Reinforcement-learning-with-tensorflow icon indicating copy to clipboard operation
Reinforcement-learning-with-tensorflow copied to clipboard

Published 20 hours ago • verified publisher icon MorvanZhou

DDPG——当动作为取值范围不同的二维情况应该怎么解决呢？

Open Tonywangrui opened this issue 5 years ago • 0 comments

在我研究的问题中，agent的动作包含两个维度，且两个维度的取值范围不一样，请问怎么解决这个问题呢，谢谢各位的回答先！

Tonywangrui avatar Jun 09 '20 16:06 Tonywangrui