baseToComplex/maze_env2.py at master · Jason33Wang/baseToComplex · GitHub

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
"""
Reinforcement learning maze example.

Red rectangle:          explorer.
Black rectangles:       hells       [reward = -1].
Yellow bin circle:      paradise    [reward = +1].
All other states:       ground      [reward = 0].

This script is the environment part of this example.
The RL is in RL_brain.py.

View more on my tutorial page: https://morvanzhou.github.io/tutorials/
"""
import numpy as np
import time
import sys
if sys.version_info.major == 2:
    import Tkinter as tk
else:
    import tkinter as tk

UNIT = 40   # pixels
MAZE_H = 4  # grid height
MAZE_W = 4  # grid width


class Maze(tk.Tk, object):
    def __init__(self):
        super(Maze, self).__init__()
        self.action_space = ['u', 'd', 'l', 'r']
        self.n_actions = len(self.action_space)
        self.n_features = 2
        self.title('maze')
        self.geometry('{0}x{1}'.format(MAZE_H * UNIT, MAZE_H * UNIT))
        self._build_maze()

    def _build_maze(self):
        self.canvas = tk.Canvas(self, bg='white',
                           height=MAZE_H * UNIT,
                           width=MAZE_W * UNIT)

        # create grids
        for c in range(0, MAZE_W * UNIT, UNIT):
            x0, y0, x1, y1 = c, 0, c, MAZE_H * UNIT
            self.canvas.create_line(x0, y0, x1, y1)
        for r in range(0, MAZE_H * UNIT, UNIT):
            x0, y0, x1, y1 = 0, r, MAZE_H * UNIT, r
            self.canvas.create_line(x0, y0, x1, y1)

        # create origin
        origin = np.array([20, 20])

        # hell
        hell1_center = origin + np.array([UNIT * 2, UNIT])
        self.hell1 = self.canvas.create_rectangle(
            hell1_center[0] - 15, hell1_center[1] - 15,
            hell1_center[0] + 15, hell1_center[1] + 15,
            fill='black')
        # hell
        # hell2_center = origin + np.array([UNIT, UNIT * 2])
        # self.hell2 = self.canvas.create_rectangle(
        #     hell2_center[0] - 15, hell2_center[1] - 15,
        #     hell2_center[0] + 15, hell2_center[1] + 15,
        #     fill='black')

        # create oval
        oval_center = origin + UNIT * 2
        self.oval = self.canvas.create_oval(
            oval_center[0] - 15, oval_center[1] - 15,
            oval_center[0] + 15, oval_center[1] + 15,
            fill='yellow')

        # create red rect
        self.rect = self.canvas.create_rectangle(
            origin[0] - 15, origin[1] - 15,
            origin[0] + 15, origin[1] + 15,
            fill='red')

        # pack all
        self.canvas.pack()

    def reset(self):
        self.update()
        time.sleep(0.1)
        self.canvas.delete(self.rect)
        origin = np.array([20, 20])
        self.rect = self.canvas.create_rectangle(
            origin[0] - 15, origin[1] - 15,
            origin[0] + 15, origin[1] + 15,
            fill='red')
        # return observation
        return (np.array(self.canvas.coords(self.rect)[:2]) - np.array(self.canvas.coords(self.oval)[:2]))/(MAZE_H*UNIT)

    def step(self, action):
        s = self.canvas.coords(self.rect)
        base_action = np.array([0, 0])
        if action == 0:   # up
            if s[1] > UNIT:
                base_action[1] -= UNIT
        elif action == 1:   # down
            if s[1] < (MAZE_H - 1) * UNIT:
                base_action[1] += UNIT
        elif action == 2:   # right
            if s[0] < (MAZE_W - 1) * UNIT:
                base_action[0] += UNIT
        elif action == 3:   # left
            if s[0] > UNIT:
                base_action[0] -= UNIT

        self.canvas.move(self.rect, base_action[0], base_action[1])  # move agent

        next_coords = self.canvas.coords(self.rect)  # next state

        # reward function
        if next_coords == self.canvas.coords(self.oval):
            reward = 1
            done = True
            print("到达终点")
        elif next_coords in [self.canvas.coords(self.hell1)]:
            reward = -1
            done = True
            print("撞到障碍物了")
        else:
            reward = 0
            done = False
        s_ = (np.array(next_coords[:2]) - np.array(self.canvas.coords(self.oval)[:2]))/(MAZE_H*UNIT)
        return s_, reward, done

    def render(self):
        # time.sleep(0.01)
        self.update()

def update():
    for t in range(10):
        s = env.reset()
        while True:
            env.render()
            a = 1
            s, r, done = env.step(a)
            if done:
                break

if __name__ == '__main__':
    env = Maze()
    env.after(100, update)
    env.mainloop()