Monte Carlo Return

Problem

Estimate the value of a target state from a fixed episode using first-visit Monte Carlo.

Find the first index where states equals target and return the discounted sum of rewards from that index onward. If the target never appears, return 0.0.

Hint

The first visit matters: ignore later occurrences of the target state.

Test cases

case 1

in: [["A","B","A"],[1,2,3],"A",0.5]

expected: 2.75

case 2

in: [["A","B","A"],[1,2,3],"B",0.5]

expected: 3.5

case 3

in: [["A","B","A"],[1,2,3],"C",0.5]

expected: 0

case 4

in: [["S"],[5],"S",0.99]

expected: 5

Starter codePython

def monte_carlo_return(states, rewards, target, gamma):
    # Your code here
    pass

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