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()
return cumulative_average
if __name__ == '__main__':
eps = run_experiment_decaying_epsilon(1.0, 2.0, 3.0, 100000)
oiv = run_experiment_oiv(1.0, 2.0, 3.0, 100000)
ucb = run_experiment_ucb(1.0, 2.0, 3.0, 100000)
bayes = run_experiment(1.0, 2.0, 3.0, 100000)
# log scale plot
plt.plot(eps, label='decaying-epsilon-greedy')
plt.plot(oiv, label='optimistic')
plt.plot(ucb, label='ucb1')
plt.plot(bayes, label='bayesian')
plt.legend()
plt.xscale('log')
plt.show()
# linear plot
plt.plot(eps, label='decaying-epsilon-greedy')
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()
return cumulative_average
if __name__ == '__main__':
<<<<<<< HEAD
eps = run_experiment_decaying_epsilon(1.0, 2.0, 3.0, 100000)
oiv = run_experiment_oiv(1.0, 2.0, 3.0, 100000)
ucb = run_experiment_ucb(1.0, 2.0, 3.0, 100000)
bayes = run_experiment(1.0, 2.0, 3.0, 100000)
=======
m1 = 1.0
m2 = 2.0
m3 = 3.0
eps = run_experiment_decaying_epsilon(m1, m2, m3, 100000)
oiv = run_experiment_oiv(m1, m2, m3, 100000)
ucb = run_experiment_ucb(m1, m2, m3, 100000)
bayes = run_experiment(m1, m2, m3, 100000)
>>>>>>> upstream/master
# log scale plot
plt.plot(eps, label='decaying-epsilon-greedy')
plt.plot(oiv, label='optimistic')
# 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()
return cumulative_average
if __name__ == '__main__':
m1 = 1.0
m2 = 2.0
m3 = 3.0
eps = run_experiment_decaying_epsilon(m1, m2, m3, 100000)
oiv = run_experiment_oiv(m1, m2, m3, 100000)
ucb = run_experiment_ucb(m1, m2, m3, 100000)
bayes = run_experiment(m1, m2, m3, 100000)
# log scale plot
plt.plot(eps, label='decaying-epsilon-greedy')
plt.plot(oiv, label='optimistic')
plt.plot(ucb, label='ucb1')
plt.plot(bayes, label='bayesian')
plt.legend()
plt.xscale('log')
plt.show()
# linear plot
plt.plot(eps, label='decaying-epsilon-greedy')
plt.plot(cumulative_avg)
plt.plot(np.ones(N) * m1)
plt.plot(np.ones(N) * m2)
plt.plot(np.ones(N) * m3)
plt.xscale('log')
plt.show()
return cumulative_avg
if __name__ == '__main__':
m1, m2, m3 = 1.0, 2.0, 3.0
N = 100000
eps = run_experiment_decaying_eps(m1, m2, m3, N)
oiv = run_experiment_oiv(m1, m2, m3, N, 10)
ucb = run_experiment_ucb(m1, m2, m3, N)
bayes = run_experiment_bayesian_sampling(m1, m2, m3, N)
# Log scale plot
plt.plot(eps, label='Decaying Epsilon Greedy')
plt.plot(oiv, label='Optimistic')
plt.plot(ucb, label='UCB1')
plt.plot(bayes, label='Bayesian')
plt.legend()
plt.xscale('log')
plt.show()
# Linear plot
plt.plot(eps, label='Decaying Epsilon Greedy')
plt.plot(oiv, label='Optimistic')