Diversity (QD) algorithms are a new type of Evolutionary Algorithms (EAs), aiming to find a set of high-performing, yet diverse solutions. They have found many successful applications in reinforcement learning and robotics, helping improve the robustness in complex environments. Furthermore, they often empirically find a better overall solution than traditional search algorithms which explicitly search for a single highest-performing solution. However, their theoretical analysis is far behind, leaving many fundamental questions unexplored. In this paper, we try to shed some light on the optimization ability of QD algorithms via rigorous running time analysis. By comparing the popular QD algorithm MAP-Elites with $(μ+1)$-EA (a typical EA focusing on finding better objective values only), we prove that on two NP-hard problem classes with wide applications, i.e., monotone approximately submodular maximization with a size constraint, and set cover, MAP-Elites can achieve the (asymptotically) optimal polynomial-time approximation ratio, while $(μ+1)$-EA requires exponential expected time on some instances. This provides theoretical justification for that QD algorithms can be helpful for optimization, and discloses that the simultaneous search for high-performing solutions with diverse behaviors can provide stepping stones to good overall solutions and help avoid local optima.
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。