Update README.md

README.md

@@ -40,9 +40,19 @@ This is a trained **PPO agent** for the **LunarLander-v2** environment using Sta
 - Learning rate: 3e-4  
 - Optimizer: Adam  
 
-## 🎥 Demo
+---
+
+## 🎥 Demo (Preview)
+
 ![LunarLander](lunarlander.gif)
 
+---
+
+## 🎬 Full Demo Video
+👉 [Watch the full video here](replay.mp4)
+
+---
+
 ## 🛠 Usage
 
 ```python
@@ -55,20 +65,17 @@ from huggingface_hub import hf_hub_download
 # -------------------------
 # Environment Setup
 # -------------------------
-# Environment for human rendering
-env = gym.make("LunarLander-v2", render_mode="human")
-
-# Environment for evaluation (no render)
-eval_env = Monitor(gym.make("LunarLander-v2"))
+env = gym.make("LunarLander-v2", render_mode="human")       # Human render
+eval_env = Monitor(gym.make("LunarLander-v2"))              # Evaluation (no render)
 
 # -------------------------
-# Load pretrained model from Hugging Face Hub
+# Load pretrained model
 # -------------------------
 model_path = hf_hub_download("Vishand03/lunarlander-ppo", "model.zip")
 model = PPO.load(model_path)
 
 # -------------------------
-# Run a single episode
+# Run one episode
 # -------------------------
 obs, _ = env.reset()
 done = False