public QState GetState()
{
var p = PositionToState(transform.position);
var g = PositionToState(Goal.Position);
_grid.Populate(bounds => {
var ray = new Ray(new Vector3(bounds.center.x, 2, bounds.center.z), Vector3.down);
RaycastHit hit;
if (Physics.Raycast(ray, out hit, 3.0f))
{
return(hit.collider.gameObject == Goal.Instance.gameObject ? 1f : 0.1f);
}
return(0f);
});
var dead = !IsAboveGround();
var goal = p.SequenceEqual(g);
var line = VectorToGoal(transform.position, Goal.Position);
var v = line.normalized;
_linearState.At(0, v.x);
_linearState.At(1, v.z);
var terminal = dead || goal || DetectCycle();
var spatial = Matrix <float> .Build.Dense(1, 1, 1f);
var state = new QState(
new [] { spatial },
_linearState.Clone(),
goal ? 1 : 0,
terminal
);
return(state);
}
public QState GetState()
{
var winner = _ball.IsTerminal();
float reward;
bool terminal;
//var terminal = winner.HasValue;
//var reward = terminal ? (winner.Value == Side ? 1 : 0) : 0;
var b = PongGame.BoundsFromTransform(_ball.transform);
var controller = PongGame.BoundsFromTransform(transform);
controller.size += new Vector3(0.2f, 0, 0);
PongGame.DebugDrawBounds(controller, Color.blue);
if (b.Intersects(controller))
{
reward = 1;
terminal = true;
if (PongBenchmark.Running)
{
terminal = winner.HasValue;
}
}
else
{
terminal = winner.HasValue;
reward = terminal ? (winner.Value == Side ? 1 : 0) : 0;
}
var bp = _ball.transform.position;
var rbp = bp - transform.position;
var gbp = _grid.Locate(bp);
var bpy = gbp.HasValue ? gbp.Value.y : -1;
_grid.Populate((bo, c) => {
//var x = bo.center.x;
//var v = bo.Contains(new Vector3(x, _game.Border.min.y)) || bo.Contains(new Vector3(x, _game.Border.max.y)) ? 0.3f : 0; // walls
var ham = gbp.HasValue ? HammingDistance(gbp.Value, c) : int.MaxValue; // Hamming distance
var v = ham <= 0 ? 1f : ham <= 1 ? 0.5f : 0; // ball
//v = bo.Contains(bp + _ball.Velocity.normalized * 2) ? 150f : v;
//v = bo.Intersects(controller) ? 100 : v;
return(v);
});
var state = _grid.Matrix;
return(new QState(new[] { state }, _vect.Clone(), reward, terminal));
}