after training the cartpole for 2 episodes and saving the trained policy, when launching again, it gives me the following error:
(‘Loading from file:’, ‘qlearn_states.npy’)
Traceback (most recent call last):
File “/home/user/catkin_ws/src/my_cartpole_training/src/start_training.py”, line 60, in
qlearn.load(qfile)
File “/home/user/catkin_ws/src/my_cartpole_training/src/qlearn.py”, line 67, in load
self.q = np.load(filename).item()
File “/usr/local/lib/python2.7/dist-packages/numpy/lib/npyio.py”, line 447, in load
pickle_kwargs=pickle_kwargs)
File “/usr/local/lib/python2.7/dist-packages/numpy/lib/format.py”, line 696, in read_array
raise ValueError("Object arrays cannot be loaded when "
ValueError: Object arrays cannot be loaded when allow_pickle=False
[cartpole_gym-1] process has died [pid 13775, exit code 1, cmd /home/user/catkin_ws/src/my_cartpole_training/src/start_training.py __name:=cartpole_gym __log:=/home/user/.ros/log/40bff856-ef5c-11ea-b5ed-020c49a2de4d/cartpole_gym-1.log].
Also: where to find the learned policy file (qlearn_states.npy)? i did not find it anywhere in the files, if i want to move this learned experience file from one device to another