RND Novelty Error Lite

Problem

Compute the mean squared error between predicted and target random-network-distillation features. An empty vector returns 0.0.

Hint

Large prediction error means the state is novel to the predictor network.

case 1

in: [[1,2],[1,2]]

expected: 0

case 2

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

expected: 1

case 3

in: [[1,3],[2,1]]

expected: 2.5

case 4

in: [[],[]]

expected: 0

Starter codePython

def rnd_novelty_error(predicted, target):
    # Your code here
    pass

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