Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies
固定预算噪声进化策略中深度优先于保真度
机构 * University of California, Berkeley(加州大学伯克利分校)
AI总结 针对固定评估预算下的噪声进化策略,提出概率精英成员(PEM)方法,通过条件期望秩权重替代硬秩权重,实现Rao-Blackwell化降噪,在COCO基准和RL等任务中取得一致提升。
Comments Accepted at the 43rd International Conference on Machine Learning (ICML 2026). 28 pages, 16 figures, 7 tables, including appendices