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

checkpoint = load_from_hub("jkkawach/ppo-LunarLander-v2", "ppo-LunarLander-v2.zip")
model = PPO.load(checkpoint)

env = make_vec_env("LunarLander-v2", n_envs=1)

print("Evaluating model")
mean_reward, std_reward = evaluate_policy(
    model,
    env,
    n_eval_episodes=20,
    deterministic=True,
)
print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")

obs = env.reset()

try:
    while True:
        action, _states = model.predict(obs, deterministic=True)
        obs, rewards, dones, info = env.step(action)
        env.render()
except KeyboardInterrupt:
    pass