Target Network Lag Effect

Problem

Compute the target network after a fixed number of soft updates while the online network stays fixed.

After n steps the target equals online + (target0 - online) * (1 - tau)^n. Return the resulting vector.

Hint

The target lags the online network by a geometric factor (1 - tau) per step.

case 1

in: [[0,0],[10,20],0.1,1]

expected: [1,2]

case 2

in: [[0,0],[10,20],0.1,10]

expected: [6.513215598999999,13.026431197999997]

case 3

in: [[1,2],[1,2],0.5,5]

expected: [1,2]

Starter codePython

def target_network_lag(target, online, tau, steps):
    # Your code here
    pass

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