public LinearEgoAlloValue(IEqualityComparer <int[]> StateComparer, IEqualityComparer <int[]> ActionComparer, List <int[]> AvailableActions, int[] StartState, params object[] parameters)
: base(StateComparer, ActionComparer, AvailableActions, StartState, parameters)
{
if (parameters.Length > 0)
{
fullPredictionMode = (bool)parameters[0];
}
if (parameters.Length > 1)
{
updateTerminationStepCount = (int)parameters[1];
}
if (parameters.Length > 2)
{
if ((bool)parameters[2])
{
alloLearner = new ModelBasedValue <int[], int[]>(StateComparer, ActionComparer, AvailableActions, null, true);
}
else
{
alloLearner = new ModelFreeValue <int[], int[]>(StateComparer, ActionComparer, AvailableActions, null, true);
}
}
stateComparer = StateComparer;
actionComparer = ActionComparer;
availableActions = AvailableActions;
//alloModel = new ModelFreeValue<int[], int[]>(StateComparer, ActionComparer, availableActions, null, true);
//{
// defaultQ = 10.3
//};
egoLearner = new ModelFreeValue <int[], int[]>(StateComparer, actionComparer, availableActions, StartState)
{
alpha = 0.9
};
egoPredictionModels = new ModelBasedValue <int[], int[]> [3];
for (int i = 0; i < egoPredictionModels.Length; i++)
{
egoPredictionModels[i] = new ModelBasedValue <int[], int[]>(StateComparer, ActionComparer, availableActions, StartState)
{
gamma = 0
};
}
visitedStates = new Dictionary <int[], int> [4];
for (int i = 0; i < availableActions.Count; i++)
{
visitedStates[i] = new Dictionary <int[], int>(StateComparer);
}
}
public EgoAlloValue(IEqualityComparer <int[]> StateComparer, IEqualityComparer <int[]> ActionComparer, List <int[]> AvailableActions, int[] StartState, params object[] parameters)
: base(StateComparer, ActionComparer, AvailableActions, StartState, parameters)
{
if (parameters.Length > 0)
{
fullPredictionMode = (bool)parameters[0];
}
stateComparer = StateComparer;
actionComparer = ActionComparer;
availableActions = AvailableActions;
alloModel = new ModelBasedValue <int[], int[]>(StateComparer, ActionComparer, availableActions, StartState, true)
{
defaultQ = 10.3
};
egoModel = new ModelFreeValue <int[], int[]>(StateComparer, actionComparer, availableActions, StartState)
{
alpha = 0.9
};
network = new ActivationNetwork(new BipolarSigmoidFunction(2), 10, 10, 3);
teacher = new ParallelResilientBackpropagationLearning(network);
}
