/**
* Transition function. Currently, we only get the list of probabilities of each item.
*
* @param current - The current state
* @param action - The action
* @param possible - The possible state
* @return The list of probabilities where each index refers to the probability of that item
*/
private List<Double> transition(State current, Action action, State possible) {
List<Double> probs = new ArrayList<Double>(); // Probabilities
Map<Integer, Integer> currentStock, purchase, possibleStock; // Maps
double currentProb; // The current probability
Matrix currentMatrix; // The current probability matrix
int row, column; // The row and column
for (int i = 0; i < current.getState().size(); ++i) {
currentProb = 0.0;
currentStock = current.getState();
purchase = action.getPurchases();
possibleStock = possible.getState();
row = currentStock.get(i) + purchase.get(i);
column = row - possible.getState().get(i);
currentMatrix = this.probabilities.get(i);
if (column < 0
|| column >= currentMatrix.getNumCols()
|| row >= currentMatrix.getNumRows()) { // Invalid state
probs.add(0.0);
continue;
}
if (possibleStock.get(i) > 0
|| (possibleStock.get(i) == 0 && column == 0)) { // Sufficiently provided
currentProb = currentMatrix.get(row, column);
} else if (possibleStock.get(i) == 0 && column > 0) {
// Range of probabilities because user could have eaten plenty
for (int j = column; j < currentMatrix.getNumCols(); ++j) {
currentProb += currentMatrix.get(row, j);
}
}
probs.add(currentProb);
}
return probs;
}
public List<Integer> generateShoppingList(List<Integer> inventory, int numWeeksLeft) {
State current; // current state
Map<Integer, Integer> purchases = new HashMap<Integer, Integer>(); // Purchases
Map<Integer, Integer> map = new HashMap<Integer, Integer>(); // Mapping of integers
List<Integer> shopping = new ArrayList<Integer>(); // Shopping items
for (int i = 0; i < inventory.size(); ++i) {
map.put(i, inventory.get(i));
}
current = new State(map);
purchases = this.policy.get(current).getPurchases();
for (int i = 0; i < inventory.size(); ++i) {
shopping.add(purchases.get(i));
}
return shopping;
}
/**
* Value generation
*
* @param state - The current state
* @param action - The current action
* @param Set<State> lookup - The set of states we are looking up
* @return The total value for that state
*/
private Double valueGeneration(State state, Action action, Set<State> lookup) {
Double maxValue = null; // The maximum value
double currentVal = 0.0; // The current value
List<Double> currentProb = new ArrayList<Double>();
for (State possible : this.possibleStates) {
currentProb = transition(state, action, possible);
for (int i = 0; i < currentProb.size(); ++i) {
currentVal +=
currentProb.get(i)
* (reward(possible) + this.spec.getDiscountFactor() * possible.getCost());
}
if (maxValue == null) { // First time generating value
maxValue = currentVal;
} else { // Need to sum up these values
maxValue += currentVal;
}
}
return maxValue;
}