Matthew Bird
Matthew Bird
When training I see progress followed by degradation. This is (likely) because the model is over fitting due to the limited corpus size of 8k samples. What is happening is...
It might be nice to, as a final step, show an instance of an actual inference on the model so a reader can "tie it all together". It isn't strictly...
Can we get at least a 5-7 line example of how to use this?
This line `q_update = (reward + GAMMA * np.amax(self.model.predict(state_next)[0]))` you are taking a prediction upon your next state, and then updating your current predictions with a reward over that (next)...
### Description ``` C:\Users\XXXXX\Anaconda3\Lib\site-packages\tensor2tensor\bin>python t2t_trainer.py Traceback (most recent call last): File "t2t_trainer.py", line 24, in from tensor2tensor import models # pylint: disable=unused-import File "C:\Users\XXXXX\Anaconda3\lib\site-packages\tensor2tensor\models\__init__.py", line 26, in from tensor2tensor.models import...