schola.core.spaces.box.BoxSpace

class schola.core.spaces.box.BoxSpace(low, high, shape=None) : Bases: Box, UnrealSpace

A Space representing a box in n-dimensional space.

Parameters: : - low (Union*[float,* np.ndarray*,* List*[float]**]*) – The lower bounds of the box.

• high (Union*[float,* np.ndarray*,* List*[float]**]*) – The upper bounds of the box.
• shape (Tuple*[int]**,* optional) – The shape of the space.

shape : The shape of the space.

Type: : Tuple[int]

Note

Unlike, the gymnasium Box space, this class does not have a dtype attribute. The dtype is always np.float32.

See also

gymnasium.spaces.Box : The gym space object that this class is analogous to.

proto_spaces.BoxSpace : The protobuf representation of this space.

Methods

__init__(low, high[, shape])	Constructor of Box.
contains(x)	Return boolean specifying if x is a valid member of this space.
fill_proto(msg, values)	Convert a python representation of point in this space to a protobuf message.
from_jsonable(sample_n)	Convert a JSONable data type to a batch of samples from this space.
from_proto(message)	Create a Space Object from a protobuf representation.
is_bounded([manner])	Checks whether the box is bounded in some sense.
is_empty_definition(message)	Returns True iff this space has magnitude 0.
merge(*spaces)	Merge multiple BoxSpaces into a single space.
process_data(msg)	Convert a protobuf message corresponding to a point in this space to a pythonic representation.
sample([mask])	Generates a single random sample inside the Box.
seed([seed])	Seed the PRNG of this space and possibly the PRNGs of subspaces.
to_jsonable(sample_n)	Convert a batch of samples from this space to a JSONable data type.
to_normalized()	Normalize the bounds of the space to be between 0 and 1

Attributes

is_np_flattenable	Checks whether this space can be flattened to a spaces.Box.
np_random	Lazily seed the PRNG since this is expensive and only needed if sampling from this space.
shape	Has stricter type than gym.Space - never None.

__init__(low, high, shape=None) : Constructor of Box.

The argument low specifies the lower bound of each dimension and high specifies the upper bounds. I.e., the space that is constructed will be the product of the intervals ([\text{low}[i], \text{high}[i]]).

If low (or high) is a scalar, the lower bound (or upper bound, respectively) will be assumed to be this value across all dimensions.

Parameters: : - low (SupportsFloat | np.ndarray) – Lower bounds of the intervals. If integer, must be at least -2**63.

• high (SupportsFloat | np.ndarray*]*) – Upper bounds of the intervals. If integer, must be at most 2**63 - 2.
• shape (Optional*[Sequence[int]**]*) – The shape is inferred from the shape of low or high np.ndarrays with low and high scalars defaulting to a shape of (1,)
• dtype – The dtype of the elements of the space. If this is an integer type, the Box is essentially a discrete space.
• seed – Optionally, you can use this argument to seed the RNG that is used to sample from the space.

Raises: : ValueError – If no shape information is provided (shape is None, low is None and high is None) then a value error is raised.

fill_proto(msg, values) : Convert a python representation of point in this space to a protobuf message. Mutates msg with the result.

Parameters: : - msg (proto_points.FundamentalPoint) – The protobuf message to fill.

• value (Any) – The pythonic representation of the point.

classmethod from_proto(message) : Create a Space Object from a protobuf representation.

Parameters: : message (proto_space) – The protobuf message to convert.

Returns: : The Space subclass created from the protobuf message

Return type: : UnrealSpace

classmethod is_empty_definition(message) : Returns True iff this space has magnitude 0.

Parameters: : message (proto_space) – The protobuf message to check for emptiness.

Returns: : True iff the space is empty.

Return type: : bool

classmethod merge(*spaces) : Merge multiple BoxSpaces into a single space.

Parameters: : *spaces (List*[BoxSpace]*) – The spaces to merge.

Returns: : The merged space.

Return type: : BoxSpace

Raises: : TypeError – If any of the spaces are not BoxSpaces.

Examples

>>> merged_space = BoxSpace.merge(BoxSpace([0,0],[1,1]), BoxSpace([2,2],[3,3]))
>>> merged_space == BoxSpace([0, 0, 2, 2], [1, 1, 3, 3])
True

process_data(msg) : Convert a protobuf message corresponding to a point in this space to a pythonic representation.

Parameters: : msg (proto_points.FundamentalPoint) – The protobuf message to convert.

Returns: : The pythonic representation of the point.

Return type: : np.ndarray

proto_space : alias of BoxSpace

to_normalized() : Normalize the bounds of the space to be between 0 and 1

Returns: : The normalized space. A modified version of the space this method is called on

Return type: : BoxSpace

Examples

>>> space = BoxSpace([0, 0],[2, 2])
>>> space.to_normalized() == BoxSpace([0., 0.], [1., 1.])
True