Update a2c_sb3_cartpole.py

a2c_sb3_cartpole.py

@@ -91,3 +91,31 @@ for i in range(500):
 
 
 env.close()
+
+
+
+
+# Plot the policy loss against iterations
+plt.plot([i for i in range(0,500)],episodes_rewards)
+plt.xlabel('Iterations')
+plt.ylabel('Policy Loss')
+plt.title('Policy Loss vs. Iterations')
+plt.show()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+