动态算法配置的理论启发参数控制基准
Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration
摘要：
长期以来，人们已经观察到，进化算法和其他随机搜索算法的性能可以受益于引导其优化行为的参数的非静态选择。因此，动态（“参数控制”）或通过专门的训练过程（“动态算法配置”）识别合适配置的机制是现代演化计算框架的重要组成部分。有几种方法可以解决动态参数设置问题，但我们几乎不知道哪种方法更适合于哪种应用。在经典的基准测试中，具有已知基础事实的问题集合可以在这种情况下提供非常有意义的见解。不幸的是，具有良好理解的控制策略的设置非常罕见。我们知道哪些参数设置最小化预期运行时间的少数例外之一是LeadingOnes问题。我们通过分析最优控制策略来扩展这个基准，该策略只能从给定的可能值组合中选择参数。这也允许我们计算给定规模的最优参数投资组合。我们通过分析DDQN强化学习方法在动态算法配置中的行为来证明我们的基准测试的有用性。
英文摘要：
It has long been observed that the performance of evolutionary algorithms and other randomized search heuristics can benefit from a non-static choice of the parameters that steer their optimization behavior. Mechanisms that identify suitable configurations on the fly ("parameter control") or via a dedicated training process ("dynamic algorithm configuration") are therefore an important component of modern evolutionary computation frameworks. Several approaches to address the dynamic parameter setting problem exist, but we barely understand which ones to prefer for which applications. As in classical benchmarking, problem collections with a known ground truth can offer very meaningful insights in this context. Unfortunately, settings with well-understood control policies are very rare. One of the few exceptions for which we know which parameter settings minimize the expected runtime is the LeadingOnes problem. We extend this benchmark by analyzing optimal control policies that can select the parameters only from a given portfolio of possible values. This also allows us to compute optimal parameter portfolios of a given size. We demonstrate the usefulness of our benchmarks by analyzing the behavior of the DDQN reinforcement learning approach for dynamic algorithm configuration.
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。
