diff --git a/Chapter 13/DQN.py b/Chapter 13/DQN.py
index 09e1190..def9b29 100644
--- a/Chapter 13/DQN.py	
+++ b/Chapter 13/DQN.py	
@@ -3,6 +3,8 @@
 
 # Importing the libraries
 import numpy as np
+import gc 
+import keras
 
 # IMPLEMENTING DEEP Q-LEARNING WITH EXPERIENCE REPLAY
 
@@ -35,10 +37,13 @@ class Dqn(object):
             inputs[i] = current_state
             targets[i] = model.predict(current_state)[0]
             Q_sa = np.max(model.predict(next_state)[0])
+            gc.collect()
+            keras.backend.clear_session()
             if game_over:
                 targets[i, action] = reward
             else:
                 targets[i, action] = reward + self.discount * Q_sa
+
         return inputs, targets
 
 
diff --git a/Chapter 13/train.py b/Chapter 13/train.py
old mode 100644
new mode 100755
index 92856e8..3cc5c40
--- a/Chapter 13/train.py	
+++ b/Chapter 13/train.py	
@@ -2,12 +2,16 @@
 # Training the AI
 
 # Importing the libraries
+import tensorflow as tf
 from environment import Environment
 from brain import Brain
 from DQN import Dqn
 import numpy as np
 import matplotlib.pyplot as plt
-
+import gc
+import os
+import keras 
+
 # Defining the parameters
 memSize = 60000
 batchSize = 32
@@ -56,7 +60,9 @@ while True:
         if np.random.rand() < epsilon:
             action = np.random.randint(0, 4)
         else:
-            qvalues = model.predict(currentState)[0]
+            qvalues = model.predict(tf.convert_to_tensor(currentState))[0]
+            gc.collect()
+            keras.backend.clear_session() 
             action = np.argmax(qvalues)
         
         # Updating the environment