wfolsom/cs8803p4
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fixed unit tests, changed MDP generation to more reasonably seek the goal state, avoiding premature end of game.

Browse Source 
Removed unused google-code classes.
Regenerate policy when AdaptiveComPlayer.setTarget() is called.
This commit is contained in:
Woody Folsom
2012-04-30 17:37:37 -04:00
parent 3800436cd9
commit 8f92ae65d8
19 changed files with 53 additions and 939 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
test/aima/core/probability/mdp/MarkovDecisionProcessTest.java
View File

@@ -5,91 +5,57 @@ import junit.framework.Assert;
import org.junit.Before;
import org.junit.Test;
import aima.core.environment.cellworld.Cell;
import aima.core.environment.cellworld.CellWorld;
import aima.core.environment.cellworld.CellWorldAction;
import aima.core.environment.cellworld.CellWorldFactory;
import aima.core.environment.gridworld.GridCell;
import aima.core.environment.gridworld.GridWorld;
import aima.core.environment.gridworld.GridWorldAction;
import aima.core.environment.gridworld.GridWorldFactory;
import aima.core.probability.example.MDPFactory;
import aima.core.probability.mdp.MarkovDecisionProcess;
/**
*
* @author Ciaran O'Reilly
* @author Ravi Mohan
*
* Based on MarkovDecisionProcessTest by Ciaran O'Reilly and Ravi Mohan. Used under MIT license.
*/
public class MarkovDecisionProcessTest {
public static final double DELTA_THRESHOLD = 1e-3;
private CellWorld<Double> cw = null;
private MarkovDecisionProcess<Cell<Double>, CellWorldAction> mdp = null;
private double nonTerminalReward = -0.04;
private GridWorld<Double> gw = null;
private MarkovDecisionProcess<GridCell<Double>, GridWorldAction> mdp = null;
@Before
public void setUp() {
cw = CellWorldFactory.createCellWorldForFig17_1();
mdp = MDPFactory.createMDPForFigure17_3(cw);
int maxTiles = 6;
int maxScore = 10;
gw = GridWorldFactory.createGridWorldForTileGame(maxTiles, maxScore, nonTerminalReward);
mdp = MDPFactory.createMDPForTileGame(gw, maxTiles, maxScore);
}
@Test
public void testActions() {
// Ensure all actions can be performed in each cell
// except for the terminal states.
for (Cell<Double> s : cw.getCells()) {
if (4 == s.getX() && (3 == s.getY() || 2 == s.getY())) {
for (GridCell<Double> s : gw.getCells()) {
if (6 == s.getX() && 10 == s.getY()) {
Assert.assertEquals(0, mdp.actions(s).size());
} else {
Assert.assertEquals(5, mdp.actions(s).size());
Assert.assertEquals(3, mdp.actions(s).size());
}
}
}
@Test
public void testMDPTransitionModel() {
Assert.assertEquals(0.8, mdp.transitionProbability(cw.getCellAt(1, 2),
cw.getCellAt(1, 1), CellWorldAction.Up), DELTA_THRESHOLD);
Assert.assertEquals(0.1, mdp.transitionProbability(cw.getCellAt(1, 1),
cw.getCellAt(1, 1), CellWorldAction.Up), DELTA_THRESHOLD);
Assert.assertEquals(0.1, mdp.transitionProbability(cw.getCellAt(2, 1),
cw.getCellAt(1, 1), CellWorldAction.Up), DELTA_THRESHOLD);
Assert.assertEquals(0.0, mdp.transitionProbability(cw.getCellAt(1, 3),
cw.getCellAt(1, 1), CellWorldAction.Up), DELTA_THRESHOLD);
Assert.assertEquals(0.9, mdp.transitionProbability(cw.getCellAt(1, 1),
cw.getCellAt(1, 1), CellWorldAction.Down), DELTA_THRESHOLD);
Assert.assertEquals(0.1, mdp.transitionProbability(cw.getCellAt(2, 1),
cw.getCellAt(1, 1), CellWorldAction.Down), DELTA_THRESHOLD);
Assert.assertEquals(0.0, mdp.transitionProbability(cw.getCellAt(3, 1),
cw.getCellAt(1, 1), CellWorldAction.Down), DELTA_THRESHOLD);
Assert.assertEquals(0.0, mdp.transitionProbability(cw.getCellAt(1, 2),
cw.getCellAt(1, 1), CellWorldAction.Down), DELTA_THRESHOLD);
Assert.assertEquals(0.9, mdp.transitionProbability(cw.getCellAt(1, 1),
cw.getCellAt(1, 1), CellWorldAction.Left), DELTA_THRESHOLD);
Assert.assertEquals(0.0, mdp.transitionProbability(cw.getCellAt(2, 1),
cw.getCellAt(1, 1), CellWorldAction.Left), DELTA_THRESHOLD);
Assert.assertEquals(0.0, mdp.transitionProbability(cw.getCellAt(3, 1),
cw.getCellAt(1, 1), CellWorldAction.Left), DELTA_THRESHOLD);
Assert.assertEquals(0.1, mdp.transitionProbability(cw.getCellAt(1, 2),
cw.getCellAt(1, 1), CellWorldAction.Left), DELTA_THRESHOLD);
Assert.assertEquals(0.8, mdp.transitionProbability(cw.getCellAt(2, 1),
cw.getCellAt(1, 1), CellWorldAction.Right), DELTA_THRESHOLD);
Assert.assertEquals(0.1, mdp.transitionProbability(cw.getCellAt(1, 1),
cw.getCellAt(1, 1), CellWorldAction.Right), DELTA_THRESHOLD);
Assert.assertEquals(0.1, mdp.transitionProbability(cw.getCellAt(1, 2),
cw.getCellAt(1, 1), CellWorldAction.Right), DELTA_THRESHOLD);
Assert.assertEquals(0.0, mdp.transitionProbability(cw.getCellAt(1, 3),
cw.getCellAt(1, 1), CellWorldAction.Right), DELTA_THRESHOLD);
Assert.assertEquals(0.66, mdp.transitionProbability(gw.getCellAt(2, 2),
gw.getCellAt(1, 1), GridWorldAction.AddTile), DELTA_THRESHOLD);
}
@Test
public void testRewardFunction() {
// Ensure all actions can be performed in each cell.
for (Cell<Double> s : cw.getCells()) {
if (4 == s.getX() && 3 == s.getY()) {
for (GridCell<Double> s : gw.getCells()) {
if (6 == s.getX() && 10 == s.getY()) {
Assert.assertEquals(1.0, mdp.reward(s), DELTA_THRESHOLD);
} else if (4 == s.getX() && 2 == s.getY()) {
Assert.assertEquals(-1.0, mdp.reward(s), DELTA_THRESHOLD);
} else {
Assert.assertEquals(-0.04, mdp.reward(s), DELTA_THRESHOLD);
}