import gymnasium as gym
from huggingface_sb3 import load_from_hub
from stable_baselines3 import PPO
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.monitor import Monitor

env_id = "LunarLander-v2"

model_fp = load_from_hub(
    "jostyposty/drl-course-unit-01-lunar-lander-v2",
    "ppo-LunarLander-v2_010_000_000_hf_defaults.zip",
)

model = PPO.load(model_fp, print_system_info=True)
eval_env = Monitor(gym.make(env_id))
mean_reward, std_reward = evaluate_policy(
    model, eval_env, n_eval_episodes=10, deterministic=True
)
print(f"results: {mean_reward - std_reward:.2f}")
print(f"mean_reward: {mean_reward:.2f} +/- {std_reward}")