Update README.md

README.md

@@ -24,42 +24,39 @@ model-index:
   This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
   
   ## Usage (with Stable-baselines3)
-  ```python
-  import gym
-from stable_baselines3 import PPO
-from stable_baselines3.common.evaluation import evaluate_policy
-from stable_baselines3.common.env_util import make_vec_env
-
-# Create a vectorized environment of 64 parallel environments
-env = make_vec_env("LunarLander-v2", n_envs=64)
-
-# Optimizaed Hyperparameters
-model = PPO(
-    "MlpPolicy",
-    env=env,
-    n_steps=1024,
-    batch_size=32,
-    n_epochs=10,
-    gamma=0.997,
-    gae_lambda=0.98,
-    ent_coef=0.01,
-    verbose=1,
-)
 
-# Train it for 1,000,000 timesteps
-model.learn(total_timesteps=int(1e6))
+Using this model becomes easy when you have stable-baselines3 and huggingface_sb3 installed:
+```
+pip install stable-baselines3
+pip install huggingface_sb3
+```
+Then, you can use the model like this:
+```python
+import gym
 
-# Create a new environment for evaluation
-eval_env = gym.make("LunarLander-v2")
+from huggingface_sb3 import load_from_hub
+from stable_baselines3 import PPO
+from stable_baselines3.common.evaluation import evaluate_policy
 
-# Evaluate the model with 10 evaluation episodes and deterministic=True
-mean_reward, std_reward = evaluate_policy(
-    model, eval_env, n_eval_episodes=10, deterministic=True
-)
+# Retrieve the model from the hub
+## repo_id =  id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name})
+## filename = name of the model zip file from the repository
+checkpoint = load_from_hub(repo_id="kingabzpro/Moonman-Lunar-Landing-v2", filename="Moonman-Lunar-Landing-v2.zip")
+model = PPO.load(checkpoint)
 
-# Print the results
+# Evaluate the agent
+eval_env = gym.make('LunarLander-v2')
+mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
 print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
-
-# >>> mean_reward=261.42 +/- 18.69168514436243
-  ```
+ 
+# Watch the agent play
+obs = eval_env.reset()
+for i in range(1000):
+    action, _state = model.predict(obs)
+    obs, reward, done, info = eval_env.step(action)
+    eval_env.render()
+    if done:
+        obs = eval_env.reset()
+eval_env.close()
+```