floodsung / DDPG

Reimplementation of DDPG(Continuous Control with Deep Reinforcement Learning) based on OpenAI Gym + Tensorflow
MIT License
555 stars 178 forks source link

mistake found #5

Open fangthu opened 7 years ago

fangthu commented 7 years ago

hi, thank you for you job. It is very helpful and easy to understand!

But it seems there's a mistake in 'filter_env.py'

The line 'ac_f = np.clip(self.filter_action(action),self.action_space.low,self.action_space.high)'

All the actions are constrained to '-1 to 1' instead of the real inputs.

And another question is : have you ever used XX_bn as the networks ?

In my situation, the result is worse. I do not know it is normal of not .

Best