Update README.md

README.md

@@ -12,6 +12,8 @@ This repo contains the model and the notebook [to this Keras example on Deep Det
 
 Full credits to: [Hemant Singh](https://github.com/amifunny)
 
+![pendulum_gif](https://i.imgur.com/eEH8Cz6.gif)
+
 ## Background Information 
 Deep Deterministic Policy Gradient (DDPG) is a model-free off-policy algorithm for learning continous actions.
 
@@ -39,4 +41,3 @@ Second, it uses Experience Replay.
 
 We store list of tuples (state, action, reward, next_state), and instead of learning only from recent experience, we learn from sampling all of our experience accumulated so far. 
 
-![pendulum_gif](https://i.imgur.com/eEH8Cz6.gif)