dracero commited on
Commit
9fd094a
1 Parent(s): bbf7d11

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -3
README.md CHANGED
@@ -26,12 +26,41 @@ This is a trained model of a **PPO** agent playing **LunarLander-v2**
26
  using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
 
28
  ## Usage (with Stable-baselines3)
29
- TODO: Add your code
30
 
31
 
32
  ```python
33
- from stable_baselines3 import ...
34
- from huggingface_sb3 import load_from_hub
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
 
36
  ...
37
  ```
 
26
  using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
 
28
  ## Usage (with Stable-baselines3)
29
+ TODO: Diego's code
30
 
31
 
32
  ```python
33
+ import gymnasium as gym
34
+ from stable_baselines3.common.vec_env import DummyVecEnv
35
+ from stable_baselines3.common.env_util import make_vec_env
36
+
37
+ from huggingface_sb3 import package_to_hub
38
+
39
+ ## TODO: Define a repo_id
40
+ ## 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
41
+ repo_id =
42
+
43
+ # TODO: Define the name of the environment
44
+ env_id =
45
+
46
+ # Create the evaluation env and set the render_mode="rgb_array"
47
+ eval_env = DummyVecEnv([lambda: Monitor(gym.make(env_id, render_mode="rgb_array"))])
48
+
49
+
50
+ # TODO: Define the model architecture we used
51
+ model_architecture = ""
52
+
53
+ ## TODO: Define the commit message
54
+ commit_message = ""
55
+
56
+ # method save, evaluate, generate a model card and record a replay video of your agent before pushing the repo to the hub
57
+ package_to_hub(model=model, # Our trained model
58
+ model_name=model_name, # The name of our trained model
59
+ model_architecture=model_architecture, # The model architecture we used: in our case PPO
60
+ env_id=env_id, # Name of the environment
61
+ eval_env=eval_env, # Evaluation Environment
62
+ 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
63
+ commit_message=commit_message)
64
 
65
  ...
66
  ```