RenderImagesWrapper
Full path:
schola.sb3.utils.RenderImagesWrapper
schola.sb3.utils.RenderImagesWrapper
RenderImagesWrapper
RenderImagesWrapper(venv)Bases: VecEnvWrapper
Renders image observations to an interactive matplotlib window. It assumes that the observations are square RGB images, and attempts to reshape any box observation to 3xLxL.
Parameters
venv (VecEnv)
: The vectorized environment being wrapped.
Methods
| Item | Description |
|---|---|
| init | — |
| close | — |
| convert_to_plt_format | Convert to a format supported by matplotlib. |
| reset | — |
| step | — |
| step_async | — |
| step_wait | — |
| update_images | Updates the images in the plt window with the given observations. |
init
__init__(venv)Parameters
venv (VecEnv)
close
close()convert_to_plt_format
convert_to_plt_format(obs)Convert to a format supported by matplotlib. (e.g. (W,H), (W,H,3), and (W,H,4)). No Chanels or Chanels last, from Chanels first.
Parameters
obs (np.ndarray)
: The observation to convert.
Returns
The converted observation.
Return type: np.ndarray
reset
reset()Returns
VecEnvObs
step
step(action)Parameters
action (ndarray)
Returns
Tuple[VecEnvObs, ndarray, ndarray, List[Dict]]
step_async
step_async(actions)Parameters
actions (ndarray)
Returns
None
step_wait
step_wait()Returns
Tuple[VecEnvObs, ndarray, ndarray, List[Dict]]
update_images
update_images(obs)Updates the images in the plt window with the given observations.
Parameters
obs (Dict[str,np.ndarray])
: Maps the names of the observations to the observation data.
Returns
The original observation.
Return type: Dict[str,np.ndarray]