Ta的回复 ：不止这个fluid.data出现未初始化的情况，其他的有些计算的中间过程也出现过为初始化的情况    

Ta的回复 ：在社区里面也没找到相关的答案

Ta的回复 ：被初始化给按在地上反复的摩擦  

Ta的回复 ：还有这个未初始化 [图片]

Ta的回复 ：exe.run(fluid.default_startup_program())  

Ta的回复 ：试了，没用。太蛋疼了  

Ta的回复 ：提了，官方的人还没有搞定。刚刚又碰到了同样的错误了。突然感觉paddle很垃圾，但奈何他是国产的，还是要继续喜欢他啊。

Ta的回复 ：[代码]

Ta的回复 ：D:\kj7541\Anaconda3\envs\pdl\python.exe F:/kj7541/AI/RL/MyStudy/AC_PDL/MY_AC_dygraph.py D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\paddle\fluid\executor.py:1070: UserWarning: The following exception is not an EOF exception. "The following exception is not an EOF exception.") Traceback (most recent call last): File "F:/kj7541/AI/RL/MyStudy/AC_PDL/MY_AC_dygraph.py", line 56, in critic.train(dat(state), dat(reward), dat(next_state)) File "F:/kj7541/AI/RL/MyStudy/AC_PDL/MY_AC_dygraph.py", line 34, in train fetch_list=[self.value])[0] File "D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\paddle\fluid\executor.py", line 1071, in run six.reraise(*sys.exc_info()) File "D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\six.py", line 703, in reraise raise value File "D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\paddle\fluid\executor.py", line 1066, in run return_merged=return_merged) File "D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\paddle\fluid\executor.py", line 1154, in _run_impl use_program_cache=use_program_cache) File "D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\paddle\fluid\executor.py", line 1229, in _run_program fetch_var_name) paddle.fluid.core_noavx.EnforceNotMet: -------------------------------------------- C++ Call Stacks (More useful to developers): -------------------------------------------- Windows not support stack backtrace yet. ------------------------------------------ Python Call Stacks (More useful to users): ------------------------------------------ File "D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\paddle\fluid\framework.py", line 2610, in append_op attrs=kwargs.get("attrs", None)) File "D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\paddle\fluid\layers\math_op_patch.py", line 158, in _scalar_elementwise_op_ "bias": bias}) File "D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\paddle\fluid\layers\math_op_patch.py", line 174, in _scalar_elementwise_mul_ return _scalar_elementwise_op_(var, value, 0.0) File "D:\kj7541\Anaconda3\envs\pdl\lib\site-packages\paddle\fluid\layers\math_op_patch.py", line 193, in __impl__ return scalar_method(self, other_var) File "F:/kj7541/AI/RL/MyStudy/AC_PDL/MY_AC_dygraph.py", line 25, in _built_net self.td_error = reward + self.gamma * next_reward_ - self.value File "F:/kj7541/AI/RL/MyStudy/AC_PDL/MY_AC_dygraph.py", line 13, in __init__ self._built_net() File "F:/kj7541/AI/RL/MyStudy/AC_PDL/MY_AC_dygraph.py", line 45, in critic = Critic(exe, gamma=0.9, state_dim=4, lr=0.005) ---------------------- Error Message Summary: ---------------------- InvalidArgumentError: The Tensor in the scale Op's Input Variable X(next_reward_) is not initialized. [Hint: Expected t->IsInitialized() == true, but received t->IsInitialized():0 != true:1.] at (D:\1.8.1\paddle\paddle\fluid\framework\operator.cc:1289) [operator < scale > error]