資源簡介
Actor-Critic簡單應用例子,連續狀態空間,離散動作
代碼片段和文件信息
clc;
clear;
figure(8);
par=zeros(1100);
par2=zeros(1100);
time=zeros(1100);
sstep=zeros(1100);
for?j=1:1
????disp(‘------------------------------------------------------------------‘);
????episodes=100;??
????theta=zeros(541);
????distance=0;
????v=zeros(271);
????gamma=0.9;
????lambda=0.5;
????epsilon=10^(-20);
%???F=400*eye(10);
????pend_actions=2;
????for?r=1:episodes
????????disp(‘%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%‘);
????????noise=(2*rand(13)‘-1).*[2;2;0];%初始化狀態
????????state=[140;0;0]+0*noise;??
????????z=zeros(271);
????????step=0;
????????signal=0;
????????endsim=0;
????????mytime=cputime;
????????
????????while??endsim==0
????????????step=step+1;
????????????phi=computphi(state);
????????????phi_sa=zer
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????文件???????2765??2014-04-26?19:48??example\AC.asv
?????文件???????2776??2014-04-27?20:36??example\AC.m
?????文件????????414??2014-04-25?11:11??example\computphi.asv
?????文件????????420??2014-04-26?16:11??example\computphi.m
?????文件????????214??2014-04-25?17:38??example\computpi.m
?????文件????????214??2014-04-18?16:32??example\computpsi.m
?????文件????????691??2014-04-26?20:00??example\evaluate.m
?????文件????????140??2014-04-25?23:05??example\select.m
?????文件????????512??2014-04-26?00:11??example\simulator.asv
?????文件????????517??2014-04-27?20:51??example\simulator.m
?????目錄??????????0??2014-04-26?22:20??example
-----------?---------??----------?-----??----
?????????????????8663????????????????????11
- 上一篇:DCT 本文設計基于DCT的人臉識別系統
- 下一篇:AFD
評論
共有 條評論