처음 시작하는 곳
main.m 에서 시작하여 초기에 initsimulation.m에 있는 initsimulation 함수를 호출한다.
main.m
initSimulation;
%% ----- Main loop
while(true)
버튼이 눌려지면 모드가 변경이 되고 변경된 모드에 의해서 작업이 수행이 되는 형식으로 진행이 된다.
elseif( strcmp(mode,'Start2') )
mode = '';
info_s1 = sprintf('%sd%21sd%22s.2f', 'Trials:', j-1, 'Steps:', steps2, 'Total reward:', reward2);
for j = j:max_trials
subplot(h_plot2(1));
[nn_params, Q_nn, Q_est, reward2, steps2, n_crash2, cost, info_s2] = ...
nnTrials(nn_params, input_layer_size, hidden_layer_size,...
output_layer_size, alpha2, gamma, T2, actions, max_steps,...
n_crash2, stadium_option2, h_car2, h_poly2, h_circ2, radius, wheel_radius, info_s1, h_text2);
subplot(h_plot2(1));
delete(h_car2);
h_car2 = createCarCircle(radius, sensor_lengde, 'b');
drawnow;
if( strcmp(mode,'Pause2') ), break; end
if(T2 > 1.0e-3), T2 = 0.95*T2; end
info_s1 = sprintf('%sd%21sd%22s.2f', 'Trials:', j, 'Steps:', steps2, 'Total reward:', reward2);
info_s = sprintf('%s\n%s', info_s1, info_s2);
set(h_text2, 'String', info_s);
n_steps2 = n_steps2 + steps2;
tot_steps2 = tot_steps2 + steps2;
total_reward2 = total_reward2 + reward2;
cost_fun(j) = cost;
if( mod(j,10) == 0)
n2 = n2 + 1;
x2(n2) = n2-1;
y3(n2) = n_steps2/10;
y4(n2) = total_reward2;
subplot(h_plot2(2));
plot(x2,y3);
xlabel('Trials x10');
ylabel('Average steps each 10th trials');
subplot(h_plot2(3));
plot(x2,y4);
title('Total reward');
xlabel('Trials x10');
ylabel('Accumulated reward');
n_steps2 = 0;
subplot(h_plot2(1));
drawnow;
end
if(j == 300 && ~figure2)
set(h_button2(1), 'BackGroundColor', [0.4,0.4,0.4], 'Enable', 'off');
set(h_button2(2), 'BackGroundColor', 'b', 'Enable', 'on');
figure2 = true;
end
if(mod(j,50) == 0), clc; end
Tekst = sprintf('Trials: %d', j);
fprintf([Tekst,'\n']);
end
end
initsimulation.m
% GUI
[h_plot1, h_plot2, h_text1, h_text2, h_button1, h_button2] = createSimulation(xlimit, ylimit, max_trials, max_steps,...
alpha1, alpha2, gamma, epsilon, T1);
% Simulation Environments
subplot(h_plot1(1));
[h_poly1, h_circ1] = createStadium(stadium_option1); ---> createStadium.m
h_car1 = createCarCircle(radius, sensor_lengde, 'b'); ----> createCarCircle
subplot(h_plot2(1));
[h_poly2, h_circ2] = createStadium(stadium_option2);
h_car2 = createCarCircle(radius, sensor_lengde, 'b');
initSimulation.m 에 있는 createSimulation 함수 호출 ---> createSimulation.m에 createSimulation 함수 원형
방식이 두가지가 있는 것으로 추정됨 - Tab에 의해서 결정이 됨
%% ----- Tab 1: Q-Table
%% ----- Tab 2: Neural Network
버튼 및 callback 함수
Tab 2: Neural Network
start_button2 = uicontrol(NN_panel, 'Style', 'pushbutton', 'BackGroundColor', 'g', 'String', 'Start', 'Position', [800, 220, 90, 45]);
pause_button2 = uicontrol(NN_panel, 'Style', 'pushbutton', 'BackGroundColor', [0.4,0.4,0.4],...
'Enable', 'off', 'String', 'Pause', 'Position', [920, 220, 90, 45]);
upload_button2 = uicontrol(NN_panel, 'Style', 'pushbutton', 'BackGroundColor', 'y',...
'Enable', 'on', 'String', 'Upload', 'Position', [800, 140, 90, 45]);
save_button2 = uicontrol(NN_panel, 'Style', 'pushbutton', 'BackGroundColor', [0.4,0.4,0.4],...
'Enable', 'off', 'String', 'Save', 'Position', [920, 140, 90, 45]);
reset_button2 = uicontrol(NN_panel, 'Style', 'pushbutton', 'BackGroundColor', [0.4,0.4,0.4],...
'Enable', 'off', 'String', 'Reset', 'Position', [855, 60, 100, 50]);
%% ----- Callback functions
set(start_button1, 'callback', {@funStart1, pause_button1, reset_button1, start_button2, pause_button2,...
reset_button2, upload_button1, save_button1, upload_button2, save_button2});
set(pause_button1, 'callback', {@funPause1, start_button1, reset_button1, start_button2, pause_button2,...
reset_button2, upload_button1, save_button1, upload_button2, save_button2});
set(reset_button1, 'callback', {@funReset1, start_button1, pause_button1, save_button1});
set(upload_button1, 'callback', @funUpload1);
set(save_button1, 'callback', @funSave1);
set(start_button2, 'callback', {@funStart2, start_button1, pause_button1, reset_button1, pause_button2,...
reset_button2, upload_button1, save_button1, upload_button2, save_button2});
set(pause_button2, 'callback', {@funPause2, start_button1, pause_button1, reset_button1, start_button2,...
reset_button2, upload_button1, save_button1, upload_button2, save_button2});
set(reset_button2, 'callback', {@funReset2, start_button2, pause_button2, save_button2});
set(upload_button2, 'callback', @funUpload2);
set(save_button2, 'callback', @funSave2);
명령
mode 변수 있는 값에 따라 명령을 수행함
Reset1
Upload1
Save1
Reset2
Upload2
Save2
Start1
Pause1
Start2
Pause2
Static
Dynamic
Start2 -> for j = j:max_trials
-> nnTrials
circularMotion -> rotate
nnFeedForward -> reshape
-> tanhActivation
nnSoftMaxSelection -> getBestAction
doActionCircle -> Move forward/Turn left/Turn right 각속도 계산
-> moveCarCircle -> rotate
-> moveSensor
checkCrash -> obstacle_polygon xxxxx
-> obstacle_circle xxxxx
-> obstacleCrash
-> sensorValues -> sensor_vertices xxxx
-> sensor_temp xxxxxx
nnGetReward
computeQEstimate -> nnFeedForward
nnBackPropagation
-> reshape
-> zeros
-> length
-> tanhActivation
-> tanhDerivative
gradientDescent
