NaturalShower

我在actor和critic的learn()上瞎改一通后能跑了 def learn(self, s, a, td): s = torch.Tensor(s[np.newaxis, :]) acts_prob = self.actor_net(s) log_prob = torch.log(acts_prob[0, a]) with torch.no_grad(): exp_v = torch.mean(log_prob * td loss = -exp_v torch.autograd.set_detect_anomaly(True) loss.requires_grad_(True) self.optimizer.zero_grad()...