© 1999-2048 dssz.net 粤ICP备11031372号
[算法与数据结构] DiCE: The Infinitely Differentiable Monte Carlo Estimator
说明: The score function estimator is widely used for estimating gradients of stochastic objectives in Stochastic Computation Graphs (SCG), e.g., in reinforcement learning and meta-learning. While deriving the first order gradient estimators by differenti<peter_wwhe> 上传 | 大小:419kb