Error: one of the variables needed for gradient computation has been modified by an inplace operation

Question

我正在为我的一个项目使用可用的 Soft Actor-Critic 实现 here。但是当我尝试运行它时，出现以下错误：

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [256, 1]], which is output 0 of TBackward, is at version 3; expected version 2 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

错误是由sac.py文件中的梯度计算引起的。我看不到可能就地进行的操作。有帮助吗？

回溯：

Traceback (most recent call last)
<ipython-input-10-c124add9a61d> in <module>()
     22             for i in range(updates_per_step):
     23                 # Update parameters of all the networks
---> 24                 critic_1_loss, critic_2_loss, policy_loss, ent_loss, alpha = agent.update_parameters(memory, batch_size, updates)
     25                 updates += 1
     26 

2 frames
<ipython-input-7-a2432c4c3767> in update_parameters(self, memory, batch_size, updates)
     87 
     88         self.policy_optim.zero_grad()
---> 89         policy_loss.backward()
     90         self.policy_optim.step()
     91 

/usr/local/lib/python3.6/dist-packages/torch/tensor.py in backward(self, gradient, retain_graph, create_graph)
    196                 products. Defaults to ``False``.
    197         """
--> 198         torch.autograd.backward(self, gradient, retain_graph, create_graph)
    199 
    200     def register_hook(self, hook):

/usr/local/lib/python3.6/dist-packages/torch/autograd/__init__.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables)
     98     Variable._execution_engine.run_backward(
     99         tensors, grad_tensors, retain_graph, create_graph,
--> 100         allow_unreachable=True)  # allow_unreachable flag
    101 
    102

Answer 1

只需将 PyTorch 降级到 1.5.0 下的任何版本（在撰写本文时这是最新的）。

pip uninstall torch
pip install torch==1.4.0

Error: one of the variables needed for gradient computation has been modified by an inplace operation

Error: one of the variables needed for gradient computation has been modified by an inplace operation

python

reinforcement-learning

pytorch