标签：__ venv return self py step vec env def

common/vec_env/vec_env.py模块内容：

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)

 

 

类

class AlreadySteppingError(Exception): 

class NotSteppingError(Exception):

作为异常类不过多介绍。

 

class VecEnv(ABC):  作为抽象类是对gym的环境进行进一步的包装，该类的作用就是进行多环境env的并行操作，也就是并行与环境进行交互和采样。

继承并实现该类进行初始化的时候需要设置并行的环境数和环境的状态空间和动作空间。

该类的主要操作为 reset, step, render ,  这三个操作的含义和gym的设定相同，不同的是并行操作部分：

step函数中调用 self.step_async(actions) 保证多个环境都可以并行的收到下步的动作，self.step_wait() 可以视作阻塞操作用来同步多进程下多个环境的step同步，并将多个环境返回的：

 

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 object

 

向上返回。

 

render函数为绘图动作，该函数将多个环境的当前状态的图片进行拼接，在'human'模式下将拼接后的图片进行绘图操作，在'rgb_array'模式下对拼接后的图片的np.array形式数据进行返回。

多环境当前状态图片的拼接参见： https://www.cnblogs.com/devilmaycry812839668/p/16025513.html

 

 

 

 

 

 

 

================================================

 

标签：__,venv,return,self,py,step,vec,env,def
来源： https://www.cnblogs.com/devilmaycry812839668/p/16027382.html

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。