diff --git a/baselines/her/ddpg.py b/baselines/her/ddpg.py index 96384da..91e91f3 100644 --- a/baselines/her/ddpg.py +++ b/baselines/her/ddpg.py @@ -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)