public RLPolicy(List <int> dimSize)
{
this.dimSize = dimSize;
qValuesTable = new EndlessArray <List <double> >(dimSize, default(List <double>), default(List <double>));
states = dimSize[0];
for (int j = 1; j < dimSize.Count - 1; j++)
{
states *= dimSize[j];
}
actions = dimSize[dimSize.Count - 1];
}
public QLearner(List <Action> actions, List <int> tableDimensions, double startingQ)
{
this.actions = actions;
qValues = new EndlessArray <double>(tableDimensions, startingQ, -startingQ);
}