Created
January 25, 2020 21:57
-
-
Save ryandgoldenberg1/84868f7523a677cc2e72fcf23a260a4f to your computer and use it in GitHub Desktop.
Cross Entropy Method for Optimization
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Adapted from Wikipedia page here: https://en.wikipedia.org/wiki/Cross-entropy_method | |
import numpy as np | |
def cem(mean, variance, maxits, num_samples, num_keep, objective_fn): | |
for t in range(1, maxits + 1): | |
# Sample according to current distribution | |
x = np.random.normal(loc=mean, scale=np.sqrt(variance), size=num_samples) | |
# Evaluate samples | |
s = objective_fn(x) | |
# Keep only top performing samples | |
s_order = np.flip(s.argsort()) | |
x = x[s_order][:num_keep] | |
# Update parameters | |
mean = np.mean(x) | |
variance = np.var(x, ddof=1) | |
# Log progress | |
print(f'iter: {t}, mean: {mean:.02f}, var: {variance:.02f}, value: {objective_fn(mean):.02f}') | |
return mean | |
if __name__ == '__main__': | |
# Objective function | |
def R(x): | |
return np.exp(-(x - 2)**2) + 0.8 * np.exp(-(x + 2)**2) | |
mean = cem( | |
mean=-6, | |
variance=100, | |
maxits=100, | |
num_samples=100, | |
num_keep=10, | |
objective_fn=R) | |
print('* Final Results:') | |
print(f'mean: {mean:.02f}, value: {R(mean):.02f}') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment