diff --git a/HISTORY.md b/HISTORY.md
index 9e5c560e5b..cc43905132 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -1,5 +1,7 @@
 ### mlpack ?.?.?
 ###### ????-??-??
+  * Updated terminal state for Pendulum environment (#2354).
+
   * Added `EliSH` activation function (#2323).
 
   * Add L1 Loss function (#2203).
diff --git a/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp b/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
index 55c02668cd..770e4ee020 100644
--- a/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
+++ b/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
@@ -98,14 +98,14 @@ class Pendulum
    *    state is considered terminal.
    * @param doneReward The reward recieved by the agent on success.
    * @param maxSteps The number of steps after which the episode
-   *    terminates. If the value is 0, there is no limit.
+   *    terminates. If the value is 0, there is no limit (Default: 200 steps). 
    */
   Pendulum(const double maxAngularVelocity = 8,
            const double maxTorque = 2.0,
            const double dt = 0.05,
            const double angleThreshold = M_PI / 12,
            const double doneReward = 0.0,
-           const size_t maxSteps = 0) :
+           const size_t maxSteps = 200) :
       maxAngularVelocity(maxAngularVelocity),
       maxTorque(maxTorque),
       dt(dt),
@@ -222,12 +222,6 @@ class Pendulum
           "being taken.";
       return true;
     }
-    else if (state.Theta() > M_PI - angleThreshold ||
-        state.Theta() < -M_PI + angleThreshold)
-    {
-      Log::Info << "Episode terminated due to agent succeeding.";
-      return true;
-    }
     return false;
   }