Reward-Free Exploration Count

Problem

Choose the least-visited state for reward-free exploration.

Return the index with the smallest visit count, breaking ties toward the smallest index. An empty list returns -1.

Hint

A strict less-than comparison makes the first minimum win ties.

case 1

in: [[3,1,2]]

expected: 1

case 2

in: [[5,5,5]]

expected: 0

case 3

in: [[2,0,1,0]]

expected: 1

case 4

in: [[]]

expected: -1

Starter codePython

def reward_free_exploration_count(visit_counts):
    # Your code here
    pass

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