Deterministic Eval Policy

Problem

Return the greedy (deterministic) action values used for evaluation: the maximum Q value of every state row.

Hint

Evaluation uses argmax actions so results are reproducible across runs.

case 1

in: [[[1,3,2],[5,5,1]]]

expected: [3,5]

case 2

in: [[[-1,-2]]]

expected: [-1]

case 3

in: [[]]

expected: []

Starter codePython

def deterministic_eval_values(Q):
    # Your code here
    pass

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