feat(gamecli): implement pure Reward.Compute with unit tests

GameCli/Reward.cs

@@ -0,0 +1,29 @@
+namespace GameCli;
+
+/// <summary>
+/// Reward = -distance_to_target
+///        - λ_v · speed
+///        - λ_θ · |angle|
+///        - λ_fuel · engine_on
+/// 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 engineOn = action == Physics.ActionNoop ? 0f : 1f;
+
+        return -distance
+             - LambdaVelocity * speed
+             - LambdaAngle    * MathF.Abs(s.Angle)
+             - LambdaFuel     * engineOn;
+    }
+}