Count-Based Bonus

Problem

Compute the count-based exploration bonus beta / (1 + count), where count is how many times the state-action pair has been visited. More visits shrink the bonus.

Hint

The bonus is a decreasing function of visitation count.

Test cases

case 1

in: [0,1]

expected: 1

case 2

in: [1,1]

expected: 0.5

case 3

in: [9,2]

expected: 0.2

case 4

in: [3,0]

expected: 0

Starter codePython

def count_based_bonus(count, beta):
    # Your code here
    pass

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