-
Notifications
You must be signed in to change notification settings - Fork 103
Did someone know why DQN agent add one shape to array? #7
Comments
Related to #11 , exhibits the same behaviour of adding a dimension. For a quick fix, add a squeeze layer via keras.backend.squeeze |
I appreciate your response and your explaination. And here is my ( for now ) solution #229 |
For the next people that will have this issue this is how i've changed the method in dqn.py ( and i suppose in the other agent of this library )
I suppose the error is in the numpy.array that add the extra dimension for some reasons. |
After some searching, I found the issue in the function compute_q_values In the function, the state value is being forcefully put in another array.
After removing the explicit list conversion. It works fine for me. |
So this is my setting:
keras==2.3.1
keras-rl2
tensorflow-gpu==2.0.0-beta1
numpy==1.16.4
And when i fit the DQN agent, my model go on full craziness
This is the error :
But it start here:
row #169 core.py
I'm quite new in this library, maybe i'm missing something
The text was updated successfully, but these errors were encountered: