论文标题
锥：凸自然进化策略
CoNES: Convex Natural Evolutionary Strategies
论文作者
论文摘要
我们提出了一种新颖的算法 - 凸自然进化策略（锥体），用于通过利用凸优化和信息几何形状的工具来优化高维黑框函数。锥体被配制为有效溶解的凸面程序，可适应进化策略（ES）梯度估计以促进快速收敛。所得算法对于信念分布的参数化是不变的。我们的数值结果表明，在用于基准BlackBox优化器的一系列功能上，锥体的表现远胜于常规的黑框优化方法。此外，锥体证明了与传统的黑框方法相比，在选择运动的Mujoco增强学习任务上，收敛的速度更快。
We present a novel algorithm -- convex natural evolutionary strategies (CoNES) -- for optimizing high-dimensional blackbox functions by leveraging tools from convex optimization and information geometry. CoNES is formulated as an efficiently-solvable convex program that adapts the evolutionary strategies (ES) gradient estimate to promote rapid convergence. The resulting algorithm is invariant to the parameterization of the belief distribution. Our numerical results demonstrate that CoNES vastly outperforms conventional blackbox optimization methods on a suite of functions used for benchmarking blackbox optimizers. Furthermore, CoNES demonstrates the ability to converge faster than conventional blackbox methods on a selection of OpenAI's MuJoCo reinforcement learning tasks for locomotion.
