In [1]:
import numpy as np
import matplotlib.pyplot as plt
import scipy.signal as sig
import control
import plot_learning_curve as plc
In [2]:
num_failures, time_steps_to_failure = control.simulate()
The number of trials obtained for the reinforcement learning algorithm to converge was the following.
In [3]:
print(num_failures)
The learning curve for the reinforcement learning algorithm is the following.
In [4]:
plot = plc.plot_learning_curve(time_steps_to_failure[:num_failures])
In [5]:
plt.show()
In [ ]: