-
Notifications
You must be signed in to change notification settings - Fork 0
/
main.py
45 lines (33 loc) · 1014 Bytes
/
main.py
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
import numpy as np
import qlearning
from maze import Maze
from colorama import init
import time
def main():
# Colorama initialization
init()
# Importing the maze from the txt file
list = [[]]
with open('maze.txt') as f:
i = 0
for line in f:
for char in line:
if char == '\n':
list.append([])
i = i + 1
else:
list[i].append(int(char))
arr = np.array(list)
#Initializing our MDP
env = Maze(arr)
# Running reinforcement learning algorithm
print("\nRunning the algorithm...")
start_time = time.time()
ql = qlearning.QLearning(learning_rate=0.1, discount_factor=0.9, epsilon=0.1, epochs = 2000, environment=env)
training_time = time.time() - start_time
# Printing the path
env.displayMaze(ql.path)
ql.displayFitness()
print("Training time : {}\n".format(training_time))
if __name__ == '__main__':
main()