Error caused by in-place operation in SAC

[VansWaston]

I met the error as follow:

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [256, 1]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

at line pi_loss.backward(retain_graph = True) :

self.policy_optimizer.zero_grad()
pi_loss.backward(retain_graph = True)
nn.utils.clip_grad_norm_(self.policy_net.parameters(), 0.5)
self.policy_optimizer.step()

after tried using torch.autograd.set_detect_anomaly(True) , the error report is as follows:

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [256, 1]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

does there anyone have met this problem? thank you!