Update README.md

README.md

@@ -41,7 +41,7 @@ This is a trained **PPO agent** for the **LunarLander-v2** environment using Sta
 - Optimizer: Adam  
 
 ## 🎥 Demo
-![LunarLander](lunarlander_loop.gif)
+![LunarLander](lunarlander.gif)
 
 ## 🛠 Usage
 
@@ -52,19 +52,24 @@ from stable_baselines3.common.monitor import Monitor
 from stable_baselines3.common.evaluation import evaluate_policy
 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"))
 
-# Download the model from Hugging Face Hub
+# -------------------------
+# Load pretrained model from Hugging Face Hub
+# -------------------------
 model_path = hf_hub_download("Vishand03/lunarlander-ppo", "model.zip")
-
-# Load the model
 model = PPO.load(model_path)
 
+# -------------------------
 # Run a single episode
+# -------------------------
 obs, _ = env.reset()
 done = False
 while not done:
@@ -72,6 +77,8 @@ while not done:
     obs, reward, terminated, truncated, _ = env.step(action)
     done = terminated or truncated
 
-# Evaluate the policy
+# -------------------------
+# Evaluate policy
+# -------------------------
 mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
 print(f"Mean Reward: {mean_reward:.2f} +/- {std_reward:.2f}")