search

madvn / DDPG

Deep Deterministic Policy Gradients in TF r2.0
13 stars 2 forks source link

About the result #4

Closed Jian-Yin-Shine closed 4 years ago

Jian-Yin-Shine commented 4 years ago

Hello, I found that the final result of this code is not very good. Can you do better?

madvn commented 4 years ago

You might have to tune the hyperparameters - network size, learning rates, noise parameters etc.