您好，我在运行7. PPO_Continuous时，结果为：杆子越转越快，根本不会停止。请问您那边运行情况怎么样呢？谢谢！

LiSir-HIT / Reinforcement-Learning

kinds of reinforcement learning model by Pytorch

257 stars 61 forks source link

Open MicroPlusone opened 1 year ago

YanShulinjj commented 9 months ago

No description provided.

兄弟，解决了吗，我咋感觉模型没有学到东西

MicroPlusone commented 9 months ago

是状态数和动作数错了。改一下这两个地方就行。

gaoyang797 commented 7 months ago

怎么改，一头雾水