Rollout Average Return

Problem

Return the average return across a batch of rollout returns. An empty batch returns 0.0.

Hint

This is the plain Monte Carlo estimate of the policy's expected return.

case 1

in: [[1,2,3]]

expected: 2

case 2

in: [[]]

expected: 0

case 3

in: [[5]]

expected: 5

case 4

in: [[-1,1]]

expected: 0

Starter codePython

def rollout_average_return(returns):
    # Your code here
    pass

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