Jackmeory

关于open AI gym运行报错

2

我下载了DQN的代码，发现运行报错，主要错误在两个地方上 1.choose_action(self, observation): observation = observation[np.newaxis, :]出现错误为TypeError: tuple indices must be integers or slices, not tuple 2.在修改了第一部分的错误之后（通过课程讨论区一位朋友提供的想法先observation=np.array(observation)然后再进行reshape，发现在transition部分又出现错误，提示输入的transition和self.memory列数不同，在进行observation的打印之后发现它的格式很奇怪，是(array([ 0.00107828, -0.02266533, -0.03175206, -0.04841794], dtype=float32), {}) 这样的一个形式，和observation_的形式也不同，我又回去check了maze的observation和observation_的形式发现maze的是相同，不知道该如何修改RL_brain的代码，希望大神们能给点建议

AttributeError: 'CoraGraphDataset' object has no attribute 'features'

5

Anyone has encountered this type of problem while processing data in the python file continuum?

Encounter this error while try the train.py with model KTransCAT, and this issue may be inside the layer FeatTransKCat. Also may I ask the FGN in the paper refer to...