File size: 25,582 Bytes
987ed1b | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 | """
Back ported methods: call, set_attr from v0.26
Disabled auto-reset after done
Added render method.
"""
import numpy as np
import multiprocessing as mp
import time
import sys
from enum import Enum
from copy import deepcopy
from gym import logger
from gym.vector.vector_env import VectorEnv
from gym.error import (
AlreadyPendingCallError,
NoAsyncCallError,
ClosedEnvironmentError,
CustomSpaceError,
)
from gym.vector.utils import (
create_shared_memory,
create_empty_array,
write_to_shared_memory,
read_from_shared_memory,
concatenate,
CloudpickleWrapper,
clear_mpi_env_vars,
)
__all__ = ["AsyncVectorEnv"]
class AsyncState(Enum):
DEFAULT = "default"
WAITING_RESET = "reset"
WAITING_STEP = "step"
WAITING_CALL = "call"
class AsyncVectorEnv(VectorEnv):
"""Vectorized environment that runs multiple environments in parallel. It
uses `multiprocessing` processes, and pipes for communication.
Parameters
----------
env_fns : iterable of callable
Functions that create the environments.
observation_space : `gym.spaces.Space` instance, optional
Observation space of a single environment. If `None`, then the
observation space of the first environment is taken.
action_space : `gym.spaces.Space` instance, optional
Action space of a single environment. If `None`, then the action space
of the first environment is taken.
shared_memory : bool (default: `True`)
If `True`, then the observations from the worker processes are
communicated back through shared variables. This can improve the
efficiency if the observations are large (e.g. images).
copy : bool (default: `True`)
If `True`, then the `reset` and `step` methods return a copy of the
observations.
context : str, optional
Context for multiprocessing. If `None`, then the default context is used.
Only available in Python 3.
daemon : bool (default: `True`)
If `True`, then subprocesses have `daemon` flag turned on; that is, they
will quit if the head process quits. However, `daemon=True` prevents
subprocesses to spawn children, so for some environments you may want
to have it set to `False`
worker : function, optional
WARNING - advanced mode option! If set, then use that worker in a subprocess
instead of a default one. Can be useful to override some inner vector env
logic, for instance, how resets on done are handled. Provides high
degree of flexibility and a high chance to shoot yourself in the foot; thus,
if you are writing your own worker, it is recommended to start from the code
for `_worker` (or `_worker_shared_memory`) method below, and add changes
"""
def __init__(
self,
env_fns,
dummy_env_fn=None,
observation_space=None,
action_space=None,
shared_memory=True,
copy=True,
context=None,
daemon=True,
worker=None,
):
ctx = mp.get_context(context)
self.env_fns = env_fns
self.shared_memory = shared_memory
self.copy = copy
# Added dummy_env_fn to fix OpenGL error in Mujoco
# disable any OpenGL rendering in dummy_env_fn, since it
# will conflict with OpenGL context in the forked child process
if dummy_env_fn is None:
dummy_env_fn = env_fns[0]
dummy_env = dummy_env_fn()
self.metadata = dummy_env.metadata
if (observation_space is None) or (action_space is None):
observation_space = observation_space or dummy_env.observation_space
action_space = action_space or dummy_env.action_space
dummy_env.close()
del dummy_env
super(AsyncVectorEnv, self).__init__(
num_envs=len(env_fns),
observation_space=observation_space,
action_space=action_space,
)
if self.shared_memory:
try:
_obs_buffer = create_shared_memory(
self.single_observation_space, n=self.num_envs, ctx=ctx
)
self.observations = read_from_shared_memory(
_obs_buffer, self.single_observation_space, n=self.num_envs
)
except CustomSpaceError:
raise ValueError(
"Using `shared_memory=True` in `AsyncVectorEnv` "
"is incompatible with non-standard Gym observation spaces "
"(i.e. custom spaces inheriting from `gym.Space`), and is "
"only compatible with default Gym spaces (e.g. `Box`, "
"`Tuple`, `Dict`) for batching. Set `shared_memory=False` "
"if you use custom observation spaces."
)
else:
_obs_buffer = None
self.observations = create_empty_array(
self.single_observation_space, n=self.num_envs, fn=np.zeros
)
self.parent_pipes, self.processes = [], []
self.error_queue = ctx.Queue()
target = _worker_shared_memory if self.shared_memory else _worker
target = worker or target
with clear_mpi_env_vars():
for idx, env_fn in enumerate(self.env_fns):
parent_pipe, child_pipe = ctx.Pipe()
process = ctx.Process(
target=target,
name="Worker<{0}>-{1}".format(type(self).__name__, idx),
args=(
idx,
CloudpickleWrapper(env_fn),
child_pipe,
parent_pipe,
_obs_buffer,
self.error_queue,
),
)
self.parent_pipes.append(parent_pipe)
self.processes.append(process)
process.daemon = daemon
process.start()
child_pipe.close()
self._state = AsyncState.DEFAULT
self._check_observation_spaces()
def seed(self, seeds=None):
self._assert_is_running()
if seeds is None:
seeds = [None for _ in range(self.num_envs)]
if isinstance(seeds, int):
seeds = [seeds + i for i in range(self.num_envs)]
assert len(seeds) == self.num_envs
if self._state != AsyncState.DEFAULT:
raise AlreadyPendingCallError(
"Calling `seed` while waiting "
"for a pending call to `{0}` to complete.".format(self._state.value),
self._state.value,
)
for pipe, seed in zip(self.parent_pipes, seeds):
pipe.send(("seed", seed))
_, successes = zip(*[pipe.recv() for pipe in self.parent_pipes])
self._raise_if_errors(successes)
def reset_async(self):
self._assert_is_running()
if self._state != AsyncState.DEFAULT:
raise AlreadyPendingCallError(
"Calling `reset_async` while waiting "
"for a pending call to `{0}` to complete".format(self._state.value),
self._state.value,
)
for pipe in self.parent_pipes:
pipe.send(("reset", None))
self._state = AsyncState.WAITING_RESET
def reset_wait(self, timeout=None):
"""
Parameters
----------
timeout : int or float, optional
Number of seconds before the call to `reset_wait` times out. If
`None`, the call to `reset_wait` never times out.
Returns
-------
observations : sample from `observation_space`
A batch of observations from the vectorized environment.
"""
self._assert_is_running()
if self._state != AsyncState.WAITING_RESET:
raise NoAsyncCallError(
"Calling `reset_wait` without any prior " "call to `reset_async`.",
AsyncState.WAITING_RESET.value,
)
if not self._poll(timeout):
self._state = AsyncState.DEFAULT
raise mp.TimeoutError(
"The call to `reset_wait` has timed out after "
"{0} second{1}.".format(timeout, "s" if timeout > 1 else "")
)
results, successes = zip(*[pipe.recv() for pipe in self.parent_pipes])
self._raise_if_errors(successes)
self._state = AsyncState.DEFAULT
if not self.shared_memory:
self.observations = concatenate(
results, self.observations, self.single_observation_space
)
return deepcopy(self.observations) if self.copy else self.observations
def step_async(self, actions):
"""
Parameters
----------
actions : iterable of samples from `action_space`
List of actions.
"""
self._assert_is_running()
if self._state != AsyncState.DEFAULT:
raise AlreadyPendingCallError(
"Calling `step_async` while waiting "
"for a pending call to `{0}` to complete.".format(self._state.value),
self._state.value,
)
for pipe, action in zip(self.parent_pipes, actions):
pipe.send(("step", action))
self._state = AsyncState.WAITING_STEP
def step_wait(self, timeout=None):
"""
Parameters
----------
timeout : int or float, optional
Number of seconds before the call to `step_wait` times out. If
`None`, the call to `step_wait` never times out.
Returns
-------
observations : sample from `observation_space`
A batch of observations from the vectorized environment.
rewards : `np.ndarray` instance (dtype `np.float_`)
A vector of rewards from the vectorized environment.
dones : `np.ndarray` instance (dtype `np.bool_`)
A vector whose entries indicate whether the episode has ended.
infos : list of dict
A list of auxiliary diagnostic information.
"""
self._assert_is_running()
if self._state != AsyncState.WAITING_STEP:
raise NoAsyncCallError(
"Calling `step_wait` without any prior call " "to `step_async`.",
AsyncState.WAITING_STEP.value,
)
if not self._poll(timeout):
self._state = AsyncState.DEFAULT
raise mp.TimeoutError(
"The call to `step_wait` has timed out after "
"{0} second{1}.".format(timeout, "s" if timeout > 1 else "")
)
results, successes = zip(*[pipe.recv() for pipe in self.parent_pipes])
self._raise_if_errors(successes)
self._state = AsyncState.DEFAULT
observations_list, rewards, dones, infos = zip(*results)
if not self.shared_memory:
self.observations = concatenate(
observations_list, self.observations, self.single_observation_space
)
return (
deepcopy(self.observations) if self.copy else self.observations,
np.array(rewards),
np.array(dones, dtype=np.bool_),
infos,
)
def close_extras(self, timeout=None, terminate=False):
"""
Parameters
----------
timeout : int or float, optional
Number of seconds before the call to `close` times out. If `None`,
the call to `close` never times out. If the call to `close` times
out, then all processes are terminated.
terminate : bool (default: `False`)
If `True`, then the `close` operation is forced and all processes
are terminated.
"""
timeout = 0 if terminate else timeout
try:
if self._state != AsyncState.DEFAULT:
logger.warn(
"Calling `close` while waiting for a pending "
"call to `{0}` to complete.".format(self._state.value)
)
function = getattr(self, "{0}_wait".format(self._state.value))
function(timeout)
except mp.TimeoutError:
terminate = True
if terminate:
for process in self.processes:
if process.is_alive():
process.terminate()
else:
for pipe in self.parent_pipes:
if (pipe is not None) and (not pipe.closed):
pipe.send(("close", None))
for pipe in self.parent_pipes:
if (pipe is not None) and (not pipe.closed):
pipe.recv()
for pipe in self.parent_pipes:
if pipe is not None:
pipe.close()
for process in self.processes:
process.join()
def _poll(self, timeout=None):
self._assert_is_running()
if timeout is None:
return True
end_time = time.perf_counter() + timeout
delta = None
for pipe in self.parent_pipes:
delta = max(end_time - time.perf_counter(), 0)
if pipe is None:
return False
if pipe.closed or (not pipe.poll(delta)):
return False
return True
def _check_observation_spaces(self):
self._assert_is_running()
for pipe in self.parent_pipes:
pipe.send(("_check_observation_space", self.single_observation_space))
same_spaces, successes = zip(*[pipe.recv() for pipe in self.parent_pipes])
self._raise_if_errors(successes)
if not all(same_spaces):
raise RuntimeError(
"Some environments have an observation space "
"different from `{0}`. In order to batch observations, the "
"observation spaces from all environments must be "
"equal.".format(self.single_observation_space)
)
def _assert_is_running(self):
if self.closed:
raise ClosedEnvironmentError(
"Trying to operate on `{0}`, after a "
"call to `close()`.".format(type(self).__name__)
)
def _raise_if_errors(self, successes):
if all(successes):
return
num_errors = self.num_envs - sum(successes)
assert num_errors > 0
for _ in range(num_errors):
index, exctype, value = self.error_queue.get()
logger.error(
"Received the following error from Worker-{0}: "
"{1}: {2}".format(index, exctype.__name__, value)
)
logger.error("Shutting down Worker-{0}.".format(index))
self.parent_pipes[index].close()
self.parent_pipes[index] = None
logger.error("Raising the last exception back to the main process.")
raise exctype(value)
def call_async(self, name: str, *args, **kwargs):
"""Calls the method with name asynchronously and apply args and kwargs to the method.
Args:
name: Name of the method or property to call.
*args: Arguments to apply to the method call.
**kwargs: Keyword arguments to apply to the method call.
Raises:
ClosedEnvironmentError: If the environment was closed (if :meth:`close` was previously called).
AlreadyPendingCallError: Calling `call_async` while waiting for a pending call to complete
"""
self._assert_is_running()
if self._state != AsyncState.DEFAULT:
raise AlreadyPendingCallError(
"Calling `call_async` while waiting "
f"for a pending call to `{self._state.value}` to complete.",
self._state.value,
)
for pipe in self.parent_pipes:
pipe.send(("_call", (name, args, kwargs)))
self._state = AsyncState.WAITING_CALL
def call_wait(self, timeout = None) -> list:
"""Calls all parent pipes and waits for the results.
Args:
timeout: Number of seconds before the call to `step_wait` times out.
If `None` (default), the call to `step_wait` never times out.
Returns:
List of the results of the individual calls to the method or property for each environment.
Raises:
NoAsyncCallError: Calling `call_wait` without any prior call to `call_async`.
TimeoutError: The call to `call_wait` has timed out after timeout second(s).
"""
self._assert_is_running()
if self._state != AsyncState.WAITING_CALL:
raise NoAsyncCallError(
"Calling `call_wait` without any prior call to `call_async`.",
AsyncState.WAITING_CALL.value,
)
if not self._poll(timeout):
self._state = AsyncState.DEFAULT
raise mp.TimeoutError(
f"The call to `call_wait` has timed out after {timeout} second(s)."
)
results, successes = zip(*[pipe.recv() for pipe in self.parent_pipes])
self._raise_if_errors(successes)
self._state = AsyncState.DEFAULT
return results
def call(self, name: str, *args, **kwargs):
"""Call a method, or get a property, from each parallel environment.
Args:
name (str): Name of the method or property to call.
*args: Arguments to apply to the method call.
**kwargs: Keyword arguments to apply to the method call.
Returns:
List of the results of the individual calls to the method or property for each environment.
"""
self.call_async(name, *args, **kwargs)
return self.call_wait()
def call_each(self, name: str,
args_list: list=None,
kwargs_list: list=None,
timeout = None):
n_envs = len(self.parent_pipes)
if args_list is None:
args_list = [[]] * n_envs
assert len(args_list) == n_envs
if kwargs_list is None:
kwargs_list = [dict()] * n_envs
assert len(kwargs_list) == n_envs
# send
self._assert_is_running()
if self._state != AsyncState.DEFAULT:
raise AlreadyPendingCallError(
"Calling `call_async` while waiting "
f"for a pending call to `{self._state.value}` to complete.",
self._state.value,
)
for i, pipe in enumerate(self.parent_pipes):
pipe.send(("_call", (name, args_list[i], kwargs_list[i])))
self._state = AsyncState.WAITING_CALL
# receive
self._assert_is_running()
if self._state != AsyncState.WAITING_CALL:
raise NoAsyncCallError(
"Calling `call_wait` without any prior call to `call_async`.",
AsyncState.WAITING_CALL.value,
)
if not self._poll(timeout):
self._state = AsyncState.DEFAULT
raise mp.TimeoutError(
f"The call to `call_wait` has timed out after {timeout} second(s)."
)
results, successes = zip(*[pipe.recv() for pipe in self.parent_pipes])
self._raise_if_errors(successes)
self._state = AsyncState.DEFAULT
return results
def set_attr(self, name: str, values):
"""Sets an attribute of the sub-environments.
Args:
name: Name of the property to be set in each individual environment.
values: Values of the property to be set to. If ``values`` is a list or
tuple, then it corresponds to the values for each individual
environment, otherwise a single value is set for all environments.
Raises:
ValueError: Values must be a list or tuple with length equal to the number of environments.
AlreadyPendingCallError: Calling `set_attr` while waiting for a pending call to complete.
"""
self._assert_is_running()
if not isinstance(values, (list, tuple)):
values = [values for _ in range(self.num_envs)]
if len(values) != self.num_envs:
raise ValueError(
"Values must be a list or tuple with length equal to the "
f"number of environments. Got `{len(values)}` values for "
f"{self.num_envs} environments."
)
if self._state != AsyncState.DEFAULT:
raise AlreadyPendingCallError(
"Calling `set_attr` while waiting "
f"for a pending call to `{self._state.value}` to complete.",
self._state.value,
)
for pipe, value in zip(self.parent_pipes, values):
pipe.send(("_setattr", (name, value)))
_, successes = zip(*[pipe.recv() for pipe in self.parent_pipes])
self._raise_if_errors(successes)
def render(self, *args, **kwargs):
return self.call('render', *args, **kwargs)
def _worker(index, env_fn, pipe, parent_pipe, shared_memory, error_queue):
assert shared_memory is None
env = env_fn()
parent_pipe.close()
try:
while True:
command, data = pipe.recv()
if command == "reset":
observation = env.reset()
pipe.send((observation, True))
elif command == "step":
observation, reward, done, info = env.step(data)
# if done:
# observation = env.reset()
pipe.send(((observation, reward, done, info), True))
elif command == "seed":
env.seed(data)
pipe.send((None, True))
elif command == "close":
pipe.send((None, True))
break
elif command == "_call":
name, args, kwargs = data
if name in ["reset", "step", "seed", "close"]:
raise ValueError(
f"Trying to call function `{name}` with "
f"`_call`. Use `{name}` directly instead."
)
function = getattr(env, name)
if callable(function):
pipe.send((function(*args, **kwargs), True))
else:
pipe.send((function, True))
elif command == "_setattr":
name, value = data
setattr(env, name, value)
pipe.send((None, True))
elif command == "_check_observation_space":
pipe.send((data == env.observation_space, True))
else:
raise RuntimeError(
"Received unknown command `{0}`. Must "
"be one of {`reset`, `step`, `seed`, `close`, "
"`_check_observation_space`}.".format(command)
)
except (KeyboardInterrupt, Exception):
error_queue.put((index,) + sys.exc_info()[:2])
pipe.send((None, False))
finally:
env.close()
def _worker_shared_memory(index, env_fn, pipe, parent_pipe, shared_memory, error_queue):
assert shared_memory is not None
env = env_fn()
observation_space = env.observation_space
parent_pipe.close()
try:
while True:
command, data = pipe.recv()
if command == "reset":
observation = env.reset()
write_to_shared_memory(
index, observation, shared_memory, observation_space
)
pipe.send((None, True))
elif command == "step":
observation, reward, done, info = env.step(data)
# if done:
# observation = env.reset()
write_to_shared_memory(
index, observation, shared_memory, observation_space
)
pipe.send(((None, reward, done, info), True))
elif command == "seed":
env.seed(data)
pipe.send((None, True))
elif command == "close":
pipe.send((None, True))
break
elif command == "_call":
name, args, kwargs = data
if name in ["reset", "step", "seed", "close"]:
raise ValueError(
f"Trying to call function `{name}` with "
f"`_call`. Use `{name}` directly instead."
)
function = getattr(env, name)
if callable(function):
pipe.send((function(*args, **kwargs), True))
else:
pipe.send((function, True))
elif command == "_setattr":
name, value = data
setattr(env, name, value)
pipe.send((None, True))
elif command == "_check_observation_space":
pipe.send((data == observation_space, True))
else:
raise RuntimeError(
"Received unknown command `{0}`. Must "
"be one of {`reset`, `step`, `seed`, `close`, "
"`_check_observation_space`}.".format(command)
)
except (KeyboardInterrupt, Exception):
error_queue.put((index,) + sys.exc_info()[:2])
pipe.send((None, False))
finally:
env.close() |