我如何更改它以使用 q table 进行强化学习

How can I change this to use a q table for reinforcement learning

我正在通过仅使用一维数组向前和向后移动的简单版本学习 q-tables 和 运行。现在我正在尝试 4 方向移动并卡在控制人上。

我现在把 运行dom 移动下来,它最终会找到目标。但我希望它学习如何实现目标,而不是 运行 在目标上跌跌撞撞。因此,我将不胜感激有关在此代码中添加 qlearning 的任何建议。谢谢。

这是我的完整代码,因为它现在非常简单。

import numpy as np
import random
import math

world = np.zeros((5,5))
print(world)
# Make sure that it can never be 0 i.e the start point
goal_x = random.randint(1,4)
goal_y = random.randint(1,4)
goal = (goal_x, goal_y)
print(goal)
world[goal] = 1
print(world)

LEFT = 0
RIGHT = 1
UP = 2
DOWN = 3
map_range_min = 0
map_range_max = 5

class Agent:
    def __init__(self, current_position, my_goal, world):
        self.current_position = current_position
        self.last_postion = current_position
        self.visited_positions = []
        self.goal = my_goal
        self.last_reward = 0
        self.totalReward = 0
        self.q_table = world


    # Update the totoal reward by the reward        
    def updateReward(self, extra_reward):
        # This will either increase or decrese the total reward for the episode
        x = (self.goal[0] - self.current_position[0]) **2
        y = (self.goal[1] - self.current_position[1]) **2
        dist = math.sqrt(x + y)
        complet_reward = dist + extra_reward
        self.totalReward += complet_reward 

    def validate_move(self):
        valid_move_set = []
        # Check for x ranges
        if map_range_min < self.current_position[0] < map_range_max:
            valid_move_set.append(LEFT)
            valid_move_set.append(RIGHT)
        elif map_range_min == self.current_position[0]:
            valid_move_set.append(RIGHT)
        else:
            valid_move_set.append(LEFT)
        # Check for Y ranges
        if map_range_min < self.current_position[1] < map_range_max:
            valid_move_set.append(UP)
            valid_move_set.append(DOWN)
        elif map_range_min == self.current_position[1]:
            valid_move_set.append(DOWN)
        else:
            valid_move_set.append(UP)
        return valid_move_set

    # Make the agent move
    def move_right(self):
        self.last_postion = self.current_position
        x = self.current_position[0]
        x += 1
        y = self.current_position[1]
        return (x, y)
    def move_left(self):
        self.last_postion = self.current_position
        x = self.current_position[0]
        x -= 1
        y = self.current_position[1]
        return (x, y)
    def move_down(self):
        self.last_postion = self.current_position
        x = self.current_position[0]
        y = self.current_position[1]
        y += 1
        return (x, y)
    def move_up(self):
        self.last_postion = self.current_position
        x = self.current_position[0]
        y = self.current_position[1]
        y -= 1
        return (x, y)

    def move_agent(self):
        move_set = self.validate_move()
        randChoice = random.randint(0, len(move_set)-1)
        move = move_set[randChoice]
        if move == UP:
            return self.move_up()
        elif move == DOWN:
            return self.move_down()
        elif move == RIGHT:
            return self.move_right()
        else:
            return self.move_left()

    # Update the rewards
    # Return True to kill the episode
    def checkPosition(self):
        if self.current_position == self.goal:
            print("Found Goal")
            self.updateReward(10)
            return False
        else:
            #Chose new direction
            self.current_position = self.move_agent()
            self.visited_positions.append(self.current_position)
            # Currently get nothing for not reaching the goal
            self.updateReward(0)
            return True


gus = Agent((0, 0) , goal)
play = gus.checkPosition()
while play:
    play = gus.checkPosition()

print(gus.totalReward)

根据您的代码示例,我有一些建议:

  1. 将环境与代理分开。环境需要具有 new_state, reward = env.step(old_state, action) 形式的方法。此方法说明一个动作如何将您的旧状态转换为新状态。将您的状态和动作编码为简单的整数是个好主意。我强烈建议为此方法设置单元测试。

  2. 然后代理需要一个等效的方法action = agent.policy(state, reward)。作为第一步,您应该手动编写一个执行您认为正确的代理程序。例如,它可能只是试图前往目标位置。

  3. 考虑状态表示是否马尔可夫的问题。如果你对你访问过的所有过去状态都有记忆,那么你可以在这个问题上做得更好,那么这个状态就没有马尔可夫属性。最好状态表示应该是紧凑的(仍然是马尔可夫的最小集合)。

  4. 一旦这个结构是set-up,你就可以考虑真正学习一个Qtable。一种可能的方法(很容易理解但不一定那么有效)是 Monte Carlo 探索开始或 epsilon-soft 贪婪。一本好的 RL 书籍应该为任一变体提供伪代码。

自信的时候,就来openai gymhttps://gym.openai.com/ for some more detailed class structures. There are some hints about creating your own environments here: https://gym.openai.com/docs/#environments