Update README.md

README.md

@@ -74,7 +74,7 @@ mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, d
 print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
 ```
 
-## 3. Re-train model (choice 1)
+## 3. Re-train model (Optional 1)
 
 ```python
 # Load a saved LunarLander model from the Hub and retrain
@@ -143,7 +143,7 @@ package_to_hub(model=model, # Our trained model
                commit_message=commit_message)
 ```
 
-## 4. Re-train model (choice 2)
+## 4. Re-train model (Optional 2)
 - Change `--repo_id` become your repo id :)
 - `--id_retrain` and `--filename_retrain` in order to load my trained model, you can change to your trained model
 ```python
@@ -151,7 +151,7 @@ package_to_hub(model=model, # Our trained model
 --commit_message "retrain model from hub 5m" \
 --id_retrain "thien1892/LunarLander-v2-ppo-v5" \
 --filename_retrain "ppo-LunarLander-v2.zip" \
---total_timesteps 5000000 \
---learning_rate 1e-6 \
+--total_timesteps 2000000 \
+--learning_rate 3e-5 \
 --n_envs 64
 ```