observation类型转换错误

[Code-Newborn]

此处运行不通过，报错： f:\Github\DDPG\DDPG.py:51: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at C:\cb\pytorch_1000000000000\work\torch\csrc\utils\tensor_new.cpp:233.) state = T.tensor(observation, dtype=T.float).to(device) Traceback (most recent call last): File "f:\Github\DDPG\train.py", line 53, in main() File "f:\Github\DDPG\train.py", line 31, in main action = agent.choose_action(observation, train=True) File "f:\Github\DDPG\DDPG.py", line 51, in choose_action state = T.tensor(observation, dtype=T.float).to(device) ValueError: expected sequence of length 8 at dim 1 (got 0)

[Yzhtc]

同样的错误！

[zheng85]

请问这个错误怎么解决？我也遇到了，你们解决了吗？

[Code-Newborn]

忘记回帖了，已解决，改成如下所示：