ParallelTrainingSB3.py

from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env

# Parallel environments
env = make_vec_env("CartPole-v1", n_envs=4)

model = PPO("MlpPolicy", env, verbose=1)
model.learn(total_timesteps=25000)
model.save("ppo_cartpole")

obs = env.reset()
for i in range(1000):
    action, _state = model.predict(obs, deterministic=True)
    obs, reward, done, info = env.step(action)
    env.render()