mriusero/ppo-LunarLander-v2

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)

from huggingface_sb3 import load_from_hub

from stable_baselines3.common.env_util import make_vec_env
from stable_baselines3 import PPO
from stable_baselines3.common.evaluation import evaluate_policy

model_checkpoint = load_from_hub(                # Download model from the hub
    repo_id="mriusero/ppo-LunarLander-v2",
    filename="ppo-LunarLander-v2.zip",
)
env = make_vec_env("LunarLander-v2", n_envs=1)   # Create a vectorized environment
model = PPO.load(model_checkpoint, env=env)      # Load the model

print("Evaluating model")                        # Evaluate the model
mean_reward, std_reward = evaluate_policy(
    model,
    env,
    n_eval_episodes=10,
    deterministic=True,
)
print(f"Mean reward = {mean_reward:.2f} +/- {std_reward}")