def simple_bandit_experiment():
b = Bandit()
alpha = 0.1
beta = 1.2
print('alpha: {:.2f} beta: {:.2f}\n'.format(alpha, beta))
agent = Agent(b, alpha, beta)
trials = 1000
for _ in range(trials):
agent.run()
df = agent.get_df()
ml = ML(df, 2)
r = ml.ml_estimation()
alpha_hat, beta_hat = r.x
print(r)
fig, ax = plt.subplots(1, 1)
ml.plot_ml(ax, alpha, beta, alpha_hat, beta_hat)
plt.show()
