public void GetQValues_ForReplay(SarsaElement elem,
out List <Double> q_values, out Boolean randomaction)
{
Int32 index = 0;
Boolean found = false;
q_values = new List <Double>();
while (!found && index < table.Count)
{
if (table[index].state.Equal(elem.state))
{
found = true;
}
else
{
index++;
}
}
if (found)
{
randomaction = false;
q_values.Add(table[index].q_turnleft);
q_values.Add(table[index].q_turnright);
q_values.Add(table[index].q_movefw);
q_values.Add(table[index].q_movebw);
q_values.Add(table[index].q_item);
q_values.Add(table[index].q_shoot);
}
else
{
randomaction = true;
}
}
public Int32 SearchIndex_OrAddElem(SarsaElement elem)
{
Int32 index = 0;
Boolean found = false;
while (!found && index < table.Count)
{
if (table[index].state.Equal(elem.state))
{
found = true;
}
else
{
index++;
}
}
if (found)
{
return(index);
}
else
{
table.Add(elem);
return(table.Count - 1);
}
}
public void GetBestAction_ForReplay(SarsaElement elem, out Action bestaction, out Double max_q_value, out Boolean randomaction)
{
Int32 index = 0;
Boolean found = false;
while (!found && index < table.Count)
{
if (table[index].state.Equal(elem.state))
{
found = true;
}
else
{
index++;
}
}
if (found)
{
// Get best Q-value and action according to policy
max_q_value = table[index].q_turnleft;
bestaction = Action.turnleft;
if (table[index].q_turnright > max_q_value)
{
max_q_value = table[index].q_turnright;
bestaction = Action.turnright;
}
if (table[index].q_movefw > max_q_value)
{
max_q_value = table[index].q_movefw;
bestaction = Action.movefw;
}
if (table[index].q_movebw > max_q_value)
{
max_q_value = table[index].q_movebw;
bestaction = Action.movebw;
}
if (table[index].q_item > max_q_value)
{
max_q_value = table[index].q_item;
bestaction = Action.item;
}
if (table[index].q_shoot > max_q_value)
{
max_q_value = table[index].q_shoot;
bestaction = Action.shoot;
}
randomaction = false;
}
else
{
// If state was not found, take a random action
Random rand = new Random();
bestaction = (Action)(rand.Next(0, 6));
max_q_value = 0;
randomaction = true;
}
}
public Double GetMaxQValue_AllActions(SarsaElement elem)
{
Int32 index = SearchIndex_OrAddElem(elem);
if (index < 0)
{
return(0.0); // error
}
Double q_max = table[index].q_turnleft;
if (table[index].q_turnright > q_max)
{
q_max = table[index].q_turnright;
}
if (table[index].q_movefw > q_max)
{
q_max = table[index].q_movefw;
}
if (table[index].q_movebw > q_max)
{
q_max = table[index].q_movebw;
}
if (table[index].q_item > q_max)
{
q_max = table[index].q_item;
}
if (table[index].q_shoot > q_max)
{
q_max = table[index].q_shoot;
}
return(q_max);
}
