Missing line in Saving and loading (#369)

* Missing line in Saving and loading

* Bugs in Background & C51 docs

docs/source/usage/tutorials/Deep/Background.rst

@@ -60,7 +60,7 @@ The State Value Function is defined as the expected return starting from only St
     V^{\pi}(s) = E\left[ R_{t} \right]
 
 State Action Value Function
----------------------
+---------------------------
 
 The Action Value Function is defined as the expected return starting from a state s and a taking an action a.
 

docs/source/usage/tutorials/Deep/Categorical_DQN.rst

@@ -1,3 +1,4 @@
+===========================
 Categorical Deep Q-Networks
 ===========================
 

docs/source/usage/tutorials/Saving and loading.rst

@@ -6,6 +6,7 @@ We often want to checkpoint our training model in the RL setting, GenRL offers t
 Following is a sample code to save checkpoints - 
 
 .. code-block:: python
+
     import gym
     import shutil
     
@@ -33,6 +34,7 @@ Following is a sample code to save checkpoints -
 Let's say you have a saved weights and hyperparameters file to load onto the model you can change your trainer as below to load it - 
 
 .. code-block:: python
+
     trainer = OnPolicyTrainer(
         algo,
         env,