from stable_baselines3.common.monitor import Monitor
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3 import SAC
from stock_env import StockEnv
import const as cst

MODEL_NAME = [
    #'best_model_1',
    'best_model_ab_120c',
    'best_model_ab_128c_2',
    'best_model_ab_128c_3',
    'best_model_ab_128c_4',
    'best_model_able',
    'best_model_all',
    'best_model_all_128c',
    'best_model_all_128c_2',
    'best_model_all_128c_3',
    'best_model_all_128c_4',
    'best_model_all_128c_5',
    'best_model_all_128c_2000_4',
    'best_model_all_128c_2000_4_16l',
    'best_model_all_128c_2000_5',
    'best_model_all_128c_4000_5',
    'best_model_all_128c_6000_4',
    'best_model_zz500',
    'best_model_zz500_128c',

    'sac_stock_all_128c_5',
    'sac_stock_all_128c_16l',
    'sac_stock_all_128c_2000_4',
    'sac_stock_all_128c_2000_4_16l',
    'sac_stock_all_128c_2000_5',
    'sac_stock_all_128c_4000_5',
    'sac_stock_all_128c_6000_4'
]

# The algorithms require a vectorized environment to run
env = Monitor(StockEnv())
for it in MODEL_NAME:

    model = SAC.load("./model/"+it,env)
    mean_reward, std_reward = evaluate_policy(model, env, n_eval_episodes=10, render=False)
    print(f"{it} {mean_reward} {std_reward}")