Closed shanyou92 closed 7 years ago
I am runnning the run_ALE.py, and I use the keras model:
from deer.q_networks.q_net_keras import MyQNetwork.
However, this goes wrong.
Traceback (most recent call last): File "run_ALE.py", line 85, in rng) File "/share/syou/deer/local/lib/python2.7/site-packages/deer/q_networks/q_net_keras.py", line 60, in init self.q_vals, self.params = Q_net._buildDQN() TypeError: _buildDQN() takes exactly 2 arguments (1 given)
Btw, when I use theano, it goes well. Any ideas?
I think you passed a theano neural network to the Q_network. If you use keras, you have to pass a keras neural network.
I am runnning the run_ALE.py, and I use the keras model:
from deer.q_networks.q_net_keras import MyQNetwork.
However, this goes wrong.
Traceback (most recent call last): File "run_ALE.py", line 85, in
rng)
File "/share/syou/deer/local/lib/python2.7/site-packages/deer/q_networks/q_net_keras.py", line 60, in init
self.q_vals, self.params = Q_net._buildDQN()
TypeError: _buildDQN() takes exactly 2 arguments (1 given)
Btw, when I use theano, it goes well. Any ideas?