Stable-baselines: SubprocVecEnv problem

[maystroh]

When I try to use run a training with multiprocessed environments using the following code

Code example

import gym
import numpy as np

from stable_baselines.common.policies import MlpPolicy
from stable_baselines.common.vec_env import SubprocVecEnv
from stable_baselines.common import set_global_seeds
from stable_baselines import ACKTR

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_global_seeds(seed)
    return _init

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)])

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

obs = env.reset()
for _ in range(1000):
    action, _states = model.predict(obs)
    obs, rewards, dones, info = env.step(action)
    env.render()

It crashes with the following error:

File "/opt/conda/lib/python3.6/multiprocessing/forkserver.py", line 196, in main
    _serve_one(s, listener, alive_r, old_handlers)
  File "/opt/conda/lib/python3.6/multiprocessing/forkserver.py", line 231, in _serve_one
    code = spawn._main(child_r)
  File "/opt/conda/lib/python3.6/multiprocessing/spawn.py", line 114, in _main
    prepare(preparation_data)
  File "/opt/conda/lib/python3.6/multiprocessing/spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/opt/conda/lib/python3.6/multiprocessing/spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "/opt/conda/lib/python3.6/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/opt/conda/lib/python3.6/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/opt/conda/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/hassan/ClusterGPU/data_GPU/hassan/SurgerySimulator/Local_RL_Cataract/ml-agents-gym/trainings/unity-gym/cataract_mono_tests/test_xvbf.py", line 28, in <module>
    env = SubprocVecEnv([make_env(env_id, i) for i in range(num_cpu)])
  File "/data_GPU/hassan/SurgerySimulator/Local_RL_Cataract/ml-agents-gym/stable_baselines/common/vec_env/subproc_vec_env.py", line 90, in __init__
    process.start()
  File "/opt/conda/lib/python3.6/multiprocessing/process.py", line 105, in start
    self._popen = self._Popen(self)
  File "/opt/conda/lib/python3.6/multiprocessing/context.py", line 291, in _Popen
    return Popen(process_obj)
  File "/opt/conda/lib/python3.6/multiprocessing/popen_forkserver.py", line 35, in __init__
    super().__init__(process_obj)
  File "/opt/conda/lib/python3.6/multiprocessing/popen_fork.py", line 19, in __init__
    self._launch(process_obj)
  File "/opt/conda/lib/python3.6/multiprocessing/popen_forkserver.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/opt/conda/lib/python3.6/multiprocessing/spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "/opt/conda/lib/python3.6/multiprocessing/spawn.py", line 136, in _check_not_importing_main
    is not going to be frozen to produce an executable.''')
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
Traceback (most recent call last):
  File "test_xvbf.py", line 28, in <module>
    env = SubprocVecEnv([make_env(env_id, i) for i in range(num_cpu)])
  File "/data_GPU/hassan/SurgerySimulator/Local_RL_Cataract/ml-agents-gym/stable_baselines/common/vec_env/subproc_vec_env.py", line 95, in __init__
    observation_space, action_space = self.remotes[0].recv()
  File "/opt/conda/lib/python3.6/multiprocessing/connection.py", line 250, in recv
    buf = self._recv_bytes()
  File "/opt/conda/lib/python3.6/multiprocessing/connection.py", line 407, in _recv_bytes
    buf = self._recv(4)
  File "/opt/conda/lib/python3.6/multiprocessing/connection.py", line 379, in _recv
    chunk = read(handle, remaining)
ConnectionResetError: [Errno 104] Connection reset by peer

System Info
Describe the characteristic of your environment:

• Describe how the library was installed: source
• GPU models and configuration: GTX 1080Ti
• Python version: 3.6
• Tensorflow version: 1.8

[Miffyli]

As the error message suggests, try putting your code into functions and have the if __name__ == '__main__' start the code, i.e.

import gym
import numpy as np

from stable_baselines.common.policies import MlpPolicy
from stable_baselines.common.vec_env import SubprocVecEnv
from stable_baselines.common import set_global_seeds
from stable_baselines import ACKTR

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_global_seeds(seed)
    return _init

def 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)])

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

    obs = env.reset()
    for _ in range(1000):
        action, _states = model.predict(obs)
        obs, rewards, dones, info = env.step(action)
        env.render()

if __name__ == '__main__':
    main()

This should not be a problem on *nixes which use forking for multiprocessing by default, but for you it seems to be starting new processes for some reason.

[maystroh]

Thanks, it was my bad.

[araffin]

Your problem was already explained in the documentation...