gaspersic/baselines
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Removed code that prevented changes to actor loss when training with demos (#740)

Browse Source
This commit is contained in:
Timothy Lee
2018-11-29 20:28:09 -05:00
committed by pzhokhov
parent f3a5abaeeb
commit 146bbf886b
1 changed files with 0 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
baselines/her/ddpg.py
View File

@@ -367,8 +367,6 @@ class DDPG(object):
self.pi_loss_tf = -tf.reduce_mean(self.main.Q_pi_tf)
self.pi_loss_tf += self.action_l2 * tf.reduce_mean(tf.square(self.main.pi_tf / self.max_u))
self.pi_loss_tf = -tf.reduce_mean(self.main.Q_pi_tf)
self.pi_loss_tf += self.action_l2 * tf.reduce_mean(tf.square(self.main.pi_tf / self.max_u))
Q_grads_tf = tf.gradients(self.Q_loss_tf, self._vars('main/Q'))
pi_grads_tf = tf.gradients(self.pi_loss_tf, self._vars('main/pi'))
assert len(self._vars('main/Q')) == len(Q_grads_tf)