qlsimulator.java

Reinforcement Learning

import java.awt.BorderLayout;
import java.awt.Color;
import java.awt.Graphics;
import java.awt.event.ActionEvent;
import java.awt.event.ActionListener;
import java.io.File;
import java.io.FileInputStream;
import java.io.ObjectInputStream;
import java.text.DecimalFormat;
import java.util.Vector;
import java.util.zip.GZIPInputStream;

import javax.swing.BorderFactory;
import javax.swing.DebugGraphics;
import javax.swing.JButton;
import javax.swing.JCheckBox;
import javax.swing.JFileChooser;
import javax.swing.JLabel;
import javax.swing.JPanel;
import javax.swing.JScrollPane;
import javax.swing.JSeparator;
import javax.swing.JTextField;
import javax.swing.SwingConstants;
import javax.swing.WindowConstants;
import javax.swing.border.TitledBorder;

public class QLSimulator extends javax.swing.JFrame 
						 implements ActionListener
{
	private JPanel jPanel;
	private JButton jLoadButton;
	private JSeparator jSeparator1;
	private JButton jInitializeButton;
	private JButton jStepButton;
	private JButton jCycleButton;
	private JFileChooser fc;
	private JLabel jLabelSqSize;
	private JCheckBox jDecayLRCheckBox;
	private JTextField jDelayTextField;
	private JLabel jDelayLabel;
	private JLabel jConvErrorLabel;
	private JTextField jConverErrorTextField;
	private JCheckBox jPolicyCheckBox;
	private JCheckBox jValuesCheckBox;
	private JButton jUpdateButton;
	private JButton jRefreshButton;
	private JLabel jStatusLabel;
	private JTextField jFileNameTextField;
	private JTextField jCyclesTextField;
	private JTextField sqSizeTextField;
	private JTextField jLearnRateTextField; 
	private JTextField pjogTextField;
	private JLabel JLabelPJOG;
	private JLabel jLabelLearningRate;
	//	private Algorithms alg = null;//this is commented for q learning customization
	
	private Maze myMaze = null;
	private QLearning ql;
	private boolean ShowValue = true;
	private boolean ShowPolicy = true;
	private boolean Animate = true;
	
	DecimalFormat df = new DecimalFormat("0.0");
    private JScrollPane jScrollPane;
    
	private String mazeStatus = "Load Maze First...";
	private String algorithmStatus = "";
    private JTextField jEpsilonTextField;
    private JLabel jLabelEpsilon;
    private JCheckBox jAnimateCheckBox;
    private JButton jEpisodeButton;
	
	{
		//Set Look & Feel
		try {
			javax.swing.UIManager.setLookAndFeel("com.sun.java.swing.plaf.windows.WindowsLookAndFeel");
		} catch(Exception e) {
			e.printStackTrace();
		}
	}
	
	/**
	 * Auto-generated main method to display this JFrame
	 */
	public static void main(String[] args) {
		QLSimulator inst = new QLSimulator();
		inst.setVisible(true);
	}
	
	public QLSimulator() {
		super("RL-MDP:Simulation");
		initGUI();
		
	}
	
	private void initGUI() {
		try {
		    this.setSize(1000, 800);
			this.setExtendedState(MAXIMIZED_BOTH);
			setDefaultCloseOperation(WindowConstants.DISPOSE_ON_CLOSE);
			{
				jPanel = new JPanel();
				this.getContentPane().add(jPanel, BorderLayout.CENTER);
				jPanel.setLayout(null);
				jPanel.setBackground(new java.awt.Color(235, 241, 238));
				jPanel.setPreferredSize(new java.awt.Dimension(900, 700));
			}
			
			{
				jLoadButton = new JButton();
				jPanel.add(jLoadButton);
				jLoadButton.setText("LoadMaze...");
				jLoadButton.setBounds(25, 58, 110, 28);
				jLoadButton.setActionCommand("LoadMaze");
				jLoadButton.addActionListener(this);
			}
			{
				JLabelPJOG = new JLabel();
				jPanel.add(JLabelPJOG);
				JLabelPJOG.setText("PJOG");
				JLabelPJOG.setBounds(20, 105, 70, 21);
				JLabelPJOG.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				pjogTextField = new JTextField();
				jPanel.add(pjogTextField);
				pjogTextField.setText("0.3");
				pjogTextField.setBounds(95, 104, 40, 20);
				pjogTextField.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				jLabelEpsilon = new JLabel();
				jPanel.add(jLabelEpsilon);
				jLabelEpsilon.setText("Epsilon");
				jLabelEpsilon.setBounds(20, 126, 70, 21);
				jLabelEpsilon.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				jEpsilonTextField = new JTextField();
				jPanel.add(jEpsilonTextField);
				jEpsilonTextField.setText("0.1");
				jEpsilonTextField.setBounds(95, 125, 40, 20);
				jEpsilonTextField.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				jConvErrorLabel = new JLabel();
				jPanel.add(jConvErrorLabel);
				jConvErrorLabel.setText("Precision");
				jConvErrorLabel.setBounds(20, 147, 70, 21);
				jConvErrorLabel.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				jConverErrorTextField = new JTextField();
				jPanel.add(jConverErrorTextField);
				jConverErrorTextField.setText("0.001");
				jConverErrorTextField.setBounds(95, 146, 40, 20);
				jConverErrorTextField.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				jLabelLearningRate = new JLabel();
				jPanel.add(jLabelLearningRate);
				jLabelLearningRate.setText("Learning Rate");
				jLabelLearningRate.setBounds(20, 168, 70, 21);
				jLabelLearningRate.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				jLearnRateTextField = new JTextField();
				jPanel.add(jLearnRateTextField);
				jLearnRateTextField.setText("0.7");
				jLearnRateTextField.setBounds(95, 167, 40, 20);
				jLearnRateTextField.setHorizontalAlignment(SwingConstants.RIGHT);
			}
            {
                jDecayLRCheckBox = new JCheckBox();
                jPanel.add(jDecayLRCheckBox);
                jDecayLRCheckBox.setText("Decaying LR");
                jDecayLRCheckBox.setBounds(36, 195, 95, 17);
                jDecayLRCheckBox.setOpaque(false);
                jDecayLRCheckBox.setSelected(true);
                jDecayLRCheckBox.addActionListener(this);
            }
			{
			    jInitializeButton = new JButton();
				jPanel.add(jInitializeButton);
				jInitializeButton.setText("Initialize");
				jInitializeButton.setBounds(25, 223, 110, 28);
				jInitializeButton.addActionListener(this);
				jInitializeButton.setActionCommand("Initialize");
			}
			{
				jUpdateButton = new JButton();
				jPanel.add(jUpdateButton);
				jUpdateButton.setText("Update");
				jUpdateButton.setBounds(25, 258, 110, 28);
				jUpdateButton.setActionCommand("Update");
				jUpdateButton.addActionListener(this);
			}
			{
				jStepButton = new JButton();
				jPanel.add(jStepButton);
				jStepButton.setText("Step");
				jStepButton.setBounds(25, 314, 110, 28);
				jStepButton.addActionListener(this);
				jStepButton.setActionCommand("Step");
			}
			{
				jEpisodeButton = new JButton();
				jPanel.add(jEpisodeButton);
				jEpisodeButton.setText("Episode");
				jEpisodeButton.setBounds(25, 350, 110, 28);
				jEpisodeButton.addActionListener(this);
				jEpisodeButton.setActionCommand("Episode");
			}
			{
			    jCyclesTextField = new JTextField();
			    jPanel.add(jCyclesTextField);
			    jCyclesTextField.setText("1000");
			    jCyclesTextField.setBounds(25, 387, 35, 26);
			}
			{
				jCycleButton = new JButton();
				jPanel.add(jCycleButton);
				jCycleButton.setText("Cycles");
				jCycleButton.setBounds(65, 386, 70, 28);
				jCycleButton.addActionListener(this);
				jCycleButton.setActionCommand("Cycles");
			}

			{
				jLabelSqSize = new JLabel();
				jPanel.add(jLabelSqSize);
				jLabelSqSize.setText("Square Size");
				jLabelSqSize.setBounds(20, 445, 70, 21);
				jLabelSqSize.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				sqSizeTextField = new JTextField();
				jPanel.add(sqSizeTextField);
				sqSizeTextField.setText("80");
				sqSizeTextField.setBounds(96, 446, 40, 20);
				sqSizeTextField.setHorizontalAlignment(SwingConstants.RIGHT);
				sqSizeTextField.addActionListener(this);
			}
			{
				jDelayLabel = new JLabel();
				jPanel.add(jDelayLabel);
				jDelayLabel.setText("Delay(in ms)");
				jDelayLabel.setBounds(22, 470, 70, 21);
				jDelayLabel.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				jDelayTextField = new JTextField();
				jPanel.add(jDelayTextField);
				jDelayTextField.setText("30");
				jDelayTextField.setBounds(96, 472, 40, 20);
				jDelayTextField.setHorizontalAlignment(SwingConstants.RIGHT);
			}
			{
				jRefreshButton = new JButton();
				jPanel.add(jRefreshButton);
				jRefreshButton.setText("Refresh");
				jRefreshButton.setBounds(26, 500, 110, 28);
				jRefreshButton.setActionCommand("Refresh");
				jRefreshButton.addActionListener(this);
			}
			{
				jValuesCheckBox = new JCheckBox();
				jPanel.add(jValuesCheckBox);
				jValuesCheckBox.setText("Show Values");
				jValuesCheckBox.setBounds(35, 553, 93, 17);
				jValuesCheckBox.setOpaque(false);
				jValuesCheckBox.setSelected(true);
				jValuesCheckBox.addActionListener(this);
			}
			{
				jPolicyCheckBox = new JCheckBox();
				jPanel.add(jPolicyCheckBox);
				jPolicyCheckBox.setText("Show Policy");
				jPolicyCheckBox.setBounds(35, 573, 85, 17);
				jPolicyCheckBox.setOpaque(false);
				jPolicyCheckBox.setSelected(true);
				jPolicyCheckBox.addActionListener(this);
			}
			{
				jAnimateCheckBox = new JCheckBox();
				jPanel.add(jAnimateCheckBox);
				jAnimateCheckBox.setText("Animate");
				jAnimateCheckBox.setBounds(35, 593, 85, 17);
				jAnimateCheckBox.setOpaque(false);
				jAnimateCheckBox.setSelected(true);
				jAnimateCheckBox.addActionListener(this);
			}
			
			
			{
				jSeparator1 = new JSeparator();
				jPanel.add(jSeparator1);
				jSeparator1.setBounds(161, 2, 4, 400);
				jSeparator1.setBorder(BorderFactory.createTitledBorder(
						null,
						"",
						TitledBorder.LEADING,
						TitledBorder.TOP,
						new java.awt.Font("MS Sans Serif", 0, 11),
						new java.awt.Color(0, 0, 0)));
			}
			{
				jStatusLabel = new JLabel();
				jPanel.add(jStatusLabel);
				jStatusLabel.setText("Load Maze First... | Q-learning");
				jStatusLabel.setBounds(182, 14, 770, 34);
				jStatusLabel.setBackground(new java.awt.Color(192,192,192));
				jStatusLabel.setBorder(BorderFactory.createTitledBorder(null, "", TitledBorder.LEADING, TitledBorder.TOP, new java.awt.Font("MS Sans Serif",0,11), new java.awt.Color(0,0,0)));
				jStatusLabel.setFont(new java.awt.Font("Georgia",1,12));
				jStatusLabel.setDebugGraphicsOptions(DebugGraphics.NONE_OPTION);
				jStatusLabel.setOpaque(true);
				jStatusLabel.setHorizontalAlignment(SwingConstants.CENTER);
				jStatusLabel.setPreferredSize(new java.awt.Dimension(984, 35));
			}

		} catch (Exception e) {
			e.printStackTrace();
		}
	}
	
	public void actionPerformed(ActionEvent evt)
	{