Update README.md

README.md

@@ -122,19 +122,19 @@ We trained a GPT-2 policy agent using HuggingFace TRL (Proximal Policy Optimizat
 👉 **This demonstrates measurable learning, not random behavior.**
 
 ### Reward Curve
-![Training Reward Curve](
+Training Reward Curve
 
 ![Screenshot 2026-04-26 163716](https://cdn-uploads.huggingface.co/production/uploads/68e1066110db6d257dfceb12/J_jMixXqJNBc7AEYp4hxr.png)
 
-)
+
 *The PPO agent successfully learns to outperform the random baseline, finding stable fiscal policies that maximize the multi-objective reward.*
 
 ### Baseline vs. Trained Comparison
-![Comparison Chart](
+Comparison Chart
 
 ![Screenshot 2026-04-26 164009](https://cdn-uploads.huggingface.co/production/uploads/68e1066110db6d257dfceb12/tNnWRZDymTsXVTPfVbtAt.png)
 
-)
+
 *The trained agent demonstrates significant improvement across all difficulty tiers, particularly in the macroeconomic stabilization task.*
 
 ---