File size: 1,464 Bytes
f5657ed | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | import gym
import numpy as np
from stable_baselines3 import PPO
from stable_baselines3.common.vec_env import DummyVecEnv, SubprocVecEnv
from stable_baselines3.common.env_util import make_vec_env
from stable_baselines3.common.utils import set_random_seed
def make_env(env_id, rank, seed=0):
"""
Utility function for multiprocessed env.
:param env_id: (str) the environment ID
:param num_env: (int) the number of environments you wish to have in subprocesses
:param seed: (int) the inital seed for RNG
:param rank: (int) index of the subprocess
"""
def _init():
env = gym.make(env_id)
env.seed(seed + rank)
return env
set_random_seed(seed)
return _init
if __name__ == '__main__':
env_id = "CartPole-v1"
num_cpu = 4 # Number of processes to use
# Create the vectorized environment
env = SubprocVecEnv([make_env(env_id, i) for i in range(num_cpu)])
# Stable Baselines provides you with make_vec_env() helper
# which does exactly the previous steps for you.
# You can choose between `DummyVecEnv` (usually faster) and `SubprocVecEnv`
# env = make_vec_env(env_id, n_envs=num_cpu, seed=0, vec_env_cls=SubprocVecEnv)
model = PPO('MlpPolicy', env, verbose=1)
model.learn(total_timesteps=25_000)
obs = env.reset()
for _ in range(1000):
action, _states = model.predict(obs)
obs, rewards, dones, info = env.step(action)
env.render() |