本篇文章主要介绍在gym环境下env环境编写（未待完续，空闲更新）

经典的迷宫宝藏例子

import numpy as np
import time
import tkinter as tk # 窗口界面库

UNIT = 40   # 像素
MAZE_H = 5  # 高宽格子数
MAZE_W = 3

class Maze(tk.Tk): # 新类继承父类tkinter.Tk
    def __init__(self):
        super(Maze, self).__init__() # super类继承方法,初始化
        self.action_space = ['u', 'd', 'l', 'r']
        self.n_actions = len(self.action_space)
        self.title('maze')
        self.geometry('{0}x{1}'.format(MAZE_H * UNIT, MAZE_H * UNIT)) # format格式化函数 geometry分辨率函数
        self._build_maze()

    def _build_maze(self):
        self.canvas = tk.Canvas(self, bg='white', # tk画图组件
                           height=MAZE_H * UNIT,
                           width=MAZE_W * UNIT)
        for c in range(0, MAZE_W * UNIT, UNIT): # 网格
            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_W * UNIT, r
            self.canvas.create_line(x0, y0, x1, y1)

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

        hell2_center = origin + np.array([UNIT * 0, UNIT * 1])
        self.hell2 = self.canvas.create_rectangle(
            hell2_center[0] - 15, hell2_center[1] - 15,
            hell2_center[0] + 15, hell2_center[1] + 15,
            fill='black')
        hell3_center = origin + np.array([UNIT * 1, UNIT * 1])
        self.hell3 = self.canvas.create_rectangle(
            hell3_center[0] - 15, hell3_center[1] - 15,
            hell3_center[0] + 15, hell3_center[1] + 15,
            fill='black')
        hell6_center = origin + np.array([UNIT * 1, UNIT * 3])
        self.hell6 = self.canvas.create_rectangle(
            hell6_center[0] - 15, hell6_center[1] - 15,
            hell6_center[0] + 15, hell6_center[1] + 15,
            fill='black')
        hell7_center = origin + np.array([UNIT * 2, UNIT * 3])
        self.hell7 = self.canvas.create_rectangle(
            hell7_center[0] - 15, hell7_center[1] - 15,
            hell7_center[0] + 15, hell7_center[1] + 15,
            fill='black')
        oval_center = origin + np.array([UNIT * 2, UNIT * 4]) # 宝藏
        self.oval = self.canvas.create_oval(
            oval_center[0] - 15, oval_center[1] - 15,
            oval_center[0] + 15, oval_center[1] + 15,
            fill='yellow')
        self.rect = self.canvas.create_rectangle( # 主体
            origin[0] - 15, origin[1] - 15,
            origin[0] + 15, origin[1] + 15,
            fill='red')

        self.canvas.pack() # 打包

    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 self.canvas.coords(self.rect)

    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

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

        # reward function
        if s_ == self.canvas.coords(self.oval):
            reward = 1
            done = True
            s_ = 'terminal'
        elif s_ in [self.canvas.coords(self.hell2), self.canvas.coords(self.hell3),
                    self.canvas.coords(self.hell6), self.canvas.coords(self.hell7)]:
            reward = -1
            done = True
            s_ = 'terminal'
        else:
            reward = 0
            done = False

        return s_, reward, done

    def render(self):
        time.sleep(0.1)
        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()

经典的CartP例子