MOSS Index

Problem

Compute the MOSS index for an arm.

With n = len(rewards) and ratio = max(1, total / n), return mean(rewards) + sqrt(c * log(ratio) / n). An empty reward list or a non-positive total returns 0.0.

Hint

The ratio is clamped at 1 so the log is never negative.

Test cases

case 1

in: [[1,0.5,0.5],30,2]

expected: 1.905640729616613

case 2

in: [[2],1,2]

expected: 2

case 3

in: [[0,1],10,1]

expected: 1.3970612889970506

Starter codePython

def moss_index(rewards, total, c):
    # Your code here
    pass

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