ICM Forward Loss

Problem

Compute the ICM forward-model loss: one half of the mean squared error between predicted and actual next-state features. An empty vector returns 0.0.

Hint

The intrinsic reward is proportional to this forward prediction loss.

case 1

in: [[0,0],[1,1]]

expected: 0.5

case 2

in: [[1,1],[1,1]]

expected: 0

case 3

in: [[2],[0]]

expected: 2

case 4

in: [[],[]]

expected: 0

Starter codePython

def icm_forward_loss(predicted_next, actual_next):
    # Your code here
    pass

4 test cases · run your code against them in the editor