Entropy Bonus

Problem

Compute the entropy of an action distribution in nats: H = -sum p * ln(p).

Skip zero probabilities and return 0.0 for an empty distribution.

Hint

Maximum entropy is ln(n) for a uniform distribution over n actions.

case 1

in: [[0.5,0.5]]

expected: 0.6931471805599453

case 2

in: [[1,0]]

expected: 0

case 3

in: [[0.25,0.25,0.25,0.25]]

expected: 1.3862943611198906

case 4

in: [[]]

expected: 0

Starter codePython

import math
def entropy_bonus(probs):
    # Your code here
    pass

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