Kevin Yang, Tianjun Zhang, Yuandong Tian, Dan Klein
Summary Search/path planning is an important topic with applications to a variety of other domains, e.g., RL, robotics, chemistry, compiler optimization. However, random search is too inefficient for many applications. Classic global approaches such as Bayesian Optimization may struggle with high-dimensional spaces and smaller numbers of samples. Local approaches such as CEM and CMA-ES may struggle to escape local optima. We propose to explore and partition the search...