“tensorflow.python.framework.ops.tensor”对象没有属性“squence”

Question

我正在尝试使用huskarl并将演示文件加载到tesnt，以确保我已正确安装了所有内容。但是，当我运行任何演示文件时，我会遇到以下跟踪：

Traceback (most recent call last):
  File "ddpg-pendulum.py", line 48, in <module>
    sim.train(max_steps=30_000, visualize=True, plot=plot_rewards)
  File "C:\Users\Project Apollo\AppData\Local\Programs\Python\Python37\lib\site-packages\huskarl\simulation.py", line 32, in train
    self._sp_train(max_steps, instances, visualize, plot)
  File "C:\Users\Project Apollo\AppData\Local\Programs\Python\Python37\lib\site-packages\huskarl\simulation.py", line 66, in _sp_train
    self.agent.train(step)
  File "C:\Users\Project Apollo\AppData\Local\Programs\Python\Python37\lib\site-packages\huskarl\agent\ddpg.py", line 101, in train
    target_qvals[non_final_mask] = self.target_critic.predict_on_batch([target_actions, np.array(non_final_last_next_states)]).squeeze()
AttributeError: 'tensorflow.python.framework.ops.EagerTensor' object has no attribute 'squeeze'

知道格涅怎么了吗

Answer 1

末尾使用的挤压函数中存在错误

self.target\u critic.predict\u on\u batch（[target\u actions，np.array（非最终\u last\u next\u states）]）.squeak（）

尝试使用tf.squeeze()或np.squeeze()

Answer 2

所以我发现huskarl只与tensorflow==2.0.0a0兼容。我通过卸载tf并重新安装它并捕获错误发现了这一点。：/