增强学习之q_learning

Q-learning的算法思想如下：

code as follows if you are interested in it.

"""
'---------T' our environment
A simple example for Reinforcement Learning using table lookup Q-learning method.
An agent "o" is on the left of a 1 dimensional world, the treasure is on the rightmost location.
Run this program and to see how the agent will improve its strategy of finding the treasure.
If you want to know more, please run this demo in your device
"""

import numpy as np
import pandas as pd
import time

np.random.seed(2)  # reproducible


N_STATES = 6   # the length of the 1 dimensional world
ACTIONS = ['left', 'right']     # available actions
EPSILON = 0.9   # greedy police
ALPHA = 0.1     # learning rate
GAMMA = 0.9    # discount factor
MAX_EPISODES = 13   # maximum episodes
FRESH_TIME = 0.3    # fresh time for one move

#创建q_table表
def build_q_table(n_states, actions):
    table = pd.DataFrame(
        np.zeros((n_states, len(actions))),     # q_table initial values
        columns=actions,    # actions's name
    )
    # print(table)    # show table
    return table

#选择一个action
def choose_action(state, q_table):
    # This is how to choose an action
    state_actions = q_table.iloc[state, :]
    if (np.random.uniform() > EPSILON) or ((state_actions == 0).all()):  # act non-greedy or state-action have no value，随机更像探索
        action_name = np.random.choice(ACTIONS)
    else:   # act greedy
        action_name = state_actions.idxmax()    # replace argmax to idxmax as argmax means a different function in newer version of pandas，贪心更像利用已经存储的记忆
    return action_name

#得到环境反馈
def get_env_feedback(S, A):
    # This is how agent will interact with the environment
    if A == 'right':    # move right
        if S == N_STATES - 2:   # terminate
            S_ = 'terminal'
            R = 1
        else:
            S_ = S + 1
            R = 0
    else:   # move left
        R = 0
        if S == 0:
            S_ = S  # reach the wall
        else:
            S_ = S - 1
    return S_, R

#更新环境
def update_env(S, episode, step_counter):
    # This is how environment be updated
    env_list = ['-']*(N_STATES-1) + ['T']   # '---------T' our environment
    if S == 'terminal':
        interaction = 'Episode %s: total_steps = %s' % (episode+1, step_counter)
        print('\r{}'.format(interaction), end='')
        time.sleep(2)
        print('\r                                ', end='')
    else:
        env_list[S] = 'o'
        interaction = ''.join(env_list)
        print('\r{}'.format(interaction), end='')
        time.sleep(FRESH_TIME)

#主循环
def rl():
    # main part of RL loop
    q_table = build_q_table(N_STATES, ACTIONS)
    print(q_table)
    for episode in range(MAX_EPISODES):
        step_counter = 0
        S = 0   #刚开始所处的位置
        is_terminated = False
        update_env(S, episode, step_counter)
        while not is_terminated:

            A = choose_action(S, q_table)
            S_, R = get_env_feedback(S, A)  # take action & get next state and reward
            q_predict = q_table.loc[S, A]
            if S_ != 'terminal':
                q_target = R + GAMMA * q_table.iloc[S_, :].max()   # next state is not terminal
            else:
                q_target = R     # next state is terminal
                is_terminated = True    # terminate this episode

            q_table.loc[S, A] += ALPHA * (q_target - q_predict)  # update，核心的东西
            S = S_  # move to next state ，移到下一个状态

            update_env(S, episode, step_counter+1)  #更新环境
            step_counter += 1
    return q_table


if __name__ == "__main__":
    q_table = rl()
    print('\r\nQ-table:\n')
    print(q_table)