Normalize actor gradients?

[panjiangwei]

This gradient for actor needs to be normalized over batch_size?

DDPG/actor_network_bn.py

Line 37 in 18825ee

self.parameters_gradients = tf.gradients(self.action_output,self.net,-self.q_gradient_input)

[j314erre]

I have the same question, since I've seen implementations that normalize these gradients. However, if batch size is always the same constant, then it doesn't matter that much and you can just adjust the learning rate, right?