File size: 6,195 Bytes
5960497 | 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 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 | import contextlib
import os
from abc import ABC, abstractmethod
from baselines.common.tile_images import tile_images
class AlreadySteppingError(Exception):
"""
Raised when an asynchronous step is running while
step_async() is called again.
"""
def __init__(self):
msg = 'already running an async step'
Exception.__init__(self, msg)
class NotSteppingError(Exception):
"""
Raised when an asynchronous step is not running but
step_wait() is called.
"""
def __init__(self):
msg = 'not running an async step'
Exception.__init__(self, msg)
class VecEnv(ABC):
"""
An abstract asynchronous, vectorized environment.
Used to batch data from multiple copies of an environment, so that
each observation becomes an batch of observations, and expected action is a batch of actions to
be applied per-environment.
"""
closed = False
viewer = None
metadata = {
'render.modes': ['human', 'rgb_array']
}
def __init__(self, num_envs, observation_space, action_space):
self.num_envs = num_envs
self.observation_space = observation_space
self.action_space = action_space
@abstractmethod
def reset(self):
"""
Reset all the environments and return an array of
observations, or a dict of observation arrays.
If step_async is still doing work, that work will
be cancelled and step_wait() should not be called
until step_async() is invoked again.
"""
pass
@abstractmethod
def step_async(self, actions):
"""
Tell all the environments to start taking a step
with the given actions.
Call step_wait() to get the results of the step.
You should not call this if a step_async run is
already pending.
"""
pass
@abstractmethod
def step_wait(self):
"""
Wait for the step taken with step_async().
Returns (obs, rews, dones, infos):
- obs: an array of observations, or a dict of
arrays of observations.
- rews: an array of rewards
- dones: an array of "episode done" booleans
- infos: a sequence of info objects
"""
pass
def close_extras(self):
"""
Clean up the extra resources, beyond what's in this base class.
Only runs when not self.closed.
"""
pass
def close(self):
if self.closed:
return
if self.viewer is not None:
self.viewer.close()
self.close_extras()
self.closed = True
def step(self, actions):
"""
Step the environments synchronously.
This is available for backwards compatibility.
"""
self.step_async(actions)
return self.step_wait()
def render(self, mode='human'):
imgs = self.get_images()
bigimg = tile_images(imgs)
if mode == 'human':
self.get_viewer().imshow(bigimg)
return self.get_viewer().isopen
elif mode == 'rgb_array':
return bigimg
else:
raise NotImplementedError
def get_images(self):
"""
Return RGB images from each environment
"""
raise NotImplementedError
@property
def unwrapped(self):
if isinstance(self, VecEnvWrapper):
return self.venv.unwrapped
else:
return self
def get_viewer(self):
if self.viewer is None:
from gym.envs.classic_control import rendering
self.viewer = rendering.SimpleImageViewer()
return self.viewer
class VecEnvWrapper(VecEnv):
"""
An environment wrapper that applies to an entire batch
of environments at once.
"""
def __init__(self, venv, observation_space=None, action_space=None):
self.venv = venv
super().__init__(num_envs=venv.num_envs,
observation_space=observation_space or venv.observation_space,
action_space=action_space or venv.action_space)
def step_async(self, actions):
self.venv.step_async(actions)
@abstractmethod
def reset(self):
pass
@abstractmethod
def step_wait(self):
pass
def close(self):
return self.venv.close()
def render(self, mode='human'):
return self.venv.render(mode=mode)
def get_images(self):
return self.venv.get_images()
def __getattr__(self, name):
if name.startswith('_'):
raise AttributeError("attempted to get missing private attribute '{}'".format(name))
return getattr(self.venv, name)
class VecEnvObservationWrapper(VecEnvWrapper):
@abstractmethod
def process(self, obs):
pass
def reset(self):
obs = self.venv.reset()
return self.process(obs)
def step_wait(self):
obs, rews, dones, infos = self.venv.step_wait()
return self.process(obs), rews, dones, infos
class CloudpickleWrapper(object):
"""
Uses cloudpickle to serialize contents (otherwise multiprocessing tries to use pickle)
"""
def __init__(self, x):
self.x = x
def __getstate__(self):
import cloudpickle
return cloudpickle.dumps(self.x)
def __setstate__(self, ob):
import pickle
self.x = pickle.loads(ob)
@contextlib.contextmanager
def clear_mpi_env_vars():
"""
from mpi4py import MPI will call MPI_Init by default. If the child process has MPI environment variables, MPI will think that the child process is an MPI process just like the parent and do bad things such as hang.
This context manager is a hacky way to clear those environment variables temporarily such as when we are starting multiprocessing
Processes.
"""
removed_environment = {}
for k, v in list(os.environ.items()):
for prefix in ['OMPI_', 'PMI_']:
if k.startswith(prefix):
removed_environment[k] = v
del os.environ[k]
try:
yield
finally:
os.environ.update(removed_environment)
|