public static GameState GetNextState(GameState s, Action a)
{
var nextS = s.Clone();
if (a == core.Action.LEFT)
{
nextS = new GameState(nextS.UserHp, nextS.UserPos - 1, nextS.TowerHp);
}
else if (a == core.Action.RIGHT)
{
nextS = new GameState(nextS.UserHp, nextS.UserPos + 1, nextS.TowerHp);
}
if (nextS.UserPos == 0)
{
nextS = new GameState(5, nextS.UserPos, nextS.TowerHp);
}
else if (nextS.UserPos == 2)
{
nextS = new GameState(nextS.UserHp - 1, nextS.UserPos, nextS.TowerHp - 1);
}
if (s is CompactGameState)
{
nextS = new CompactGameState(nextS.UserHp, nextS.UserPos, nextS.TowerHp);
}
return(nextS);
}
public static GameState GetNextState(GameState s, Action a)
{
var nextS = s.Clone();
if (a == core.Action.LEFT)
nextS = new GameState(nextS.UserHp, nextS.UserPos - 1, nextS.TowerHp);
else if (a == core.Action.RIGHT)
nextS = new GameState(nextS.UserHp, nextS.UserPos + 1, nextS.TowerHp);
if (nextS.UserPos == 0)
nextS = new GameState(5, nextS.UserPos, nextS.TowerHp);
else if (nextS.UserPos == 2)
nextS = new GameState(nextS.UserHp - 1, nextS.UserPos, nextS.TowerHp - 1);
if (s is CompactGameState)
nextS = new CompactGameState(nextS.UserHp, nextS.UserPos, nextS.TowerHp);
return nextS;
}
private void resetModel()
{
_agent = new QLearningAgent();
trackBarAlpha.Value = 2;
trackBarGamma.Value = 8;
trackBarEpsilon.Value = 1;
_agent.alpha = 0.2;
_agent.gamma = 0.8;
_agent.epsilon = 0.05;
// regiser state-qvalue
foreach (var userHp in Enumerable.Range(0, _maxUserHp + 1))
{
foreach (var userPos in Enumerable.Range(0, _maxUserPos + 1))
{
foreach (var towerHp in Enumerable.Range(0, _maxTowerHp + 1))
{
var state = new GameState(userHp, userPos, towerHp);
var compactState = new CompactGameState(userHp, userPos, towerHp);
foreach (var action in state.GetActionSet())
{
if (checkBoxCompact.Checked)
_agent.registerStateQValue(compactState, action, 0);
else
_agent.registerStateQValue(state, action, 0);
}
}
}
}
}