更多代码: gitee主页：https://gitee.com/GZHzzz
博客主页： CSDN：https://blog.csdn.net/gzhzzaa

写在前面

• 作为一个新手，写这个强化学习-基础知识专栏是想和大家分享一下自己强化学习的学习历程，希望大家互相交流一起进步！在我的gitee收集了强化学习经典论文：强化学习经典论文，搭建了基于pytorch的典型智能体模型，大家一起多篇多交流，互相学习啊！

show me code, no bb

"""
Reinforcement learning maze example.
Red rectangle:          explorer.
Black rectangles:       hells       [reward = -1].
Yellow bin circle:      paradise    [reward = +1].
All other states:       ground      [reward = 0].
"""
import numpy as np
import pandas as pd
import numpy as np
import time
import sys
import tkinter as tk
 
UNIT = 40   # pixels   像素
MAZE_H = 10  # grid height
MAZE_W = 10  # grid width
 
class Maze(tk.Tk, object):
    def __init__(self):
        super(Maze, self).__init__()
        self.action_space = ['u', 'd', 'l', 'r']                #行为
        self.n_actions = len(self.action_space)                  #行为数
        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_W * UNIT
            self.canvas.create_line(x0, y0, x1, y1)   #画一条从(x0,y0)到(x1,y1)的线
        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            #画第一个黑色正方形
        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            #画第二个黑色正方形
        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     #画黄色的正方形
        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   #画红色的正方形
        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(0.5)
        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    #减40
        elif action == 1:   # down
            if s[1] < (MAZE_H - 1) * UNIT:
                base_action[1] += UNIT     #加40
        elif action == 2:   # right
            if s[0] < (MAZE_W - 1) * UNIT:
                base_action[0] += UNIT    #右移40
        elif action == 3:   # left
            if s[0] > UNIT:               #左移40
                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.hell1), self.canvas.coords(self.hell2)]:
            reward = -1
            done = True
            s_ = 'terminal'
        else:
            reward = 0
            done = False
        return s_, reward, done
 
    def render(self):
        time.sleep(0.1)
        self.update()
 
class QLearningTable:
    def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9):
        '''
        :param actions:    行为
        :param learning_rate: 学习率, 来决定这次的误差有多少是要被学习的
        :param reward_decay: 是折扣因子，表示时间的远近对回报的影响程度，为0表示之看当前状态采取行动的reward。 
        :param e_greedy: 是用在决策上的一种策略, 比如 epsilon = 0.9 时, 就说明有90% 的情况我会按照 Q 表的最优值选择行为, 10% 的时间使用随机选行为
        '''
        self.actions = actions  # a list
        self.lr = learning_rate
        self.gamma = reward_decay
        self.epsilon = e_greedy
        self.q_table = pd.DataFrame(columns=self.actions, dtype=np.float64)
 
    def choose_action(self, observation):
        self.check_state_exist(observation)
        # action selection
        if np.random.uniform() < self.epsilon:
            # choose best action
            state_action = self.q_table.loc[observation, :]
            # some actions may have the same value, randomly choose on in these actions
            action = np.random.choice(state_action[state_action == np.max(state_action)].index)
        else:
            # choose random action
            action = np.random.choice(self.actions)
        return action
 
    def learn(self, s, a, r, s_):
        self.check_state_exist(s_)
        q_predict = self.q_table.loc[s, a]
        if s_ != 'terminal':
            q_target = r + self.gamma * self.q_table.loc[s_, :].max()  # next state is not terminal
        else:
            q_target = r  # next state is terminal
        self.q_table.loc[s, a] += self.lr * (q_target - q_predict)  # update
 
    def check_state_exist(self, state):
        if state not in self.q_table.index:
            # append new state to q table
            self.q_table = self.q_table.append(
                pd.Series(
                    [0]*len(self.actions),
                    index=self.q_table.columns,
                    name=state,
                )
            )
 
def update():
    for episode in range(100):
        # initial observation
        observation = env.reset()
        while True:
            # fresh env
            env.render()
            # RL choose action based on observation
            action = RL.choose_action(str(observation))
            # RL take action and get next observation and reward
            observation_, reward, done = env.step(action)
            # RL learn from this transition
            RL.learn(str(observation), action, reward, str(observation_))
            # swap observation
            observation = observation_
            # break while loop when end of this episode
            if done:
                break
    print(RL.q_table)
    RL.q_table.to_csv("./1.csv")
    # end of game
    print('game over')
    env.destroy()
if __name__ == "__main__":
    env = Maze()
    RL = QLearningTable(actions=list(range(env.n_actions)))
    # print(RL.q_table)
    env.after(100, update)
    # print("hahah")
    # print(RL.q_table)
    env.mainloop()

• 代码全部亲自跑过，你懂的！

结果展示

写在最后

十年磨剑，与君共勉！
更多代码：gitee主页：https://gitee.com/GZHzzz
博客主页：CSDN：https://blog.csdn.net/gzhzzaa

• Fighting!

基于pytorch的经典模型：基于pytorch的典型智能体模型
强化学习经典论文：强化学习经典论文

while True:
	Go life

谢谢点赞交流！(❁´◡`❁)