0002_reinforcement

0002_reinforcement

import numpy as np
ssp = [1, 1, 1, 1, 0]

def epoch():
             asp = [1, 0]
             tr = 0
             for _ in range(100):
                 a = np.random.choice(asp)
                 s = np.random.choice(ssp)
                 if a == s:
                     tr += 1  
                 asp.append(s)
             return tr

rl = np.array([epoch() for _ in range(15)])
  
print(rl.mean())