sinergym.utils.wrappers.NormalizeObservation
- class sinergym.utils.wrappers.NormalizeObservation(env: Any, ranges: Dict[str, Sequence[Any]])
- __init__(env: Any, ranges: Dict[str, Sequence[Any]])
Observations normalized to range [0, 1].
- Parameters:
env (Any) – Original Sinergym environment.
ranges (Dict[str, Sequence[Any]]) – Observation variables ranges to apply normalization (rely on environment).
Methods
__init__
(env, ranges)Observations normalized to range [0, 1].
class_name
()Returns the class name of the wrapper.
close
()Closes the wrapper and
env
.Get last environment observation without normalization.
get_wrapper_attr
(name)Gets an attribute from the wrapper and lower environments if name doesn't exist in this object.
observation
(obs)Applies normalization to observation.
render
()Uses the
render()
of theenv
that can be overwritten to change the returned data.reset
(*[, seed, options])Modifies the
env
after callingreset()
, returning a modified observation usingself.observation()
.step
(action)Modifies the
env
after callingstep()
usingself.observation()
on the returned observations.wrapper_spec
(**kwargs)Generates a WrapperSpec for the wrappers.
Attributes
action_space
Return the
Env
action_space
unless overwritten then the wrapperaction_space
is used.metadata
Returns the
Env
metadata
.np_random
Returns the
Env
np_random
attribute.observation_space
Return the
Env
observation_space
unless overwritten then the wrapperobservation_space
is used.render_mode
Returns the
Env
render_mode
.reward_range
Return the
Env
reward_range
unless overwritten then the wrapperreward_range
is used.spec
Returns the
Env
spec
attribute with the WrapperSpec if the wrapper inherits from EzPickle.unwrapped
Returns the base environment of the wrapper.
- get_unwrapped_obs() ndarray | None
Get last environment observation without normalization.
- Returns:
Last original observation. If it is the first observation, this value is None.
- Return type:
Optional[np.ndarray]
- observation(obs: ndarray) ndarray
Applies normalization to observation.
- Parameters:
obs (np.ndarray) – Original observation.
- Returns:
Normalized observation.
- Return type:
np.ndarray