Hands-On Reinforcement Learning for Games

Implementing Monte Carlo

In many cases, even understanding simple concepts that are abstract can be difficult without real-world examples. Therefore, open up the Chapter_3_1.py code sample.

We should mention before starting that , in this case, refers to the actual value we estimate at 3.14.

Follow the exercise:

1. The following is the entire code listing for reference:

from random import *from math import sqrtins = 0n = 100000for i in range(0, n):   x = (random()-.5) * 2    y = (random()-.5) * 2    if sqrt(x*x+y*y)<=1:        ins+=1pi = 4 * ins / nprint(pi)

This code solves for using the Monte Carlo method, which is quite impressive when you consider how ...