# Import the libraries
import gym
from stable_baselines3 import PPO
from stable_baselines3.common.evaluation import evaluate_policy

# Load the environment
env = gym.make('LunarLander-v2')

model = PPO.load_from_huggingface(hf_model_id="ThomasSimonini/stable-baselines3-ppo-LunarLander-v2",hf_model_filename="LunarLander-v2")
 
# Evaluate the agent
eval_env = gym.make('LunarLander-v2')
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
 
# Watch the agent play
obs = env.reset()
for i in range(1000):
    action, _state = model.predict(obs)
    obs, reward, done, info = env.step(action)
    env.render()
    if done:
      obs = env.reset()