幾種算法

不斷嘗試達到目標

import numpy as np

import pandas as pd

class qlearning_table:

def__init__(self,actions,learning_rate=0.01,reward_decay=0.9,e_greedy=0.9)

self.actions=actions

self.lr=learning_rate

self.gamma=reward_decay

self.epsilon=e_greedy

self.q_table=pd.DataFrame(columns=self.actions)

def choose_action(self,observation):

self.check_state_exist(observation)

#choose action selection

np.random.uniform()<self.epsilon:

#choose best action

state_action=self.q_table.ix[observation,:]

state_action=state_action.reindex(np.random.permutation(state_action.index))

action=state_action.argmax()

else:

action=np.random.choice(self.action)

return action

def learn(self,s,a,r,s_):

self.check_state_exist(s_)

q_predict=self.q_table.ix[s,a]

if s_ !='terminal':

q_target=r+self.gamma*self.q_table

else:

q_target=r#next state is terminal

self.q_table.ix[s,a]+=self.lr*(q_target-q_predict)#update

def check_state_exist(self,state):

if state not in self.q_table.append(

pd.Series(

[0]*len(self.action),

index=self.q_table.columns,

name=state,))

def check_state_exist(self,state):