nopcoder/game_view.py at main · dotpipe/nopcoder · 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
import pygame
import random


class GameView:

    def __init__(self, controller):

        self.controller = controller

        pygame.init()

        self.width = 600
        self.height = 600

        self.screen = pygame.display.set_mode((self.width, self.height))
        pygame.display.set_caption("AI System Live View")

        self.clock = pygame.time.Clock()

        self.grid_size = 10
        self.cell_size = self.width // self.grid_size

        self.agent_pos = [5, 5]

    # =====================================================
    # DRAW GRID
    # =====================================================
    def draw_grid(self):

        for x in range(self.grid_size):
            for y in range(self.grid_size):

                rect = pygame.Rect(
                    x * self.cell_size,
                    y * self.cell_size,
                    self.cell_size,
                    self.cell_size
                )

                pygame.draw.rect(self.screen, (30, 30, 30), rect, 1)

    # =====================================================
    # DRAW AGENT
    # =====================================================
    def draw_agent(self):

        rect = pygame.Rect(
            self.agent_pos[0] * self.cell_size,
            self.agent_pos[1] * self.cell_size,
            self.cell_size,
            self.cell_size
        )

        pygame.draw.rect(self.screen, (0, 200, 255), rect)

    # =====================================================
    # UPDATE FROM AI SYSTEM
    # =====================================================
    def update_from_system(self, output):

        # crude mapping: reward drives movement
        reward = sum(output["results"].values())

        if reward > 0.6:
            self.agent_pos[0] = min(self.grid_size - 1, self.agent_pos[0] + 1)

        elif reward < 0.3:
            self.agent_pos[1] = min(self.grid_size - 1, self.agent_pos[1] + 1)

        else:
            self.agent_pos[0] = max(0, self.agent_pos[0] - 1)

    # =====================================================
    # MAIN LOOP
    # =====================================================
    def run(self):

        running = True

        step = 0

        while running:

            self.screen.fill((0, 0, 0))

            for event in pygame.event.get():
                if event.type == pygame.QUIT:
                    running = False

            # -----------------------------
            # RUN AI STEP
            # -----------------------------
            output = self.controller.run_cycle_live(
                goal="visual_test",
                input_text="observe"
            )

            # -----------------------------
            # UPDATE VISUAL STATE
            # -----------------------------
            self.update_from_system(output)

            # -----------------------------
            # DRAW WORLD
            # -----------------------------
            self.draw_grid()
            self.draw_agent()

            pygame.display.flip()

            self.clock.tick(2)  # slow so you can see steps

            step += 1

        pygame.quit()