fix wrong variable name in docs (pytorch#2589)

Summary:
Fixed a wrong variable name in the getting started doc.

Pull Request resolved: pytorch#2589

Reviewed By: saitcakmak

Differential Revision: D64693748

Pulled By: Balandat

fbshipit-source-id: 7ed3d1fb256ed7441595d0d6b8bfb79d2e17f7f4

docs/getting_started.md

@@ -51,7 +51,7 @@ Here's a quick run down of the main components of a Bayesian Optimization loop.
 
     gp = SingleTaskGP(
         train_X=train_X,
-        train_Y=Y,
+        train_Y=train_Y,
         input_transform=Normalize(d=2),
         outcome_transform=Standardize(m=1),
     )
@@ -63,7 +63,7 @@ Here's a quick run down of the main components of a Bayesian Optimization loop.
     ```python
     from botorch.acquisition import LogExpectedImprovement
 
-    logNEI = LogExpectedImprovement(model=gp, best_f=Y.max())
+    logNEI = LogExpectedImprovement(model=gp, best_f=train_Y.max())
     ```
 
 3. Optimize the acquisition function