from stable_baselines3 import DQN
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.monitor import Monitor
import gymnasium as gym

MODEL_NAME = "ALE-Pacman-v5-control"

# the saved model does not contain the replay buffer
loaded_model = DQN.load(MODEL_NAME)
# print(f"The loaded_model has {loaded_model.replay_buffer.size()} transitions in its buffer")

# now the loaded replay is not empty anymore
# print(f"The loaded_model has {loaded_model.replay_buffer.size()} transitions in its buffer")


# Retrieve the environment
eval_env = Monitor(gym.make("ALE/Pacman-v5", render_mode="human", ))

# Evaluate the policy
mean_reward, std_reward = evaluate_policy(loaded_model.policy, eval_env, n_eval_episodes=10, deterministic=False, )

print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")