%?Q學(xué)習(xí)例程
addpath（‘modules‘）;
%%?%%%%%%%%%%%%%%%%%%%%%%%%%?Q學(xué)習(xí)初始設(shè)置?%%%%%%%%%%%%%%%%%%%%%%%%%
%?設(shè)置學(xué)習(xí)率參數(shù)γ
????gamma=0.80;
%?設(shè)置獎(jiǎng)勵(lì)矩陣R
????R=[-inf-inf-inf-inf???0?-inf;
???????-inf-inf-inf???0-inf?100;
???????-inf-inf-inf???0-inf?-inf;
???????-inf???0???0-inf???0?-inf;
??????????0-inf-inf???0-inf?100;
???????-inf???0-inf-inf???0?100];
%?初始化知識(shí)矩陣Q
????Q=zeros（size（R））;
%?設(shè)置目標(biāo)
????Target=6;
%?收斂判斷符
????count=0;
????Q_last=ones（size（R））*inf;
%%?%%%%%%%%%%%%%%%%%%%%%%%%%%%?強(qiáng)化學(xué)習(xí)?%%%%%%%%%%%%%%%%%%%%%%%%%%%
%?定義最大學(xué)習(xí)次數(shù)
episode_max=50000;
%?迭代學(xué)習(xí)
????for?episode=0:episode_max
????%%?選擇隨機(jī)初始狀態(tài)
????%?讀取狀態(tài)總數(shù)
????????state_num=size（R1）;
????%?選擇隨機(jī)初始狀態(tài)
????????state=randperm（state_num1）;
????%%?隨機(jī)搜索直到到達(dá)目標(biāo)
????????while?1
????????%%?根據(jù)當(dāng)前狀態(tài)隨機(jī)選擇一個(gè)可執(zhí)行的行為
????????%?找出可執(zhí)行的行為
????????????choices=find（?R（state:）>=0?）;
????????%?隨機(jī)選擇一個(gè)可執(zhí)行行為
????????????action=act_rand_select（?choices?）;
????????%%?根據(jù)下一個(gè)狀態(tài)更新Q表
????????%?根據(jù)所選行為到達(dá)下一個(gè)狀態(tài)
????????????ne

?屬性????????????大小?????日期????時(shí)間???名稱(chēng)
-----------?---------??----------?-----??----
?????文件????????2618??2018-03-17?18:14??Q_learning\Q_learning.m
?????目錄???????????0??2018-03-16?16:52??Q_learning\modules\
?????文件?????????369??2018-03-16?16:00??Q_learning\modules\act_rand_select.m
?????文件?????????504??2018-03-16?17:20??Q_learning\modules\conver_check.m
?????目錄???????????0??2018-03-16?22:52??Q_learning\