Pixel observation wrapper for gym.Env.

class PixelObservationWrapper(env, headless=True)

Bases: gym.Wrapper

Inheritance diagram of garage.envs.wrappers.pixel_observation.PixelObservationWrapper

Pixel observation wrapper for obtaining pixel observations.

Instead of returning the default environment observation, the wrapped environment’s render function is used to produce RGB pixel observations.

This behaves like gym.wrappers.PixelObservationWrapper but returns a gym.spaces.Box observation space and observation instead of a gym.spaces.Dict.

  • env (gym.Env) – The environment to wrap. This environment must produce non-pixel observations and have a Box observation space.

  • headless (bool) – If true, this creates a window to init GLFW. Set to true if running on a headless machine or with a dummy X server, false otherwise.

property observation_space(self)

gym.spaces.Box: Environment observation space.

reset(self, **kwargs)

gym.Env reset function.


kwargs (dict) – Keyword arguments to be passed to gym.Env.reset.


Pixel observation of shape \((O*, )\)

from the wrapped environment.

Return type


step(self, action)

gym.Env step function.

Performs one action step in the enviornment.


action (np.ndarray) – Action of shape \((A*, )\) to pass to the environment.


Pixel observation of shape \((O*, )\)

from the wrapped environment.

float : Amount of reward returned after previous action. bool : Whether the episode has ended, in which case further step()

calls will return undefined results.

dict: Contains auxiliary diagnostic information (helpful for

debugging, and sometimes learning).

Return type


property spec(self)
classmethod class_name(cls)
render(self, mode='human', **kwargs)

Renders the environment.

The set of supported modes varies per environment. (And some environments do not support rendering at all.) By convention, if mode is:

  • human: render to the current display or terminal and return nothing. Usually for human consumption.

  • rgb_array: Return an numpy.ndarray with shape (x, y, 3), representing RGB values for an x-by-y pixel image, suitable for turning into a video.

  • ansi: Return a string (str) or StringIO.StringIO containing a terminal-style text representation. The text can include newlines and ANSI escape sequences (e.g. for colors).


Make sure that your class’s metadata ‘render.modes’ key includes

the list of supported modes. It’s recommended to call super() in implementations to use the functionality of this method.


mode (str) – the mode to render with


class MyEnv(Env):

metadata = {‘render.modes’: [‘human’, ‘rgb_array’]}

def render(self, mode=’human’):
if mode == ‘rgb_array’:

return np.array(…) # return RGB frame suitable for video

elif mode == ‘human’:

… # pop up a window and render


super(MyEnv, self).render(mode=mode) # just raise an exception


Override close in your subclass to perform any necessary cleanup.

Environments will automatically close() themselves when garbage collected or when the program exits.

seed(self, seed=None)

Sets the seed for this env’s random number generator(s).


Some environments use multiple pseudorandom number generators. We want to capture all such seeds used in order to ensure that there aren’t accidental correlations between multiple generators.


Returns the list of seeds used in this env’s random

number generators. The first value in the list should be the “main” seed, or the value which a reproducer should pass to ‘seed’. Often, the main seed equals the provided ‘seed’, but this won’t be true if seed=None, for example.

Return type


compute_reward(self, achieved_goal, desired_goal, info)
property unwrapped(self)

Completely unwrap this env.


The base non-wrapped gym.Env instance

Return type