Update README.md

README.md

@@ -27,7 +27,7 @@ We call this **Schema Drift**. Most Reinforcement Learning (RL) agents are train
 
 You can see exactly what that collapse looks like in the performance data:
 
-![Chart showing cumulative reward and cache hit rate under drift, titled "Baseline Policies Collapsing Under Schema Drift".](image_3.png)
+![Performance Graph](https://huggingface.co/umar-sharif821/CDN-cache-optimizer/resolve/main/results.png)
 
 ### How We Built It (The Tech Stack)
 We didn't want to build just another "toy" environment. We wanted something that felt like real-world infrastructure.