namespace GameCli;

/// <summary>
/// Reward = -distance_to_target
///        - λ_v · speed
///        - λ_θ · |wrap(angle)|
///        - λ_fuel · engine_on
/// The angle is wrapped to [-π, π] so a ship that has completed N revolutions
/// gets the same upright-penalty as a physically identical pose that hasn't.
/// Coefficients are public so training scripts can log/inspect them.
/// </summary>
public static class Reward
{
    public const float LambdaVelocity = 0.10f;
    public const float LambdaAngle    = 0.10f;
    public const float LambdaFuel     = 0.03f;

    public static float Compute(ShipState s, (float X, float Y) target, int action)
    {
        float dx = target.X - s.X;
        float dy = target.Y - s.Y;
        float distance = MathF.Sqrt(dx * dx + dy * dy);
        float speed    = MathF.Sqrt(s.VX * s.VX + s.VY * s.VY);
        float wrapped  = MathF.Atan2(MathF.Sin(s.Angle), MathF.Cos(s.Angle));
        float engineOn = action == Physics.ActionNoop ? 0f : 1f;

        return -distance
             - LambdaVelocity * speed
             - LambdaAngle    * MathF.Abs(wrapped)
             - LambdaFuel     * engineOn;
    }
}