Upload README.md with huggingface_hub

README.md

@@ -26,8 +26,8 @@ Vision-Language Navigation system. Trained to execute VLM navigation commands
 ## Training
 
 - **Algorithm**: PPO with GAE-λ
-- **Steps trained**: 2,048
-- **Final intent-following rate**: 14.2%
+- **Steps trained**: 1,998,848
+- **Final intent-following rate**: 98.3%
 - **Reward**: R_INTENT=+2.5 (follow VLM), R_INTENT_MISS=-0.5 (diverge), R_COLLISION=-10
 
 ### Hyperparameters