PPO Agent playing LunarLander-v3

This is a trained model of a PPO agent playing LunarLander-v3 using the stable-baselines3 library.

Usage (with Stable-baselines3)

from huggingface_sb3 import load_from_hub, package_to_hub
from huggingface_hub import notebook_login
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
import gymnasium as gym
from stable_baselines3.common.vec_env import DummyVecEnv



env = make_vec_env("LunarLander-v3", 4)
print(f"Espaço Observado {env.observation_space.shape}")
print(f"Amostras {env.observation_space.sample()}")
print(f"Ações: {env.action_space.n}")

model = PPO(
    policy="MlpPolicy",
    env=env,
    n_steps=1024,
    batch_size=64,
    n_epochs=2,
    gamma=0.999,
    gae_lambda=0.98,
    ent_coef=0.01,
    verbose=1)

model.learn(1500000)

eval_env = make_vec_env("LunarLander-v3", 4)
mean_reward, std_reward = evaluate_policy(model,eval_env,n_eval_episodes=10,deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward:.2f}")

model_name = "ppo-LunarLander-v3"
model.save(model_name)

package_to_hub(
    model=model,  # Our trained model
    model_name=model_name,  # The name of our trained model
    model_architecture="PPO",  # The model architecture we used: in our case PPO
    env_id='LunarLander-v3',  # Name of the environment
    eval_env=DummyVecEnv([lambda: Monitor(gym.make("LunarLander-v3", render_mode="rgb_array"))]),  # Evaluation Environment
    repo_id="kaikytoledo/LunarLander",  # id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name} for instance ThomasSimonini/ppo-LunarLander-v2
    commit_message="Modelo LunarLander",
)

...