public override List <float> CollectState()
{
List <float> state = new List <float>( );
TicTacToe game = TicTacToe.Instance;
List <int> currentState = game.GetBoard();
int curPlayer = game.getCurPlayerVal();
bool nearingWin = false;
int winIndex = -1;
int sign = 0;
for (int i = 0; i < currentState.Count; i++)
{
if (currentState [i] == TicTacToe.DefVal)
{
int col = -1; int row = -1;
BoardGame.GetRowColFromIndex(i, out col, out row);
int sum = 0;
if (col == row)
{
sum = game.sumDiagLR(false);
if (Mathf.Abs(sum) == game.Dim - 1)
{
sign = (int)Mathf.Sign(sum);
nearingWin = true;
winIndex = i;
}
}
if (col + row == game.Dim - 1)
{
sum = game.sumDiagRL(false);
if (Mathf.Abs(sum) == game.Dim - 1)
{
if (nearingWin && sign == curPlayer)
{
// Do nothing
}
else
{
sign = (int)Mathf.Sign(sum);
nearingWin = true;
winIndex = i;
}
}
}
sum = game.sumCol(col, false);
if (Mathf.Abs(sum) == game.Dim - 1)
{
if (nearingWin && sign == curPlayer)
{
// Do nothing
}
else
{
sign = (int)Mathf.Sign(sum);
nearingWin = true;
winIndex = i;
}
}
sum = game.sumRow(row, false);
if (Mathf.Abs(sum) == game.Dim - 1)
{
if (nearingWin && sign == curPlayer)
{
// Do nothing
}
else
{
sign = (int)Mathf.Sign(sum);
nearingWin = true;
winIndex = i;
}
}
}
}
int maxVal = currentState.Count;
for (int i = 0; i < currentState.Count; i++)
{
if (winIndex == i)
{
int val = maxVal * 100;
state.Add(val);
}
else
{
if (currentState [i] == TicTacToe.DefVal)
{
int val = maxVal * 10;
state.Add(val);
}
else
{
state.Add(currentState [i] * 10);
}
}
}
state.Add((float)(curPlayer));
if (!game.IsLearning)
{
//drawStates (state);
}
return(state);
}
public override void AgentStep(float[] act)
{
TicTacToe game = TicTacToe.Instance;
if (!game.isPlayable() || game.getWinner() != TicTacToe.DefVal)
{
pubInstance.NotifyListeners("AgentReset");
return;
}
if (!isMyMove())
{
return;
}
bool isValid = false;
int index = act.Length > 0 ? Mathf.RoundToInt(act [0]) : -1;
if (index >= 0 && index < game.Dim * game.Dim)
{
if (game.GetVal(index) == TicTacToe.DefVal)
{
int row = -1;
int col = -1;
BoardGame.GetRowColFromIndex(index, out col, out row);
if (game.makeMove(col, row, game.getCurPlayerVal()))
{
isValid = true;
lastStep = stepCounter;
// Each time a valid value occurs, increment maxStep while learning
if (game.IsLearning)
{
maxStep = stepCounter + maxStepInit;
}
postStep();
return;
}
}
}
string status = "Action: " + act [0] + " Step " + stepCounter + " " + isValid;
if (game.IsLearning)
{
Status.text = status;
}
else
{
Debug.Log(status);
}
if (!isValid)
{
reward = -1;
if (!game.IsLearning)
{
randomMove();
int winner = game.getWinner();
if (winner != TicTacToe.DefVal)
{
if (game.IsLearning)
{
Status.text = "Yay! " + myVal + " won!";
if (myVal == TicTacToe.CrossVal)
{
scoreCross++;
}
else
{
scoreNot++;
}
}
}
}
else
{
pubInstance.NotifyListeners("InvalidValue");
}
}
}