100 lines
3.4 KiB
Python
100 lines
3.4 KiB
Python
import numpy as np
|
|
from multiprocessing import Process, Pipe
|
|
from baselines.common.vec_env import VecEnv, CloudpickleWrapper
|
|
from baselines.common.tile_images import tile_images
|
|
|
|
|
|
def worker(remote, parent_remote, env_fn_wrapper):
|
|
parent_remote.close()
|
|
env = env_fn_wrapper.x()
|
|
while True:
|
|
cmd, data = remote.recv()
|
|
if cmd == 'step':
|
|
ob, reward, done, info = env.step(data)
|
|
if done:
|
|
ob = env.reset()
|
|
remote.send((ob, reward, done, info))
|
|
elif cmd == 'reset':
|
|
ob = env.reset()
|
|
remote.send(ob)
|
|
elif cmd == 'render':
|
|
remote.send(env.render(mode='rgb_array'))
|
|
elif cmd == 'close':
|
|
remote.close()
|
|
break
|
|
elif cmd == 'get_spaces':
|
|
remote.send((env.observation_space, env.action_space))
|
|
else:
|
|
raise NotImplementedError
|
|
|
|
|
|
class SubprocVecEnv(VecEnv):
|
|
def __init__(self, env_fns, spaces=None):
|
|
"""
|
|
envs: list of gym environments to run in subprocesses
|
|
"""
|
|
self.waiting = False
|
|
self.closed = False
|
|
nenvs = len(env_fns)
|
|
self.remotes, self.work_remotes = zip(*[Pipe() for _ in range(nenvs)])
|
|
# using CloudPickleWrapper, when multiprocessing communicate
|
|
# it pickles env_fun high level before, and load before using it.
|
|
self.ps = [Process(target=worker, args=(work_remote, remote, CloudpickleWrapper(env_fn)))
|
|
for (work_remote, remote, env_fn) in zip(self.work_remotes, self.remotes, env_fns)]
|
|
for p in self.ps:
|
|
p.daemon = True # if the main process crashes, we should not cause things to hang
|
|
p.start()
|
|
for remote in self.work_remotes:
|
|
remote.close()
|
|
|
|
self.remotes[0].send(('get_spaces', None))
|
|
observation_space, action_space = self.remotes[0].recv()
|
|
VecEnv.__init__(self, len(env_fns), observation_space, action_space)
|
|
|
|
def step_async(self, actions):
|
|
for remote, action in zip(self.remotes, actions):
|
|
remote.send(('step', action))
|
|
self.waiting = True
|
|
|
|
def step_wait(self):
|
|
results = [remote.recv() for remote in self.remotes]
|
|
self.waiting = False
|
|
obs, rews, dones, infos = zip(*results)
|
|
return np.stack(obs), np.stack(rews), np.stack(dones), infos
|
|
|
|
def reset(self):
|
|
for remote in self.remotes:
|
|
remote.send(('reset', None))
|
|
return np.stack([remote.recv() for remote in self.remotes])
|
|
|
|
def reset_task(self):
|
|
for remote in self.remotes:
|
|
remote.send(('reset_task', None))
|
|
return np.stack([remote.recv() for remote in self.remotes])
|
|
|
|
def close(self):
|
|
if self.closed:
|
|
return
|
|
if self.waiting:
|
|
for remote in self.remotes:
|
|
remote.recv()
|
|
for remote in self.remotes:
|
|
remote.send(('close', None))
|
|
for p in self.ps:
|
|
p.join()
|
|
self.closed = True
|
|
|
|
def render(self, mode='human'):
|
|
for pipe in self.remotes:
|
|
pipe.send(('render', None))
|
|
imgs = [pipe.recv() for pipe in self.remotes]
|
|
bigimg = tile_images(imgs)
|
|
if mode == 'human':
|
|
import cv2
|
|
cv2.imshow('vecenv', bigimg[:, :, ::-1])
|
|
cv2.waitKey(1)
|
|
elif mode == 'rgb_array':
|
|
return bigimg
|
|
else:
|
|
raise NotImplementedError
|