Change batch range for FullyBayesianPosterior

Summary: Changes the batch range of FullyBayesianPosterior, which effectively means that we will regard the MC batch as a t-batch for the purposes of sampling. Reviewed By: dme65 Differential Revision: D44599898 fbshipit-source-id: 083a5ae3b2ed0022bad2f8f65bc65738784b9602
pytorch · Apr 4, 2023 · 1176a38 · 1176a38
1 parent 6c02411
commit 1176a38
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/botorch/posteriors/fully_bayesian.py b/botorch/posteriors/fully_bayesian.py
@@ -138,6 +138,6 @@ def batch_range(self) -> Tuple[int, int]:
         candidate produces same value regardless of its position on the t-batch.
         """
         if self._is_mt:
-            return (0, -3)
-        else:
             return (0, -2)
+        else:
+            return (0, -1)