Dueling Aggregation Avg

Problem

Aggregate a dueling value and advantage stream using the average of the mean and max baselines.

baseline = (mean(advantage) + max(advantage)) / 2 and Q(a) = value + advantage[a] - baseline.

Hint

Averaging the two baselines is a middle ground between mean and max aggregation.

case 1

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

expected: [3.5,4.5,5.5]

case 2

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

expected: [-1.5,-0.5,0.5]

case 3

in: [2,[4,4]]

expected: [2,2]

Starter codePython

def dueling_aggregation_avg(value, advantage):
    # Your code here
    pass

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