Function run_experiment

rl/comparing_epsilons.py:26–56

(m1, m2, m3, eps, N)

def run_experiment(m1, m2, m3, eps, N):
  bandits = [Bandit(m1), Bandit(m2), Bandit(m3)]

  data = np.empty(N)
  
  for i in range(N):
    # epsilon greedy
    p = np.random.random()
    if p < eps:
      j = np.random.choice(3)
    else:
      j = np.argmax([b.mean for b in bandits])
    x = bandits[j].pull()
    bandits[j].update(x)

    # for the plot
    data[i] = x
  cumulative_average = np.cumsum(data) / (np.arange(N) + 1)

  # plot moving average ctr
  plt.plot(cumulative_average)
  plt.plot(np.ones(N)*m1)
  plt.plot(np.ones(N)*m2)
  plt.plot(np.ones(N)*m3)
  plt.xscale('log')
  plt.show()

  for b in bandits:
    print(b.mean)

  return cumulative_average

if __name__ == '__main__':
  c_1 = run_experiment(1.0, 2.0, 3.0, 0.1, 100000)