diff --git a/3-atari/2-pong/README.md b/3-atari/2-pong/README.md
index ed36684b..0bb45f69 100644
--- a/3-atari/2-pong/README.md
+++ b/3-atari/2-pong/README.md
@@ -4,10 +4,10 @@ Minimal implementation of Stochastic Policy Gradient Algorithm in Keras
 
 ## Pong Agent
 
-![pg](assetsg.gif)
+![pg](assets/pg.gif)
 
 
 This PG agent seems to get more frequent wins after about 8000 episodes. Below is the score graph.
 
 
-![score](assetscore.png)
+![score](assets/score.png)