OU Noise Step

Problem

Take one Ornstein-Uhlenbeck step: x + theta*(mu - x)*dt + sigma*sqrt(dt)*noise. The process mean-reverts toward mu.

Hint

OU noise creates temporally correlated exploration for continuous control.

case 1

in: [0,0,0.15,0.2,0.01,1]

expected: 0.020000000000000004

case 2

in: [1,0,0.5,0.3,0.25,-1]

expected: 0.725

case 3

in: [0.5,0.5,0.1,0.1,0,1]

expected: 0.5

Starter codePython

import math
def ou_noise_step(x, mu, theta, sigma, dt, noise):
    # Your code here
    pass

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