diff --git a/botorch/acquisition/knowledge_gradient.py b/botorch/acquisition/knowledge_gradient.py
index 100a7d54be..333648854a 100644
--- a/botorch/acquisition/knowledge_gradient.py
+++ b/botorch/acquisition/knowledge_gradient.py
@@ -27,7 +27,7 @@
 from __future__ import annotations
 
 from copy import deepcopy
-from typing import Callable, Optional, Tuple, Union
+from typing import Any, Callable, Optional, Tuple, Union
 
 import torch
 from botorch import settings
@@ -71,6 +71,7 @@ def __init__(
         inner_sampler: Optional[MCSampler] = None,
         X_pending: Optional[Tensor] = None,
         current_value: Optional[Tensor] = None,
+        **kwargs: Any,
     ) -> None:
         r"""q-Knowledge Gradient (one-shot optimization).
 
@@ -227,6 +228,7 @@ def __init__(
         cost_aware_utility: Optional[CostAwareUtility] = None,
         project: Callable[[Tensor], Tensor] = lambda X: X,
         expand: Callable[[Tensor], Tensor] = lambda X: X,
+        **kwargs: Any,
     ) -> None:
         r"""Multi-Fidelity q-Knowledge Gradient (one-shot optimization).
 
diff --git a/botorch/acquisition/monte_carlo.py b/botorch/acquisition/monte_carlo.py
index d9eb79b704..68c33c43b5 100644
--- a/botorch/acquisition/monte_carlo.py
+++ b/botorch/acquisition/monte_carlo.py
@@ -22,7 +22,7 @@
 
 import math
 from abc import ABC, abstractmethod
-from typing import Optional, Union
+from typing import Any, Optional, Union
 
 import torch
 from botorch.acquisition.acquisition import AcquisitionFunction
@@ -116,6 +116,7 @@ def __init__(
         sampler: Optional[MCSampler] = None,
         objective: Optional[MCAcquisitionObjective] = None,
         X_pending: Optional[Tensor] = None,
+        **kwargs: Any,
     ) -> None:
         r"""q-Expected Improvement.
 
@@ -188,6 +189,7 @@ def __init__(
         objective: Optional[MCAcquisitionObjective] = None,
         X_pending: Optional[Tensor] = None,
         prune_baseline: bool = False,
+        **kwargs: Any,
     ) -> None:
         r"""q-Noisy Expected Improvement.