跟着莫烦老师的强化学习教程时做的笔记,原贴:https://mofanpy.com/tutorials/machine-learning/reinforcement-learning/
Q table
#一维探索者
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 有多少种状态
ACTIONS = ['left', 'right'] # available actions 有两个可以选的动作
EPSILON = 0.9 # greedy police 选择动作的时候有90%选择最优动作
ALPHA = 0.1 # learning rate 学习率
GAMMA = 0.9 # discount factor 衰减度
MAX_EPISODES = 13 # maximum episodes 跑多少回合
FRESH_TIME = 0.3 # fresh time for one move 走一步花的时间
def build_q_table(n_states, actions): #create Q table 纵轴是status,横轴是action
table = pd.DataFrame(
np.zeros((n_states, len(actions))), # q_table initial values
columns=actions, # actions's name
)
# print(table) # show table
return table
def choose_action(state, q_table): #选择动作的功能
# 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 初始化的时候Q表都是0
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 选择Q表里面left和right中值更大的那个动作
return action_name
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 #返回新的奖励和下一个状态
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)
def rl():
# main part of RL loop
q_table = build_q_table(N_STATES, ACTIONS) #创建Q表
for episode in range(MAX_EPISODES):
step_counter = 0
S = 0
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] #估计值
if S_ != 'terminal':
q_target = R + GAMMA * q_table.iloc[S_, :].max() # next state is not terminal 真实值
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 更新下一趟的state参数
S = S_ # move to next state
update_env(S, episode, step_counter+1)
step_counter += 1
return q_table
if __name__ == "__main__":
q_table = rl()
print('\r\nQ-table:\n')
print(q_table)