BriefGPT.xyz
Jun, 2020
AR-DAE: 基于无偏神经熵梯度估计的研究
AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation
HTML
PDF
Jae Hyun Lim, Aaron Courville, Christopher Pal, Chin-Wei Huang
TL;DR
该论文介绍了一种名为AR-DAE的方法，利用其逼近概率密度函数的梯度来估计熵的梯度，并通过该方法在密度估计和连续控制问题中实现了最先进的性能。
Abstract
entropy
is ubiquitous in
machine learning
, but it is in general intractable to compute the
entropy
of the distribution of an arbitrary con
→