BriefGPT.xyz
Jun, 2019
生成对抗网络是人工好奇心的特殊案例（1990），也与可预测性最小化（1991）密切相关
Unsupervised Minimax: Adversarial Curiosity, Generative Adversarial Networks, and Predictability Minimization
HTML
PDF
Juergen Schmidhuber
TL;DR
本文回顾了在博弈理论设置下，无监督或自监督神经网络玩极小化游戏的方法，包括基于AC的两个网络、GANs和PM，并更正了一项先前发表的PM不是基于极小化游戏的错误说法。
Abstract
generative adversarial networks
(GANs) learn to model data distributions through two unsupervised
neural networks
, each minimizing the objective function maximized by the other. We relate this game theoretic stra
→