Multithreading in Reinforcement Learning Algorithms
A general approach which can be used for any algorithm
1 min readMay 3, 2020
Multithreading code in stable-baselines
from stable_baselines.common.vec_env import SubprocVecEnv
from stable_baselines.common import set_global_seeds, make_vec_envnum_envs = 16 # 2*number of coresenv_name = "CartPole-v0"def make_env(env_name, rank, seed=0):
def _init():
env = gym.make(env_name)
env.seed(seed + rank)
return env
set_global_seeds(seed)
return _init
.
.
.env = SubprocVecEnv([make_env(env_name, i) for i in range(num_cpu)])
envs = SubprocVecEnv(envs)
