public StochasticRewardGridWorld()
{
availableActions = new List <int[]>();
availableActions.Add(new int[2] {
-1, 0
});
availableActions.Add(new int[2] {
0, -1
});
availableActions.Add(new int[2] {
1, 0
});
availableActions.Add(new int[2] {
0, 1
});
rewardSites = new HashSet <int[]>(comparer);
// set the default agent
startState = new int[2] {
1, 1
};
Policy <int[], int[]> policy = new EGreedyPolicy <int[], int[]>();
ActionValue <int[], int[]> value = new ModelFreeValue <int[], int[]>(new IntArrayComparer(), new IntArrayComparer(), availableActions, startState);
agent = new Agent <int[], int[]>(startState, policy, value, availableActions);
}
public EgoAlloGridWorld()
{
availableActions = new List <int[]>();
availableActions.Add(new int[2] {
-1, 0
});
availableActions.Add(new int[2] {
0, -1
});
availableActions.Add(new int[2] {
1, 0
});
availableActions.Add(new int[2] {
0, 1
});
//availableActions.Add(new int[2] { -1, -1 });
//availableActions.Add(new int[2] { 1, -1 });
//availableActions.Add(new int[2] { -1, 1 });
//availableActions.Add(new int[2] { 1, 1 });
// set the default agent
startState = new int[14] {
1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
};
Policy <int[], int[]> policy = new EGreedyPolicy <int[], int[]>();
ActionValue <int[], int[]> value = new ModelFreeValue <int[], int[]>(new IntArrayComparer(), new IntArrayComparer(), availableActions, startState);
agent = new Agent <int[], int[]>(startState, policy, value, availableActions);
}
public Taxi()
{
dropSites.Add(null);
availableActions.Add(1); //left
availableActions.Add(2); //up
availableActions.Add(3); //right
availableActions.Add(4); //down
availableActions.Add(5); //pickup
availableActions.Add(6); //drop
// set the default agent
Policy <int[], int> policy = new EGreedyPolicy <int[], int>();
ActionValue <int[], int> value = new ModelFreeValue <int[], int>(new IntArrayComparer(), EqualityComparer <int> .Default, availableActions, new int[4] {
1, 2, 1, 10
});
agent = new Agent <int[], int>(new int[4] {
1, 2, 10, 1
}, policy, value, availableActions);
}
public MountainCar()
{
availableActions.Add(-1);
//availableActions.Add(0);
availableActions.Add(1);
rndStartState(out _position, out _velocity);
// set the default agent
Policy <int[], int> policy = new EGreedyPolicy <int[], int>();
ActionValue <int[], int> value = new ModelFreeValue <int[], int>(new IntArrayComparer(), EqualityComparer <int> .Default, availableActions, discretizeState(_position, _velocity));
agent = new Agent <int[], int>(discretizeState(_position, _velocity), policy, value, availableActions);
// create the hill bitmap
for (int i = 0; i < 17; i++)
{
double position = (0.5 + 1.2) / (18 - 1) * i - 1.2;
double amplitude = Math.Sin(3 * position);
amplitude = amplitude * 50 + 50;
hill.SetPixel(i, (int)(100 - amplitude), Color.ForestGreen);
}
}