r1 weights and biases naming redundancy

[chrismessenger]

The convolutional weight and bias names have historical + '1' added to them which is not required. This is also the case in the q and r2 networks.

Plus, there are lots of commented out code that can get deleted when creating the weights.

[chrismessenger]

Also, the

self.nonlinearity_mean = tf.clip_by_value

is never used so can be removed.

[chrismessenger]

You can also delete the commented out "make positive definite covariance matrix code"