/// <summary>
/// Must enumerate every possible action to take from every possible state, where 1 action is a set of commands given to units. FOR NOW IT ONLY COMMANDS ONE UNIT!!!!
/// </summary>
/// <param name="c"></param>
void InitializePolicy()
{
Commander c = commandersToControl[0];
Debug.Log("Creating policy...");
float initialQValue = 0.8f;
policy = new List <Tuple <CommandListAbstract, float> > [stateSpace.states.Count];
//for (int s = 0; s < stateSpace.Length; s++)
for (int s = 0; s < stateSpace.states.Count; s++)
{
List <Tuple <CommandListAbstract, float> > commandLists = new List <Tuple <CommandListAbstract, float> >();
// available options for each plane
List <Maneuver>[] availableManeuvers = new List <Maneuver> [c.unitsOwned.Count];
// enumerate possible maneuvers for each plane controlled
for (int unitIdx = 0; unitIdx < c.unitsOwned.Count; unitIdx++)
{
var aircraft = stateSpace.GetAircraftAtState(s);
var potentialManeuvers = gameController.GetAvailableManeuvers(aircraft);
availableManeuvers[unitIdx] = potentialManeuvers;
}
// get all possible combinations of maneuvers for ONE plane
for (int unitIdx = 0; unitIdx < c.unitsOwned.Count; unitIdx++)
{
if (c.unitsOwned.Count > 1)
{
Debug.LogError("Whoops, did not implement Policy creation for commanding multiple units yet...");
}
var maneuvers = availableManeuvers[unitIdx];
for (int maneuverIdx = 0; maneuverIdx < maneuvers.Count; maneuverIdx++)
{
CommandListAbstract action = new CommandListAbstract();
action.Add(unitIdx, maneuvers[maneuverIdx].id);
commandLists.Add(new Tuple <CommandListAbstract, float>(action, initialQValue));
}
}
policy[s] = commandLists;
//Debug.Log("Policy creation progress: " + s + "/" + stateSpace.states.Count);
}
Debug.Log("Policy creation finished!");
}
