public static void printActionValues() {
TabularQLearningForTwo tq = tabularQLearnings.get(0);
if (tq.isPriestessProtectionAddedToState()) {
System.out.println("Opponent is protected by priestess");
State state = new State(Card.Soldier, Card.Soldier);
state.setOpponentProtectedByPriestess(true);
printActionValues(state);
System.out.println("Opponent is not protected by priestess");
state = new State(Card.Soldier, Card.Soldier);
state.setOpponentProtectedByPriestess(false);
printActionValues(state);
} else if (tq.isUsedCardsNumAddedToState()) {
for (int i = 0; i <= 12; i++) {
System.out.println(String.format("Number of used cards is %d", i));
State state = new State(Card.Soldier, Card.Soldier);
state.setUsedCardsNum(i);
printActionValues(state);
}
} else if (tq.isOpponentHandByClownAddedToState()) {
System.out.println("Opponent hand is unknown");
State state = new State(Card.Soldier, Card.Soldier);
state.setOpponentHand(null);
printActionValues(state);
for (Card opponentHand : Card.values()) {
System.out.println(String.format("Opponent hand is %s", opponentHand));
state = new State(Card.Soldier, Card.Soldier);
state.setOpponentHand(opponentHand);
printActionValues(state);
}
} else {
State state = new State(Card.Soldier, Card.Soldier);
printActionValues(state);
}
}
private static double getAverageValue(State state, Action action) {
double sumValue = 0.0;
for (TabularQLearningForTwo tq : tabularQLearnings) {
sumValue += tq.getActionValue(state, action).getValue();
}
return sumValue / tabularQLearnings.size();
}
public static void main(String[] args) {
// String csvPathTemplate = "./data/plain/%d.csv";
// String csvPathTemplate = "./data/addPriestessProtectionToState/%d.csv";
// String csvPathTemplate = "./data/addUsedCardsNumToState/%d.csv";
String csvPathTemplate = "./data/addOpponentHandByClownToState/%d.csv";
// String csvPathTemplate = "./data/addTargetCardForSoldierToAction/%d.csv";
// String csvPathTemplate = "./data/addTargetPlayerForWizardToAction/%d.csv";
tabularQLearnings = new ArrayList<TabularQLearningForTwo>();
for (int ti = 0; ti < 10; ti++) {
TabularQLearningForTwo tabularQLearning = new TabularQLearningForTwo();
String csvPath = String.format(csvPathTemplate, ti);
tabularQLearning.loadActionValuesFromCSV(csvPath);
tabularQLearnings.add(tabularQLearning);
}
printActionValues();
}
private static void printActionValues(State templateState) {
TabularQLearningForTwo tq = tabularQLearnings.get(0);
System.out.print(String.format("%15s", ""));
for (Card hand : Card.values()) {
System.out.print(String.format("%15s", hand));
}
System.out.println("");
for (Card hand1 : Card.values()) {
if (hand1 == Card.Soldier && tq.isTargetCardForSoldierAddedToAction()) {
for (Card targetCard : Card.values()) {
if (targetCard != Card.Soldier) {
System.out.print(String.format("%12s(%d)", hand1, targetCard.getStrength()));
for (Card hand2 : Card.values()) {
State state = new State(hand1, hand2);
state.setOpponentProtectedByPriestess(templateState.isOpponentProtectedByPriestess());
state.setUsedCardsNum(templateState.getUsedCardsNum());
state.setOpponentHand(templateState.getOpponentHand());
Action action = new Action(hand1);
action.setTargetCardForSoldier(targetCard);
System.out.print(String.format("%15.3f", getAverageValue(state, action)));
}
System.out.println("");
}
}
} else if (hand1 == Card.Wizard && tq.isTargetPlayerForWizardAddedToAction()) {
System.out.print(String.format("%12s(m)", hand1));
for (Card hand2 : Card.values()) {
if (isPossibleHands(hand1, hand2)) {
State state = new State(hand1, hand2);
state.setOpponentProtectedByPriestess(templateState.isOpponentProtectedByPriestess());
state.setUsedCardsNum(templateState.getUsedCardsNum());
state.setOpponentHand(templateState.getOpponentHand());
Action action = new Action(hand1);
action.setTargetMyselfForWizard(true);
System.out.print(String.format("%15.3f", getAverageValue(state, action)));
} else {
System.out.print(String.format("%15s", "-----"));
}
}
System.out.println("");
System.out.print(String.format("%12s(o)", hand1));
for (Card hand2 : Card.values()) {
if (isPossibleHands(hand1, hand2)) {
State state = new State(hand1, hand2);
state.setOpponentProtectedByPriestess(templateState.isOpponentProtectedByPriestess());
state.setUsedCardsNum(templateState.getUsedCardsNum());
state.setOpponentHand(templateState.getOpponentHand());
Action action = new Action(hand1);
action.setTargetMyselfForWizard(false);
System.out.print(String.format("%15.3f", getAverageValue(state, action)));
} else {
System.out.print(String.format("%15s", "-----"));
}
}
System.out.println("");
} else {
System.out.print(String.format("%15s", hand1));
for (Card hand2 : Card.values()) {
if (isPossibleHands(hand1, hand2)) {
State state = new State(hand1, hand2);
state.setOpponentProtectedByPriestess(templateState.isOpponentProtectedByPriestess());
state.setUsedCardsNum(templateState.getUsedCardsNum());
state.setOpponentHand(templateState.getOpponentHand());
Action action = new Action(hand1);
System.out.print(String.format("%15.3f", getAverageValue(state, action)));
} else {
System.out.print(String.format("%15s", "-----"));
}
}
System.out.println("");
}
}
}