Self-Play Reward

Problem

Return the terminal reward for a self-play player from the final score.

player is 0 or 1; the reward is 1.0 for a win, -1.0 for a loss, and 0.0 for a draw.

Hint

Flip the scores when the queried player is the second one.

case 1

in: [3,1,0]

expected: 1

case 2

in: [1,3,0]

expected: -1

case 3

in: [2,2,1]

expected: 0

case 4

in: [1,3,1]

expected: 1

Starter codePython

def self_play_reward(score_a, score_b, player):
    # Your code here
    pass

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