import numpy as np import matplotlib.pyplot as plt

def getSamplar(): mu=np.random.normal(0,10) sd=abs(np.random.normal(5,2)) getSample=lambda: np.random.normal(mu,sd) return getSample

def e_greedy(Q, e):

################################################## # Your code here ################################################## return

Please finish the code in python

Task 1 - Make One-step Decision Using e-greedy The formula is A a rg maxa Q(a), with probability 1- (break ties randomly) a random action, with probability e You are supposed to complete the e_greedy function in the kBandit.py file. In this function you choose action following the e-greedy algorithm. There are two input parameters of the function e_greedy. (1) Q - A dictionary. The keys are the possible actions. The values are the average reward you got when taking the action. (2) E- a scalar between 0 and 1. The return value of the function e_greedy is a scalar. It represents the action you are taking if you follow the e-greedy algorithm. Task 1 - Make One-step Decision Using e-greedy The formula is A a rg maxa Q(a), with probability 1- (break ties randomly) a random action, with probability e You are supposed to complete the e_greedy function in the kBandit.py file. In this function you choose action following the e-greedy algorithm. There are two input parameters of the function e_greedy. (1) Q - A dictionary. The keys are the possible actions. The values are the average reward you got when taking the action. (2) E- a scalar between 0 and 1. The return value of the function e_greedy is a scalar. It represents the action you are taking if you follow the e-greedy algorithm