state_num=6;
episode_num=300;

%初始化
gammer=0.8;??%給定折扣因子
reward_R=[
????-1-1-1-10-1;???%設置獎勵矩陣R
????-1-1-10-1100;
????-1-1-10-1-1;
????-100-10-1;
????0-1-10-1100;
????-10-1-10100;
????]
Q_table=zeros（size（reward_R））;??%設置初始化矩陣Q
final_state=6;
%For?each?episode
for?i=1:episode_num
????current_state=randperm（state_num1）;???%隨機選擇一個狀態
????while?current_state~=final_state
????action_option=find（reward_R（