a little change in ddpg.py

[kxxwz]

volatile was removed and now has no effect. Use with torch.no_grad(): instead.

[songanz]

I want to know, in the original version, the author set the next_q_values.volatile=False, and then do value_loss = criterion(q_batch, target_q_batch) value_loss.backward() So, in the original version, is he trying to do the backward() on both the target critic network and the critic network?

[kxxwz]

I want to know, in the original version, the author set the next_q_values.volatile=False, and then do value_loss = criterion(q_batch, target_q_batch) value_loss.backward() So, in the original version, is he trying to do the backward() on both the target critic network and the critic network?

I don't think the target networks will be updated by policy gradient.