search

MorvanZhou / Reinforcement-learning-with-tensorflow

Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
https://mofanpy.com/tutorials/machine-learning/reinforcement-learning/
MIT License
8.84k stars 5k forks source link

为什么a2c与a3c实现中actor的learning rate比critic的learning rate小？ #177

Closed Hins closed 4 years ago

Hins commented 4 years ago

是根据实验效果调的吗？

MorvanZhou commented 4 years ago

是的，你也可以根据自己的实验方案来调整这些参数

Hins commented 4 years ago

感谢回复，请问除了调learning rate之外，您还有其它经验，用于平衡actor收敛效果与critic收敛效果吗？我在实验中会经常遇到actor与critic收敛情况不均衡问题