Update README.md

README.md

@@ -25,13 +25,137 @@ 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)
-TODO: Add your code
+## Install dependencies and create a virtual screen 🔽
 
+```python
+# Virtual display
+from pyvirtualdisplay import Display
+
+virtual_display = Display(visible=0, size=(1400, 900))
+virtual_display.start()
+```
+## Import the packages 📦
+```python
+import gym
+
+from huggingface_sb3 import load_from_hub, package_to_hub, push_to_hub
+from huggingface_hub import notebook_login # To log to our Hugging Face account to be able to upload models to the Hub.
+
+from stable_baselines3 import PPO
+from stable_baselines3.common.evaluation import evaluate_policy
+from stable_baselines3.common.env_util import make_vec_env
+```
+## Understand what is Gym and how it works 🤖
+```python
+import gym
+
+# First, we create our environment called LunarLander-v2
+env = gym.make("LunarLander-v2")
+
+# Then we reset this environment
+observation = env.reset()
+
+for _ in range(20):
+  # Take a random action
+  action = env.action_space.sample()
+  print("Action taken:", action)
+
+  # Do this action in the environment and get
+  # next_state, reward, done and info
+  observation, reward, done, info = env.step(action)
+  
+  # If the game is done (in our case we land, crashed or timeout)
+  if done:
+      # Reset the environment
+      print("Environment is reset")
+      observation = env.reset()
+```
+## Create the LunarLander environment 🌛 and understand how it works
+```python
+# We create our environment with gym.make("<name_of_the_environment>")
+env = gym.make("LunarLander-v2")
+env.reset()
+print("_____OBSERVATION SPACE_____ \n")
+print("Observation Space Shape", env.observation_space.shape)
+print("Sample observation", env.observation_space.sample()) # Get a random observation
+print("\n _____ACTION SPACE_____ \n")
+print("Action Space Shape", env.action_space.n)
+print("Action Space Sample", env.action_space.sample()) # Take a random action
+
+# Create the environment
+env = make_vec_env('LunarLander-v2', n_envs=16)
+```
+## Create the Model 🤖
+```python
+# We added some parameters to accelerate the training
+model = PPO(
+    policy = 'MlpPolicy',
+    env = env,
+    n_steps = 1024,
+    batch_size = 64,
+    n_epochs = 4,
+    gamma = 0.999,
+    gae_lambda = 0.98,
+    ent_coef = 0.01,
+    verbose=1)
+model_name = "ppo-LunarLander-v2"
+```
+
+## Train the PPO agent 🏃
+```python
+# Train it for 1,000,000 timesteps
+model.learn(total_timesteps=3000000)
+# Save the model
+model.save(model_name)
+```
 
+## Evaluate the agent 📈
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+#load the model
+model = model.load("/content/ppo-LunarLander-v2.zip")
 
-...
+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}")
+```
+## Publish our trained model on the Hub 🔥
+```python
+notebook_login()
+!git config --global credential.helper store
 ```
+```python
+import gym
+
+from stable_baselines3 import PPO
+from stable_baselines3.common.vec_env import DummyVecEnv
+from stable_baselines3.common.env_util import make_vec_env
+
+from huggingface_sb3 import package_to_hub
+
+# PLACE the variables you've just defined two cells above
+# Define the name of the environment
+env_id = "LunarLander-v2"
+
+# TODO: Define the model architecture we used
+model_architecture = "PPO"
+
+## Define a repo_id
+## repo_id is the id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name} for instance ThomasSimonini/ppo-LunarLander-v2
+## CHANGE WITH YOUR REPO ID
+repo_id = "vicfeuga/ppo-LunarLander-v2" # Change with your repo id, you can't push with mine 😄
+
+## Define the commit message
+commit_message = "Upload PPO LunarLander-v2 trained agent"
+
+# Create the evaluation env
+eval_env = DummyVecEnv([lambda: gym.make(env_id)])
+
+# PLACE the package_to_hub function you've just filled here
+package_to_hub(model=model, # Our trained model
+               model_name=model_name, # The name of our trained model 
+               model_architecture=model_architecture, # The model architecture we used: in our case PPO
+               env_id=env_id, # Name of the environment
+               eval_env=eval_env, # Evaluation Environment
+               repo_id=repo_id, # id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name} for instance ThomasSimonini/ppo-LunarLander-v2
+               commit_message=commit_message)
+```