CRR Advantage Weights

Problem

Compute binary CRR advantage weights: 1.0 when the advantage is strictly above the threshold, otherwise 0.0. An empty batch returns [].

Hint

Binary CRR simply filters out actions that were worse than average.

case 1

in: [[1,-1,0],0]

expected: [1,0,0]

case 2

in: [[-0.5,0.5],0]

expected: [0,1]

case 3

in: [[],1]

expected: []

Starter codePython

def crr_advantage_weights(advantages, threshold):
    # Your code here
    pass

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