PPO Agent playing LunarLander-v2
A trained PPO agent playing LunarLander-v2, made with the stable-baselines3 library.
Usage
from huggingface_sb3 import load_from_hub
from stable_baselines3 import PPO
checkpoint = load_from_hub("rondahahda/ppo-LunarLander-v2", "ppo-LunarLander-v2.zip")
model = PPO.load(checkpoint)
- Downloads last month
- 15
Evaluation results
- mean_reward on LunarLander-v2self-reported274.47 +/- 19.84