TypeError: float() argument must be a string or a number

[SeekPoint]

envy@ub1404:/os_pri/github/qlearning4k/examples$ python test_catch.py
Using Theano backend.
Using gpu device 0: GeForce GTX 950M (CNMeM is disabled, CuDNN 4007)
/home/envy/.local/lib/python2.7/site-packages/theano/tensor/signal/downsample.py:5: UserWarning: downsample module has been moved to the pool module.
warnings.warn("downsample module has been moved to the pool module.")
Epoch 001/1000 | Loss 0.0000 | Epsilon 0.10 | Win count 1
Traceback (most recent call last):
File "test_catch.py", line 20, in
agent.train(catch, batch_size=10, nb_epoch=1000, epsilon=.1)
File "/home/envy/.local/lib/python2.7/site-packages/qlearning4k/agent.py", line 94, in train
loss += float(model.train_on_batch(inputs, targets))
TypeError: float() argument must be a string or a number
envy@ub1404:/os_pri/github/qlearning4k/examples$

[tigerneil]

I also have the problem.

> $ python test_snake.py                                                                                                              ⬡ 5.9.1 [±master ●]
Using TensorFlow backend.
Traceback (most recent call last):
  File "test_snake.py", line 23, in <module>
    agent.train(snake, batch_size=64, nb_epoch=10000, gamma=0.8)
  File "build/bdist.macosx-10.11-intel/egg/qlearning4k/agent.py", line 94, in train
TypeError: float() argument must be a string or a number

[wannaphong]

Fix in #11