-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path06-reinforcement-learning.Rmd
223 lines (185 loc) · 4.45 KB
/
06-reinforcement-learning.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
# Reinforcement Learning
## Upper Confidence Bound (UCB)
### Importing the libraries
**Python**
```{python}
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
```
### Importing the dataset
**Python**
```{python}
dataset = pd.read_csv('Ads_CTR_Optimisation.csv')
```
**R**
```{r}
dataset = read.csv('Ads_CTR_Optimisation.csv')
```
### Implementing UCB
**Python**
```{python}
import math
N = 10000
d = 10
ads_selected = []
numbers_of_selections = [0] * d
sums_of_rewards = [0] * d
total_reward = 0
for n in range(0, N):
ad = 0
max_upper_bound = 0
for i in range(0, d):
if (numbers_of_selections[i] > 0):
average_reward = sums_of_rewards[i] / numbers_of_selections[i]
delta_i = math.sqrt(3/2 * math.log(n + 1) / numbers_of_selections[i])
upper_bound = average_reward + delta_i
else:
upper_bound = 1e400
if upper_bound > max_upper_bound:
max_upper_bound = upper_bound
ad = i
ads_selected.append(ad)
numbers_of_selections[ad] = numbers_of_selections[ad] + 1
reward = dataset.values[n, ad]
sums_of_rewards[ad] = sums_of_rewards[ad] + reward
total_reward = total_reward + reward
```
**R**
```{r}
N = 10000
d = 10
ads_selected = integer(0)
numbers_of_selections = integer(d)
sums_of_rewards = integer(d)
total_reward = 0
for (n in 1:N) {
ad = 0
max_upper_bound = 0
for (i in 1:d) {
if (numbers_of_selections[i] > 0) {
average_reward = sums_of_rewards[i] / numbers_of_selections[i]
delta_i = sqrt(3/2 * log(n) / numbers_of_selections[i])
upper_bound = average_reward + delta_i
} else {
upper_bound = 1e400
}
if (upper_bound > max_upper_bound) {
max_upper_bound = upper_bound
ad = i
}
}
ads_selected = append(ads_selected, ad)
numbers_of_selections[ad] = numbers_of_selections[ad] + 1
reward = dataset[n, ad]
sums_of_rewards[ad] = sums_of_rewards[ad] + reward
total_reward = total_reward + reward
}
```
### Visualising the results
**Python**
```{python}
plt.hist(ads_selected)
plt.title('Histogram of ads selections')
plt.xlabel('Ads')
plt.ylabel('Number of times each ad was selected')
plt.show()
```
**R**
```{r}
hist(ads_selected,
col = 'blue',
main = 'Histogram of ads selections',
xlab = 'Ads',
ylab = 'Number of times each ad was selected')
```
## Thompson Sampling
### Importing the libraries
**Python**
```{python}
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
```
### Importing the dataset
**Python**
```{python}
dataset = pd.read_csv('Ads_CTR_Optimisation.csv')
```
**R**
```{r}
dataset = read.csv('Ads_CTR_Optimisation.csv')
```
### Implementing Thompson Sampling
**Python**
```{python}
import random
N = 10000
d = 10
ads_selected = []
numbers_of_rewards_1 = [0] * d
numbers_of_rewards_0 = [0] * d
total_reward = 0
for n in range(0, N):
ad = 0
max_random = 0
for i in range(0, d):
random_beta = random.betavariate(numbers_of_rewards_1[i] + 1, numbers_of_rewards_0[i] + 1)
if random_beta > max_random:
max_random = random_beta
ad = i
ads_selected.append(ad)
reward = dataset.values[n, ad]
if reward == 1:
numbers_of_rewards_1[ad] = numbers_of_rewards_1[ad] + 1
else:
numbers_of_rewards_0[ad] = numbers_of_rewards_0[ad] + 1
total_reward = total_reward + reward
```
**R**
```{r}
N = 10000
d = 10
ads_selected = integer(0)
numbers_of_rewards_1 = integer(d)
numbers_of_rewards_0 = integer(d)
total_reward = 0
for (n in 1:N) {
ad = 0
max_random = 0
for (i in 1:d) {
random_beta = rbeta(n = 1,
shape1 = numbers_of_rewards_1[i] + 1,
shape2 = numbers_of_rewards_0[i] + 1)
if (random_beta > max_random) {
max_random = random_beta
ad = i
}
}
ads_selected = append(ads_selected, ad)
reward = dataset[n, ad]
if (reward == 1) {
numbers_of_rewards_1[ad] = numbers_of_rewards_1[ad] + 1
} else {
numbers_of_rewards_0[ad] = numbers_of_rewards_0[ad] + 1
}
total_reward = total_reward + reward
}
```
### Visualising the results - Histogram
**Python**
```{python}
plt.hist(ads_selected)
plt.title('Histogram of ads selections')
plt.xlabel('Ads')
plt.ylabel('Number of times each ad was selected')
plt.show()
```
**R**
```{r}
hist(ads_selected,
col = 'blue',
main = 'Histogram of ads selections',
xlab = 'Ads',
ylab = 'Number of times each ad was selected')
```