kono/refo
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

add QTableFrame and clickable states that display a gui

Browse Source 
- remove org.javaTuple in favour of org.apache.common for tuples and circleQueue
- remove ViewListener from non-GUI Controller
- stateActionTable saves the last 10 states that changed. They will get displayed in QTable Frame
in JTextAreas
This commit is contained in:
kono
2020-01-01 23:54:18 +01:00
parent a8f8af1102
commit f4f1f7bd37
16 changed files with 334 additions and 136 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/main/java/core/gui/LearningInfoPanel.java
+24 -17
View File
@@ -26,24 +26,25 @@ public class LearningInfoPanel extends JPanel {
private JCheckBox drawEnvironmentCheckbox;
private JTextField learnMoreEpisodesInput;
private JButton learnMoreEpisodesButton;
private JButton showQTableButton;
public LearningInfoPanel(Learning learning, ViewListener viewListener){
public LearningInfoPanel(Learning learning, ViewListener viewListener) {
this.learning = learning;
setLayout(new BoxLayout(this, BoxLayout.Y_AXIS));
policyLabel = new JLabel();
discountLabel = new JLabel();
delayLabel = new JLabel();
if(learning instanceof Episodic){
if(learning instanceof Episodic) {
episodeLabel = new JLabel();
add(episodeLabel);
}
delaySlider = new JSlider(0,1000, learning.getDelay());
delaySlider = new JSlider(0, 1000, learning.getDelay());
delaySlider.addChangeListener(e -> viewListener.onDelayChange(delaySlider.getValue()));
add(policyLabel);
add(discountLabel);
if(learning.getPolicy() instanceof EpsilonPolicy){
if(learning.getPolicy() instanceof EpsilonPolicy) {
epsilonLabel = new JLabel();
epsilonSlider = new JSlider(0, 100, (int)((EpsilonPolicy)learning.getPolicy()).getEpsilon() * 100);
epsilonSlider = new JSlider(0, 100, (int) ((EpsilonPolicy) learning.getPolicy()).getEpsilon() * 100);
epsilonSlider.addChangeListener(e -> viewListener.onEpsilonChange(epsilonSlider.getValue() / 100f));
add(epsilonLabel);
add(epsilonSlider);
@@ -51,7 +52,7 @@ public class LearningInfoPanel extends JPanel {
toggleFastLearningButton = new JButton("Enable fast-learn");
fastLearning = false;
toggleFastLearningButton.addActionListener(e->{
toggleFastLearningButton.addActionListener(e -> {
fastLearning = !fastLearning;
delaySlider.setEnabled(!fastLearning);
epsilonSlider.setEnabled(!fastLearning);
@@ -71,10 +72,10 @@ public class LearningInfoPanel extends JPanel {
if(learning instanceof EpisodicLearning) {
learnMoreEpisodesInput = new JTextField();
learnMoreEpisodesInput.setMaximumSize(new Dimension(200,20));
learnMoreEpisodesInput.setMaximumSize(new Dimension(200, 20));
learnMoreEpisodesButton = new JButton("Learn More Episodes");
learnMoreEpisodesButton.addActionListener(e -> {
if (Util.isNumeric(learnMoreEpisodesInput.getText())) {
if(Util.isNumeric(learnMoreEpisodesInput.getText())) {
viewListener.onLearnMoreEpisodes(Integer.parseInt(learnMoreEpisodesInput.getText()));
} else {
learnMoreEpisodesInput.setText("");
@@ -83,9 +84,14 @@ public class LearningInfoPanel extends JPanel {
add(learnMoreEpisodesInput);
add(learnMoreEpisodesButton);
}
showQTableButton = new JButton("Show Q-Table");
showQTableButton.addActionListener(e -> {
viewListener.onShowQTable();
});
add(drawEnvironmentCheckbox);
add(smoothGraphCheckbox);
add(last100Checkbox);
add(showQTableButton);
refreshLabels();
setVisible(true);
}
@@ -93,17 +99,17 @@ public class LearningInfoPanel extends JPanel {
public void refreshLabels() {
policyLabel.setText("Policy: " + learning.getPolicy().getClass());
discountLabel.setText("Discount factor: " + learning.getDiscountFactor());
if(learning instanceof Episodic){
episodeLabel.setText("Episode: " + ((Episodic)(learning)).getCurrentEpisode() +
"\t Episodes to go: " + ((Episodic)(learning)).getEpisodesToGo() +
"\t Eps/Sec: " + ((Episodic)(learning)).getEpisodesPerSecond());
if(learning instanceof Episodic) {
episodeLabel.setText("Episode: " + ((Episodic) (learning)).getCurrentEpisode() +
"\t Episodes to go: " + ((Episodic) (learning)).getEpisodesToGo() +
"\t Eps/Sec: " + ((Episodic) (learning)).getEpisodesPerSecond());
}
if (learning.getPolicy() instanceof EpsilonPolicy) {
if(learning.getPolicy() instanceof EpsilonPolicy) {
epsilonLabel.setText("Exploration (Epsilon): " + ((EpsilonPolicy) learning.getPolicy()).getEpsilon());
epsilonSlider.setValue((int)(((EpsilonPolicy) learning.getPolicy()).getEpsilon() * 100));
epsilonSlider.setValue((int) (((EpsilonPolicy) learning.getPolicy()).getEpsilon() * 100));
}
delayLabel.setText("Delay (ms): " + learning.getDelay());
if(delaySlider.isEnabled()){
if(delaySlider.isEnabled()) {
delaySlider.setValue(learning.getDelay());
}
toggleFastLearningButton.setText(fastLearning ? "Disable fast-learning" : "Enable fast-learning");
@@ -112,11 +118,12 @@ public class LearningInfoPanel extends JPanel {
protected boolean isSmoothenGraphSelected() {
return smoothGraphCheckbox.isSelected();
}
protected boolean isLast100Selected(){
protected boolean isLast100Selected() {
return last100Checkbox.isSelected();
}
protected boolean isDrawEnvironmentSelected(){
protected boolean isDrawEnvironmentSelected() {
return drawEnvironmentCheckbox.isSelected();
}
}
src/main/java/core/gui/LearningView.java
+2
View File
@@ -8,5 +8,7 @@ import java.util.List;
public interface LearningView {
void repaintEnvironment();
void updateLearningInfoPanel();
void updateQTable();
void updateRewardGraph(final List<Double> rewardHistory);
void showQTableFrame();
}
src/main/java/core/gui/QTableFrame.java
+57
View File
@@ -0,0 +1,57 @@
package core.gui;
import core.State;
import core.StateActionTable;
import javax.swing.*;
import java.awt.*;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
public class QTableFrame<A extends Enum> extends JFrame {
private JLabel stateCountLabel;
private StateActionTable<A> stateActionTable;
private List<StateActionRow<A>> rows;
private JPanel areaWrapper;
public QTableFrame(StateActionTable<A> stateActionTable) {
super("Q-Table");
this.stateActionTable = stateActionTable;
rows = new ArrayList<>(10);
setDefaultCloseOperation(WindowConstants.HIDE_ON_CLOSE);
setLayout(new BorderLayout());
setPreferredSize(new Dimension(500, 500));
stateCountLabel = new JLabel();
add(BorderLayout.NORTH, stateCountLabel);
areaWrapper = new JPanel();
areaWrapper.setLayout(new BoxLayout(areaWrapper, BoxLayout.Y_AXIS));
for(int i = 0; i < 10; ++i) {
StateActionRow<A> a = new StateActionRow<>();
rows.add(a);
areaWrapper.add(a);
}
add(BorderLayout.CENTER, areaWrapper);
setVisible(false);
pack();
}
private void refreshAllTextAreas(){
for(StateActionRow<A> row : rows){
row.refreshLabels();
}
}
protected void refreshQTable() {
System.out.println("ref");
int stateCount = stateActionTable.getStateCount();
stateCountLabel.setText("Total states: " + stateCount);
int idx = -1;
for(Map.Entry<State, Map<A, Double>> entry : stateActionTable.getFirstStateEntriesForView()) {
if(++idx > rows.size() -1) break;
StateActionRow<A> row = rows.get(idx);
row.setState(entry.getKey());
row.setActionValues(entry.getValue());
}
refreshAllTextAreas();
}
}
src/main/java/core/gui/StateActionRow.java
+55
View File
@@ -0,0 +1,55 @@
package core.gui;
import core.State;
import lombok.Setter;
import javax.swing.*;
import java.awt.*;
import java.awt.event.MouseAdapter;
import java.awt.event.MouseEvent;
import java.util.Map;
@Setter
public class StateActionRow<A extends Enum> extends JTextArea {
private State state;
private Map<A, Double> actionValues;
public StateActionRow(){
this.state = null;
this.actionValues = null;
setMaximumSize(new Dimension(600, 100));
setEditable(false);
addMouseListener(new MouseAdapter() {
@Override
public void mousePressed(MouseEvent e) {
super.mousePressed(e);
showState();
}
});
}
protected void refreshLabels(){
if(state == null || actionValues == null) return;
System.out.println("refreshing");
StringBuilder sb = new StringBuilder(state.toString()).append("\n");
for(Map.Entry<A, Double> actionValue: actionValues.entrySet()){
sb.append("\t").append(actionValue.getKey()).append("\t").append(actionValue.getValue()).append("\n");
}
setText(sb.toString());
}
private void showState() {
if(state != null && state instanceof Visualizable){
new JFrame() {
{
JComponent stateComponent = ((Visualizable)state).visualize();
setPreferredSize(stateComponent.getPreferredSize());
setDefaultCloseOperation(WindowConstants.DISPOSE_ON_CLOSE);
add(stateComponent);
pack();
setVisible(true);
}
};
}
}
}
src/main/java/core/gui/View.java
+36 -32
View File
@@ -4,7 +4,8 @@ import core.Environment;
import core.algo.Learning;
import core.listener.ViewListener;
import lombok.Getter;
import org.javatuples.Pair;
import org.apache.commons.lang3.tuple.ImmutablePair;
import org.apache.commons.lang3.tuple.Pair;
import org.knowm.xchart.QuickChart;
import org.knowm.xchart.XChartPanel;
import org.knowm.xchart.XYChart;
@@ -16,7 +17,7 @@ import java.io.File;
import java.util.List;
import java.util.concurrent.CopyOnWriteArrayList;
public class View<A extends Enum> implements LearningView{
public class View<A extends Enum> implements LearningView {
private Learning<A> learning;
private Environment<A> environment;
@Getter
@@ -26,6 +27,7 @@ public class View<A extends Enum> implements LearningView{
@Getter
private JFrame mainFrame;
private JFrame environmentFrame;
private QTableFrame<A> qTableFrame;
private XChartPanel<XYChart> rewardChartPanel;
private ViewListener viewListener;
private JMenuBar menuBar;
@@ -36,11 +38,12 @@ public class View<A extends Enum> implements LearningView{
this.environment = environment;
this.viewListener = viewListener;
initMainFrame();
initQTableFrame();
}
private void initMainFrame() {
mainFrame = new JFrame();
mainFrame.setPreferredSize(new Dimension(1280, 720));
mainFrame.setPreferredSize(new Dimension(1000, 400));
mainFrame.setLayout(new BorderLayout());
menuBar = new JMenuBar();
fileMenu = new JMenu("File");
@@ -52,7 +55,7 @@ public class View<A extends Enum> implements LearningView{
fc.setCurrentDirectory(new File(System.getProperty("user.dir")));
int returnVal = fc.showOpenDialog(mainFrame);
if (returnVal == JFileChooser.APPROVE_OPTION) {
if(returnVal == JFileChooser.APPROVE_OPTION) {
viewListener.onLoadState(fc.getSelectedFile().toString());
}
}
@@ -62,7 +65,7 @@ public class View<A extends Enum> implements LearningView{
@Override
public void actionPerformed(ActionEvent e) {
String fileName = JOptionPane.showInputDialog("Enter file name", "path/to/file");
if(fileName != null){
if(fileName != null) {
viewListener.onSaveState(fileName);
}
}
@@ -78,7 +81,7 @@ public class View<A extends Enum> implements LearningView{
mainFrame.pack();
mainFrame.setVisible(true);
if (environment instanceof Visualizable) {
if(environment instanceof Visualizable) {
environmentFrame = new JFrame() {
{
add(((Visualizable) environment).visualize());
@@ -86,9 +89,21 @@ public class View<A extends Enum> implements LearningView{
setVisible(true);
}
};
}
}
private void initQTableFrame(){
qTableFrame = new QTableFrame<>(learning.getStateActionTable());
}
@Override
public void updateQTable() {
qTableFrame.refreshQTable();
}
public void showQTableFrame(){
updateQTable();
qTableFrame.setVisible(true);
}
private void initLearningInfoPanel() {
learningInfoPanel = new LearningInfoPanel(learning, viewListener);
@@ -109,32 +124,21 @@ public class View<A extends Enum> implements LearningView{
rewardChartPanel.setPreferredSize(new Dimension(300, 300));
}
public void showState(Visualizable state) {
new JFrame() {
{
JComponent stateComponent = state.visualize();
setPreferredSize(new Dimension(stateComponent.getWidth(), stateComponent.getHeight()));
add(stateComponent);
setVisible(true);
}
};
}
public void updateRewardGraph(final List<Double> rewardHistory) {
List<Integer> xValues;
List<Double> yValues;
if(learningInfoPanel.isLast100Selected()){
if(learningInfoPanel.isLast100Selected()) {
yValues = new CopyOnWriteArrayList<>(rewardHistory.subList(rewardHistory.size() - Math.min(rewardHistory.size(), 100), rewardHistory.size()));
xValues = new CopyOnWriteArrayList<>();
for(int i = rewardHistory.size() - Math.min(rewardHistory.size(), 100); i <rewardHistory.size(); ++i){
for(int i = rewardHistory.size() - Math.min(rewardHistory.size(), 100); i < rewardHistory.size(); ++i) {
xValues.add(i);
}
}else{
if(learningInfoPanel.isSmoothenGraphSelected()){
} else {
if(learningInfoPanel.isSmoothenGraphSelected()) {
Pair<List<Integer>, List<Double>> XYvalues = smoothenGraph(rewardHistory);
xValues = XYvalues.getValue0();
yValues = XYvalues.getValue1();
}else{
xValues = XYvalues.getKey();
yValues = XYvalues.getValue();
} else {
xValues = null;
yValues = rewardHistory;
}
@@ -145,37 +149,37 @@ public class View<A extends Enum> implements LearningView{
rewardChartPanel.repaint();
}
private Pair<List<Integer>, List<Double>> smoothenGraph(List<Double> original){
private Pair<List<Integer>, List<Double>> smoothenGraph(List<Double> original) {
int totalXPoints = 100;
List<Integer> xValues = new CopyOnWriteArrayList<>();
List<Double> tmp = new CopyOnWriteArrayList<>();
int meanBatch = original.size() / totalXPoints;
if(meanBatch < 1){
if(meanBatch < 1) {
meanBatch = 1;
}
int idx = 0;
int batchIdx = 0;
double batchSum = 0;
for(Double x: original) {
for(Double x : original) {
++idx;
batchSum += x;
if (idx == 1 || ++batchIdx % meanBatch == 0) {
if(idx == 1 || ++batchIdx % meanBatch == 0) {
tmp.add(batchSum / meanBatch);
xValues.add(idx);
batchSum = 0;
}
}
return new Pair<>(xValues, tmp);
return new ImmutablePair<>(xValues, tmp);
}
public void updateLearningInfoPanel() {
this.learningInfoPanel.refreshLabels();
}
public void repaintEnvironment(){
if (environmentFrame != null && learningInfoPanel.isDrawEnvironmentSelected()) {
public void repaintEnvironment() {
if(environmentFrame != null && learningInfoPanel.isDrawEnvironmentSelected()) {
environmentFrame.repaint();
}
}