private void NextEpisode(SMDPAgent agent)
{
config = RLConfig.Load("RLConfig.xml");
if (this.Episodes > config.numEpisodes)
{
return;
}
Console.WriteLine("Gets to NextEpisode() {0} times", cnt++);
if (this.Episodes == 0)
{
fitness = 1;
sum = 0;
counter = 0;
}
this.Episodes++;
agent.setEpsilon(config.lambda);
fitness = RLGameWorld.FitnessValue(agent);
reward = fitness; // This is to send a reward to endEpisode
sum += fitness;
if (this.Episodes % count_fit == 0)
{
counter++;
average_fitness = sum / count_fit;
// recordPerformance(this.Episodes, fitness);
recordPerformance(counter, average_fitness);
sum = 0;
}
//this.Previous = this.Current;
//this.Current = this.Next;
//this.Next = new KPEnvironment(this.Episode + 1);
}
public void OneEpisode(SMDPAgent agent)
{
// call the evaluator
epi++;
this.NextEpisode(agent);
if (this.OnEpisode == null)
{
// Console.WriteLine("OnEpisode is null !!!!!!");
return;
}
this.OnEpisode(this);
}
public static double FitnessValue(SMDPAgent policy)
{
int cycles = 0;
config = RLConfig.Load("RLConfig.xml");
switch (config.learningMethod)
{
case "Q_Learning":
{ for (int i = 0; i < players.Count; i++)
{
players[i].qlPolicy = (Q_LearningAgent)policy;
}
break; }
case "SARSA":
{ for (int i = 0; i < players.Count; i++)
{
players[i].saPolicy = (SarsaAgent)policy;
}
break; }
default:
Console.WriteLine("Default case does not exist");
break;
}
do
{
timer.RunCycle();
cycles++;
} while (!kref.episodeEnded);
kref.episodeEnded = false;
return(cycles / (10.0));
}
// public static int epi;
public void OneEpisode(SMDPAgent agent)
{
// call the evaluator
epi++;
this.NextEpisode(agent);
}