12-RN

pip install sb3-contrib gymnasium numpy

from sb3_contrib import MaskablePPO
from sb3_contrib.common.wrappers import ActionMasker
import gymnasium as gym

# Load 십이장기 environment
env = gym.make("MiniChess-v0")  # Environment name kept for compatibility
env = ActionMasker(env, lambda e: e.unwrapped.get_valid_actions())

# Load trained model
model = MaskablePPO.load("model_up.zip")

# Play
obs, info = env.reset()
done = False

while not done:
    # Get valid actions
    action_masks = env.unwrapped.get_valid_actions()
    
    # Predict with masking
    action, _states = model.predict(obs, action_masks=action_masks, deterministic=False)
    
    # Execute action
    obs, reward, terminated, truncated, info = env.step(action)
    done = terminated or truncated

print(f"Game ended with reward: {{reward}}")