%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%?Q?learning?of?single?agent?move?in?N?rooms?
%?Matlab?Code?companion?of?
%?Q?Learning?by?Example
%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%?
function?q=ReinforcementLearning
clc;
format?short
format?compact

????%?Two?input:?R?and?gamma
????%?immediate?reward?matrix;?
????%?row?and?column?=?states;?-Inf?=?no?door?between?room
????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];

????gamma=0.80;????????????%?learning?parameter

????q=zeros（size（R））;??????%?initialize?Q?as?zeroq的行數(shù)和列數(shù)等于矩陣R的。
????q1=ones（size（R））*inf;??%?initialize?previo