#print('obs shape',img['obs'].shape)
full_image = env_check.render('rgb_array')
#data = np.zeros((img['height'], img['width'], img['channels']), dtype=np.uint8)
#showimg = Image.fromarray(img['obs']*255/np.amax(img['obs']),'RGB')
#showimg.show()
#sys.exit(0)
print('SENSE CHECK PREPROCESSING')
# check
print('SENSE CHECK DQN AGENT')
x = dqn.get_config()
for key, value in x.items():
if key=='model':
pass
else:
print(key,value)
"""
dqn.compile(Adam(lr=.00025), metrics=['mae'])
if args.mode == 'train':
# Okay, now it's time to learn something! We capture the interrupt exception so that training
# can be prematurely aborted. Notice that you can the built-in Keras callbacks!
weights_filename = 'dqn_{}_weights.h5f'.format(args.env_name)
