Removed unused google-code classes. Regenerate policy when AdaptiveComPlayer.setTarget() is called.
61 lines
1.6 KiB
Java
61 lines
1.6 KiB
Java
package aima.core.probability.mdp;
|
|
|
|
import java.util.Map;
|
|
|
|
import org.junit.Assert;
|
|
import org.junit.Before;
|
|
import org.junit.Test;
|
|
|
|
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;
|
|
import aima.core.probability.mdp.search.ValueIteration;
|
|
|
|
/**
|
|
*
|
|
* @author Woody
|
|
*
|
|
*/
|
|
public class ValueIterationTest2 {
|
|
public static final double DELTA_THRESHOLD = 1e-3;
|
|
|
|
private GridWorld<Double> gw = null;
|
|
private MarkovDecisionProcess<GridCell<Double>, GridWorldAction> mdp = null;
|
|
private ValueIteration<GridCell<Double>, GridWorldAction> vi = null;
|
|
|
|
final int maxTiles = 6;
|
|
final int maxScore = 10;
|
|
|
|
@Before
|
|
public void setUp() {
|
|
// take 10 turns to place 6 tiles
|
|
double defaultPenalty = -0.04;
|
|
|
|
gw = GridWorldFactory.createGridWorldForTileGame(maxTiles, maxScore,
|
|
defaultPenalty);
|
|
mdp = MDPFactory.createMDPForTileGame(gw, maxTiles, maxScore);
|
|
|
|
// gamma = 1.0
|
|
vi = new ValueIteration<GridCell<Double>, GridWorldAction>(0.9);
|
|
}
|
|
|
|
@Test
|
|
public void testValueIterationForTileGame() {
|
|
Map<GridCell<Double>, Double> U = vi.valueIteration(mdp, 1.0);
|
|
|
|
for (int j = maxScore; j >= 1; j--) {
|
|
StringBuilder sb = new StringBuilder();
|
|
for (int i = 1; i <= maxTiles; i++) {
|
|
sb.append(U.get(gw.getCellAt(i, j)));
|
|
sb.append(" ");
|
|
}
|
|
System.out.println(sb.toString());
|
|
}
|
|
|
|
Assert.assertEquals(-0.1874236, U.get(gw.getCellAt(1, 1)), DELTA_THRESHOLD);
|
|
}
|
|
}
|