---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: LunarLander-v2
      type: LunarLander-v2
    metrics:
    - type: mean_reward
      value: 250.43 +/- 20.46
      name: mean_reward
      verified: false
---

# **PPO** Agent playing **LunarLander-v2**
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


```python
# !pip install -r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit1/requirements-unit1.txt
## 包有冲突，可以替换为直接安装
# !pip install stable-baselines3==2.0.0a5
# !pip install swig
# !pip install gymnasium
# !pip install box2d-py
# !pip install huggingface_sb3

## 安装模型运行的演示工具
# !sudo apt-get update
# !sudo apt-get install -y python3-opengl
# !apt install ffmpeg
# !apt install xvfb
# !pip3 install pyvirtualdisplay

## 如果演示工具不生效，请重启进程（可选）
# import os
# os.kill(os.getpid(), 9)

# Virtual display
from pyvirtualdisplay import Display

virtual_display = Display(visible=0, size=(1400, 900))
virtual_display.start()

## 安装必要的库
import gymnasium

from huggingface_sb3 import load_from_hub, package_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.env_util import make_vec_env
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.monitor import Monitor


## 环境测试——代码demo示例
import gymnasium as gym

# First, we create our environment called LunarLander-v2
env = gym.make("LunarLander-v2")

# Then we reset this environment
observation, info = 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, terminated, truncated and info
  observation, reward, terminated, truncated, info = env.step(action)

  # If the game is terminated (in our case we land, crashed) or truncated (timeout)
  if terminated or truncated:
      # Reset the environment
      print("Environment is reset")
      observation, info = env.reset()

env.close()


## 加载环境
# 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

# Create the environment（矢量化环境）
env = make_vec_env('LunarLander-v2', n_envs=16)


## 定义策略模型
# SOLUTION
# 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)


## 训练和保存

# SOLUTION
# Train it for 1,000,000 timesteps
model.learn(total_timesteps=1000000)
# Save the model
model_name = "ppo-LunarLander-v2"
model.save(model_name)


## 使用monitor评估得分
#@title
eval_env = Monitor(gym.make("LunarLander-v2", render_mode='rgb_array'))
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")


## 登录hugging face
notebook_login()
!git config --global credential.helper store

## 上传模型与演示视频
import gymnasium as 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 = "LeeJian/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 and set the render_mode="rgb_array"
eval_env = DummyVecEnv([lambda: gym.make(env_id, render_mode="rgb_array")])

# 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)

```