From c44fd26458496200a3609d91fd06e3195234e366 Mon Sep 17 00:00:00 2001
From: Nishant Kumar <nishantkr.ece18@itbhu.ac.in>
Date: Fri, 3 Apr 2020 19:11:43 +0530
Subject: [PATCH 1/4] Removing terminal state for Pendulum-v0 env

---
 .../methods/reinforcement_learning/environment/pendulum.hpp | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp b/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
index 55c02668cd..31ac5f1957 100644
--- a/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
+++ b/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
@@ -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;
   }
 

From 67322b791b82fbc415281e86820b1c42fcd276d1 Mon Sep 17 00:00:00 2001
From: Nishant Kumar <nishantkr.ece18@itbhu.ac.in>
Date: Mon, 6 Apr 2020 20:09:53 +0530
Subject: [PATCH 2/4] Update pendulum.hpp

---
 .../methods/reinforcement_learning/environment/pendulum.hpp     | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp b/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
index 31ac5f1957..402a77aedb 100644
--- a/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
+++ b/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
@@ -105,7 +105,7 @@ class Pendulum
            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),

From 88fc2e44549aa9afd02a2261969a401282fd4093 Mon Sep 17 00:00:00 2001
From: Nishant Kumar <nishantkr.ece18@itbhu.ac.in>
Date: Wed, 8 Apr 2020 00:18:37 +0530
Subject: [PATCH 3/4] Updated comment for maxSteps

---
 .../methods/reinforcement_learning/environment/pendulum.hpp     | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp b/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
index 402a77aedb..770e4ee020 100644
--- a/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
+++ b/src/mlpack/methods/reinforcement_learning/environment/pendulum.hpp
@@ -98,7 +98,7 @@ 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,

From f9bdc4b9b1e6c5be56cf3f28dc02eac53db7e467 Mon Sep 17 00:00:00 2001
From: nishantkr18 <nishantkr.ece18@itbhu.ac.in>
Date: Wed, 8 Apr 2020 00:27:24 +0530
Subject: [PATCH 4/4] updated History.md

---
 HISTORY.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/HISTORY.md b/HISTORY.md
index bcd3e5fac6..5bf264ec8f 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -1,5 +1,7 @@
 ### mlpack ?.?.?
 ###### ????-??-??
+  * Updated terminal state for Pendulum environment (#2354).
+
   * Templated return type of `Forward function` of loss functions (#2339).
   
   * Added `R2 Score` regression metric (#2323).