You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Should the actor update not utilise idx[0] and idx[1] for Q1 and Q2? currently it just gets the same value of Q from the same critic
---------------------------- update actor ----------------------------
if step == self.G-1:
actions_pred, log_prob, _ = self.actor_local.sample(states)
# TODO: make this variable for possible more than two critics
Q1 = self.critics[idx[**0**]](states, actions_pred.squeeze(0)).cpu()
Q2 = self.critics[idx[**0**]](states, actions_pred.squeeze(0)).cpu()
Q = torch.min(Q1,Q2)
The text was updated successfully, but these errors were encountered:
Should the actor update not utilise idx[0] and idx[1] for Q1 and Q2? currently it just gets the same value of Q from the same critic
---------------------------- update actor ----------------------------
The text was updated successfully, but these errors were encountered: