distinguish Qnet and set detach() on TD target

[tlt18]

I found two problems with the Double DQN code.

1. TD target does not have detach(), which is equivalent to not using semi-gradient method;
2. During debugging, I found that the outputs of policy_net and target_net are the same, which is because no they maintain the same network, and target_net changes immediately after policy_net changes.

[johnjim0816]

Thanks for your PR, I will consider you suggestions. But now we are trying to update new template for all algos, thus I cannot merge your PR now. I will add acknowledge of you when update Double DQN