PaddlePaddle / book

Deep Learning 101 with PaddlePaddle (『飞桨』深度学习框架入门教程)
http://www.paddlepaddle.org/documentation/docs/zh/1.2/beginners_guide/quick_start/index.html
2.73k stars 1.33k forks source link

Advantage Actor-Critic(A2C) #973

Closed EastSmith closed 3 years ago

EastSmith commented 3 years ago

自选题目《Advantage Actor-Critic(A2C)》

TCChenlong commented 3 years ago

有些问题,都已经comments了,辛苦修改下,感谢~

w5688414 commented 3 years ago

把ActorCritic网络画出来,更直观一点

EastSmith commented 3 years ago

1.调整了一些参数,使神经网络的收敛更加稳定和迅速;2.另外绘制了一张简略的ActorCritic模型图。