public Form3()
{
InitializeComponent();
ws = customControl11.Workspace = new InvertedPendulumEnvironment();
this.KeyPreview = true;
timer1.Enabled = true;
}
public Form1()
{
InitializeComponent();
ws = customControl11.Workspace = new InvertedPendulumEnvironment();
oppWs = customControl12.Workspace = new InvertedPendulumEnvironment();
this.KeyPreview = true;
}
public void GenerateMMatrices()
{
InvertedPendulumEnvironment testws = new InvertedPendulumEnvironment();
int statenum = InvertedPendulumQStore.LEN * InvertedPendulumQStore.LEN;
Ma = new SparseMatrix[3];
for (int i = 0; i < 3; ++i)
{
Ma[i] = new SparseMatrix(statenum);
}
for (int ii = 0; ii < statenum; ++ii)
{
int j = ii % InvertedPendulumQStore.LEN;
int k = ii / InvertedPendulumQStore.LEN;
InvertedPendulumState state;
InvertedPendulumQStore.GetState(j, k, out state);
for (int i = 0; i < 3; ++i)
{
int action = i - 1;
for (int i1 = 0; i1 < 1000; ++i1)
{
testws.a = state.a + r.NextDouble() / InvertedPendulumQStore.LEN * 2 * Math.PI;
testws.w = state.w + r.NextDouble() / InvertedPendulumQStore.LEN * 2 * 3;
testws.Step(action);
int j2, k2;
InvertedPendulumState state2 = new InvertedPendulumState(testws.a, testws.w);
InvertedPendulumQStore.GetStateIndices(state2, out j2, out k2);
int ii2 = k2 * InvertedPendulumQStore.LEN + j2;
Ma[i][ii, ii2] += 0.001f;
}
}
}
SaveMMatrices("mmatrices.dat");
}
private void GenerateRVector()
{
int statenum = InvertedPendulumQStore.LEN * InvertedPendulumQStore.LEN;
InvertedPendulumEnvironment testws = new InvertedPendulumEnvironment();
R = new Vector(statenum);
for (int ii = 0; ii < statenum; ++ii)
{
int j = ii % InvertedPendulumQStore.LEN;
int k = ii / InvertedPendulumQStore.LEN;
InvertedPendulumState state;
InvertedPendulumQStore.GetState(j, k, out state);
testws.a = state.a;
testws.w = state.w;
R.Elements[ii] = testws.Reward();
}
}
public void Train()
{
InvertedPendulumEnvironment testenv = new InvertedPendulumEnvironment();
int mincount = 100;
states = new List<InvertedPendulumState>();
for(int i=0; i<mincount; ++i) {
testenv.Reset();
InvertedPendulumState newstate = (InvertedPendulumState)testenv.State();
states.Add(newstate);
}
int statenum = states.Count;
//allapot-atmenet valsegek es varhato rewardok szamitasa
Vector R = new Vector(statenum);
SparseMatrix[] Ma = new SparseMatrix[3];
for (int i = 0; i < 3; ++i)
{
Ma[i] = new SparseMatrix(statenum);
}
Vector counts = new Vector(statenum);
for (int ii = 0; ii < statenum*10000; ++ii)
{
testenv.Reset();
InvertedPendulumState curstate = (InvertedPendulumState)testenv.State();
int from = GetClosestStateIndex(states, curstate);
R.Elements[from] += testenv.Reward();
for (int i = 0; i < 3; ++i)
{
int action = i - 1;
testenv.SetState(curstate);
testenv.Step(action);
InvertedPendulumState tostate = (InvertedPendulumState)testenv.State();
int to = GetClosestStateIndex(states, tostate);
Ma[i][from, to] += 1;
}
float temp = (float)counts.Elements[from];
if (temp != 0) temp = 1 / (1 / temp + 1);
else temp = 1;
counts.Elements[from] = temp;
}
for (int i = 0; i < 3; ++i)
{
Ma[i].Multiply(counts);
}
R.Multiply(counts);
SparseMatrix M = (Ma[0] + Ma[1] + Ma[2]);
M.Multiply(0.333333f);
M.Multiply(0.99f);
SparseMatrix IM = SparseMatrix.Identity(statenum) - M;
Vector utility = IM.SolveLinearEquation2(R);
for (int i = 0; i < 3; ++i)
{
Q[i] = Ma[i].MatrixMultiplyRight(utility);
}
}
