5篇文章 · 1000字 · 5人关注
-
阅读 2017-5-30
【解读】通过拳击学习生成对抗网络（GAN）的基本原理 ICML 2017 | Curiosity-driven 这个马里奥大叔也有很多哥哥姐姐啦...
-
Reinforcement Learning An Introduction book 2015file:///D:/搜狗高速下载/Reinforcement Learning An Introduction book2015oct.pd...
-
连续空间的递归最小二乘行动者—评论家算法2 RLSAC 算法 Policy Gradient Methods for Reinforcement Learning with Fun...
-
An Actor-Critic Algorithm for Sequence PredictionRecurrent neural networks RNNs for sequence prediction In our models, th...
-
A Survey of Actor-Critic Reinforcement Learning Standard and Natural Policy GradientsThe stochastic process to be controlled is described by the state transi...
文集作者
