Update README.md

README.md

@@ -19,6 +19,8 @@ model-index:
       value: 277.82 +/- 22.28
       name: mean_reward
       verified: false
+language:
+- en
 ---
 
 # **PPO** Agent playing **LunarLander-v2**
@@ -30,8 +32,41 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
+from stable_baselines3 import PPO
+from stable_baselines3.common.env_util import make_vec_env
+from stable_baselines3.common.evaluation import evaluate_policy
+
 from huggingface_sb3 import load_from_hub
 
-...
-```
+
+# Download the model checkpoint
+model_checkpoint = load_from_hub("prashanthgowni/ppo-LunarLander-v2", "ppo-LunarLander-v2")
+# Create a vectorized environment
+env = make_vec_env("LunarLander-v2", n_envs=1)
+
+# Load the model
+model = PPO.load(model_checkpoint, env=env)
+
+# Evaluate
+print("Evaluating model")
+mean_reward, std_reward = evaluate_policy(
+    model,
+    env,
+    n_eval_episodes=30,
+    deterministic=True,
+)
+print(f"Mean reward = {mean_reward:.2f} +/- {std_reward}")
+
+# Start a new episode
+obs = env.reset()
+
+try:
+    while True:
+        action, state = model.predict(obs, deterministic=True)
+        obs, reward, done, info = env.step(action)
+        env.render()
+
+except KeyboardInterrupt:
+    pass
+
+```