diff --git a/src/lerobot/rl/actor.py b/src/lerobot/rl/actor.py
index 6d73891b6..164d25e5f 100644
--- a/src/lerobot/rl/actor.py
+++ b/src/lerobot/rl/actor.py
@@ -327,7 +327,8 @@ def act_with_policy(
 
         # Check for intervention from transition info
         intervention_info = new_transition[TransitionKey.INFO]
-        if intervention_info.get(TeleopEvents.IS_INTERVENTION, False):
+        is_intervention = intervention_info.get(TeleopEvents.IS_INTERVENTION, False)
+        if is_intervention:
             episode_intervention = True
             episode_intervention_steps += 1
 
@@ -335,6 +336,7 @@ def act_with_policy(
             "discrete_penalty": torch.tensor(
                 [new_transition[TransitionKey.COMPLEMENTARY_DATA].get("discrete_penalty", 0.0)]
             ),
+            TeleopEvents.IS_INTERVENTION: is_intervention,
         }
         # Create transition for learner (convert to old format)
         list_transition_to_send_to_learner.append(