Update README.md

Add training code

README.md

@@ -56,3 +56,35 @@ mean_reward, std_reward = evaluate_policy(model, env,
 # Print the results
 print('mean_reward={:.2f} +/- {:.2f}'.format(mean_reward, std_reward))
 ```
+
+## Training (with Stable-baselines3)
+```python
+from huggingface_sb3 import load_from_hub
+
+from stable_baselines3 import PPO
+from stable_baselines3.common.evaluation import evaluate_policy
+from stable_baselines3.common.env_util import make_vec_env
+
+# Create the evaluation envs
+env = make_vec_env('LunarLander-v2', n_envs=16)
+env = gym.make('LunarLander-v2')
+
+# Instantiate the agent
+model = PPO(
+    policy = 'MlpPolicy',
+    env = env,
+    n_steps = 1024,
+    batch_size = 32,
+    n_epochs = 8,
+    gamma = 0.99,
+    gae_lambda = 0.95,
+    ent_coef = 0.01,
+    verbose=1,
+    seed=2022)
+
+# Train
+model.learn(total_timesteps=1500000)
+# Save model
+model_name = "Any-Name"
+model.save(model_name)
+```