public int ChooseAction(double[] actionEstimates)
{
// actions count
int actionsCount = actionEstimates.Length;
// find the best action (greedy)
double maxReward = actionEstimates[0];
int greedyAction = 0;
for (int i = 1; i < actionsCount; i++)
{
if (actionEstimates[i] > maxReward)
{
maxReward = actionEstimates[i];
greedyAction = i;
}
}
// try to do exploration
if (rand.NextDouble() < epsilon)
{
int randomAction = rand.Next(actionsCount - 1);
if (randomAction >= greedyAction)
randomAction++;
return randomAction;
}
return greedyAction;
}
}