"""
The MIT License
Copyright (c) 2017 OpenAI (http://openai.com)
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
"""
import numpy as np
from gym import spaces
from . import VecEnv
from .util import copy_obs_dict, dict_to_obs, obs_space_info
[docs]class DummyVecEnv(VecEnv):
"""
VecEnv that does runs multiple environments sequentially, that is,
the step and reset commands are send to one environment at a time.
Useful when debugging and when num_env == 1 (in the latter case,
avoids communication overhead)
"""
def __init__(self, env_fns):
"""
Arguments:
env_fns: iterable of callables functions that build environments
"""
self.envs = [fn() for fn in env_fns]
env = self.envs[0]
VecEnv.__init__(self, len(env_fns), env.observation_space, env.action_space, env.spec, env_type=env.unwrapped.__module__)
obs_space = env.observation_space
self.keys, shapes, dtypes = obs_space_info(obs_space)
self.buf_obs = { k: np.zeros((self.num_envs,) + tuple(shapes[k]), dtype=dtypes[k]) for k in self.keys }
self.buf_dones = np.zeros((self.num_envs,), dtype=np.bool)
self.buf_rews = np.zeros((self.num_envs,), dtype=np.float32)
self.buf_infos = [{} for _ in range(self.num_envs)]
self.actions = None
[docs] def step_async(self, actions):
listify = True
try:
if len(actions) == self.num_envs:
listify = False
except TypeError:
pass
if not listify:
self.actions = actions
else:
assert self.num_envs == 1, "actions {} is either not a list or has a wrong size - cannot match to {} environments".format(actions, self.num_envs)
self.actions = [actions]
[docs] def step_wait(self):
for e in range(self.num_envs):
action = self.actions[e]
if isinstance(self.envs[e].action_space, spaces.Discrete):
action = int(action)
obs, self.buf_rews[e], self.buf_dones[e], self.buf_infos[e] = self.envs[e].step(action)
if self.buf_dones[e]:
obs = self.envs[e].reset()
self._save_obs(e, obs)
return (self._obs_from_buf(), np.copy(self.buf_rews), np.copy(self.buf_dones),
self.buf_infos.copy())
[docs] def reset(self):
for e in range(self.num_envs):
obs = self.envs[e].reset()
self._save_obs(e, obs)
return self._obs_from_buf()
def _save_obs(self, e, obs):
for k in self.keys:
if k is None:
self.buf_obs[k][e] = obs
else:
self.buf_obs[k][e] = obs[k]
def _obs_from_buf(self):
return dict_to_obs(copy_obs_dict(self.buf_obs))
[docs] def get_images(self):
return [env.render(mode='rgb_array') for env in self.envs]
[docs] def set_rng_state(self, states):
for env, state in zip(self.envs, states):
env.unwrapped.np_random.set_state(state)
[docs] def get_rng_state(self):
return [env.unwrapped.np_random.get_state() for env in self.envs]
[docs] def state_dict(self):
states = []
for env in self.envs:
if hasattr(env.unwrapped, "get_env_state"):
states += [env.unwrapped.get_env_state()]
else:
states += [None]
return states
[docs] def load_state_dict(self, state_dicts):
for env, state_dict in zip(self.envs, state_dicts):
if hasattr(env.unwrapped, "set_env_state"):
env.unwrapped.set_env_state(state_dict)
[docs] def render(self, mode='human'):
if self.num_envs == 1:
return self.envs[0].render(mode=mode)
else:
return super().render(mode=mode)