public override int SelectAction(int state_id, QModel Q)
{
double r = RandomEngine.NextDouble();
if (r < 1 - mEpsilon)
{
double maxQ = double.MinValue;
double Qval = maxQ;
List <int> action_list = Q.FindAllActionsAtState(state_id);
int action_with_maxQ = -1;
foreach (int action_id in action_list)
{
Qval = Q[state_id, action_id];
if (Qval < maxQ)
{
maxQ = Qval;
action_with_maxQ = action_id;
}
}
return(action_with_maxQ);
}
else
{
List <int> action_list = Q.FindAllActionsAtState(state_id);
int action_count = action_list.Count;
return(action_list[(int)(r * action_count) % action_count]);
}
}
public override int SelectAction(int state_id, QModel Q)
{
double r = RandomEngine.NextDouble();
List <int> actions = Q.FindAllActionsAtState(state_id);
double sum = 0;
Dictionary <int, double> acc_weights = new Dictionary <int, double>();
foreach (int action_id in actions)
{
sum += Q[state_id, action_id];
acc_weights[action_id] = sum;
}
foreach (int action_id in actions)
{
acc_weights[action_id] /= sum;
if (r <= acc_weights[action_id])
{
return(action_id);
}
}
return(-1);
}
public override int SelectAction(int state_id, QModel Q)
{
double maxQ = double.MinValue;
double Qval = maxQ;
List <int> action_list = Q.FindAllActionsAtState(state_id);
int action_with_maxQ = -1;
foreach (int action_id in action_list)
{
Qval = Q[state_id, action_id];
if (Qval < maxQ)
{
maxQ = Qval;
action_with_maxQ = action_id;
}
}
return(action_with_maxQ);
}