Advantage Function

Problem

Compute the advantage of each action: A(s,a) = Q(s,a) - V(s). Return a list with the same length as Q_values.

Hint

The value function is the baseline; advantages say which actions beat it.

case 1

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

expected: [-1,0,1]

case 2

in: [[0,0],0]

expected: [0,0]

case 3

in: [[-1,5],3]

expected: [-4,2]

case 4

in: [[],1]

expected: []

Starter codePython

def advantage_function(Q_values, state_value):
    # Your code here
    pass

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