All problems
Twin Q Min
Problem
Return the elementwise minimum of the two critic outputs: min(Q1[a], Q2[a]) for every action a. Empty lists return [].
Hint
Taking the minimum of twin critics fights the overestimation bias.
Test cases
case 1
in: [[1,5,3],[4,2,3]]
expected: [1,2,3]
case 2
in: [[-1],[2]]
expected: [-1]
case 3
in: [[0,0],[0,1]]
expected: [0,0]
case 4
in: [[],[]]
expected: []
Starter codePython
def twin_q_min(Q1, Q2):
# Your code here
pass4 test cases · run your code against them in the editor