PPO Agent playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library.
Usage (with Stable-baselines3)
TODO: Add to your code
import gymnasium as gym
from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub
checkpoint_model = load_from_hub(
repo_id="Creador270/ppo-LunarLander-v2_hello_RL",
filename="ppo-LunarLander-v2_hello_RL_2.zip",
model = PPO.load(checkpoint_model) #The model you will be using
env = gym.make("LunarLander-v2")
observation, info = env.reset()
#It must be deterministic because, in the action space, we can only choose between which motor must be activated
action, _states = model.predict(observation, deterministic=True)
)
- Downloads last month
- 9
Evaluation results
- mean_reward on LunarLander-v2self-reported294.83 +/- 15.86