Custom loss function, silly example

gistfile1.txt

from keras.models import Sequential
from keras.layers import Dense
import keras.backend as K
import numpy as np


def penalized_loss(reward):
	def custom_loss(y_true, y_pred):
		return K.mean(K.square(y_pred - y_true) - K.square(y_true - reward), axis=-1)

	return custom_loss


if __name__ == '__main__':
	input_data = np.array([[1, 2, 3, 4, 5, 6], [1, 2, 3, 4, 5, 6], [1, 2, 3, 4, 5, 6]])
	x = input_data[:, :-2]  # States
	y = input_data[:, -2]  # Actions
	r = input_data[:, -1]  # Rewards

	# create model
	model = Sequential()
	model.add(Dense(12, input_dim=4, activation='relu'))
	model.add(Dense(8, activation='relu'))
	model.add(Dense(1, activation='sigmoid'))

	# Compile model
	model.compile(loss=[penalized_loss(reward=r)], optimizer='adam', metrics=['accuracy'])

	model.fit(x, y)

Tutorial on one hot encoding using sklearn and Keras:
https://machinelearningmastery.com/how-to-one-hot-encode-sequence-data-in-python/