資源簡介
Q強化學習matlab源代碼，注釋詳細，本人親自運行測試。
代碼片段和文件信息
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%?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的行數和列數等于矩陣R的。
????q1=ones（size（R））*inf;??%?initialize?previo- 上一篇：matlab實現線性卷積和循環卷積
- 下一篇：PCA matlab代碼
評論
共有 條評論