import gym

from stable_baselines3 import A2C
from stable_baselines3.common.env_util import make_vec_env

# Parallel environments
env = gym.make("CartPole-v1")

model = A2C("MlpPolicy", env, verbose=1)
model.learn(total_timesteps=25000)

obs = env.reset()
for i in range (10000):
    action, _states = model.predict(obs)
    obs, rewards, dones, info = env.step(action)
    env.render()

env.close()

model.save("a2c_Cart_Pole")