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

distinguish learning and episodic learning, enable fast-learning without drawing every step to reduce lag

Browse Source 
- repainting every step on no time delay will certainly freeze the app, so "fast-learning" will disable it, only refreshing current episode label
- Added new abstract class "Episodic Learning". Maybe just use an interface instead?! Important because TD learning is not episodic, needs another way to represent the rewards received (maybe mean of last X rewards or sth)
- Opening two JFrames, one with learning infos and one with environment
This commit is contained in:
kono
2019-12-21 00:23:09 +01:00
parent 7db5a2af3b
commit 34e7e3fdd6
14 changed files with 188 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/main/java/core/gui/LearningInfoPanel.java
+29 -5
View File
@@ -1,7 +1,8 @@
package core.gui;
import core.algo.Episodic;
import core.algo.Learning;
import core.controller.ViewListener;
import core.listener.ViewListener;
import core.policy.EpsilonPolicy;
import javax.swing.*;
@@ -11,39 +12,62 @@ public class LearningInfoPanel extends JPanel {
private JLabel policyLabel;
private JLabel discountLabel;
private JLabel epsilonLabel;
private JLabel episodeLabel;
private JSlider epsilonSlider;
private JLabel delayLabel;
private JSlider delaySlider;
private JButton toggleFastLearningButton;
private boolean fastLearning;
public LearningInfoPanel(Learning learning, ViewListener viewListener){
this.learning = learning;
setLayout(new BoxLayout(this, BoxLayout.Y_AXIS));
policyLabel = new JLabel();
discountLabel = new JLabel();
epsilonLabel = new JLabel();
delayLabel = new JLabel();
if(learning instanceof Episodic){
episodeLabel = new JLabel();
add(episodeLabel);
}
delaySlider = new JSlider(0,1000, learning.getDelay());
delaySlider.addChangeListener(e -> viewListener.onDelayChange(delaySlider.getValue()));
add(policyLabel);
add(discountLabel);
if(learning.getPolicy() instanceof EpsilonPolicy){
epsilonLabel = new JLabel();
epsilonSlider = new JSlider(0, 100, (int)((EpsilonPolicy)learning.getPolicy()).getEpsilon() * 100);
epsilonSlider.addChangeListener(e -> viewListener.onEpsilonChange(epsilonSlider.getValue() / 100f));
add(epsilonLabel);
add(epsilonSlider);
}
toggleFastLearningButton = new JButton("Enable fast-learn");
fastLearning = false;
toggleFastLearningButton.addActionListener(e->{
fastLearning = !fastLearning;
delaySlider.setEnabled(!fastLearning);
epsilonSlider.setEnabled(!fastLearning);
viewListener.onFastLearnChange(fastLearning);
});
add(delayLabel);
add(delaySlider);
add(toggleFastLearningButton);
refreshLabels();
setVisible(true);
}
public void refreshLabels(){
public void refreshLabels() {
policyLabel.setText("Policy: " + learning.getPolicy().getClass());
discountLabel.setText("Discount factor: " + learning.getDiscountFactor());
if(learning.getPolicy() instanceof EpsilonPolicy){
epsilonLabel.setText("Exploration (Epsilon): " + ((EpsilonPolicy)learning.getPolicy()).getEpsilon());
if(learning instanceof Episodic){
episodeLabel.setText("Episode: " + ((Episodic)(learning)).getCurrentEpisode());
}
if (learning.getPolicy() instanceof EpsilonPolicy) {
epsilonLabel.setText("Exploration (Epsilon): " + ((EpsilonPolicy) learning.getPolicy()).getEpsilon());
epsilonSlider.setValue((int)(((EpsilonPolicy) learning.getPolicy()).getEpsilon() * 100));
}
delayLabel.setText("Delay (ms): " + learning.getDelay());
delaySlider.setValue(learning.getDelay());
toggleFastLearningButton.setText(fastLearning ? "Disable fast-learning" : "Enable fast-learning");
}
}