README.md

---
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: 231.79 +/- 17.99
      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)
```python
import gymnasium as gym
from stable_baselines3 import PPO
from stable_baselines3.common.monitor import Monitor
from stable_baselines3.common.evaluation import evaluate_policy
from huggingface_sb3 import load_from_hub

repo_id = "JohnnyBoy00/ppo-LunarLander-v2"
filename = "ppo-LunarLander-v2.zip"

# The model was trained with Python 3.8, which uses Pickle Protocol 5.
# However, Python 3.6 and 3.7 use Pickle Protocol 4.
# Thus, in order to ensure compatibility, it is necessary to:
# 1. Install pickle5 (we done it at the beginning of the colab);
# 2. Create a custom empty object, which is passed as a parameter to PPO.load().
custom_objects = {
    "learning_rate": 0.0,
    "lr_schedule": lambda _: 0.0,
    "clip_range": lambda _: 0.0,
}

checkpoint = load_from_hub(repo_id, filename)
model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)

eval_env = Monitor(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}")
```