akro package¶
A library containing types of Spaces.
-
class
akro.
Space
[source]¶ Bases:
object
Provides a classification state spaces and action spaces.
Allows you to write generic code that applies to any Environment. E.g. to choose a random action.
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
-
class
akro.
Box
(low, high, shape=None, dtype=<class 'numpy.float32'>)[source]¶ Bases:
akro.space.Space
A box in R^n.
Each coordinate is bounded above and below.
-
bounds
¶ Return a 2-tuple containing the lower and upper bounds.
-
dtype
¶ Return the dtype of samples contained in this Space.
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
new_tensor_variable
(name, extra_dims)[source]¶ Create a tensor variable given the name and extra dimensions.
Parameters: - name – name of the variable
- extra_dims – extra dimensions in the front
Returns: the created tensor variable
-
shape
¶ Return the shape of samples contained in this Space.
-
-
class
akro.
Dict
(spaces)[source]¶ Bases:
akro.space.Space
A dictionary of simpler spaces, e.g. Discrete, Box.
- Example usage:
- self.observation_space = spaces.Dict({“position”: spaces.Discrete(2),
- “velocity”: spaces.Discrete(3)})
-
flat_dim
¶ Return a flat dimension of the dict space.
- Returns:
- flat_dim (int)
-
from_jsonable
(sample_n)[source]¶ Convert information from a JSON format into a list.
- Returns:
- ret (list)
-
class
akro.
Discrete
(n)[source]¶ Bases:
akro.space.Space
{0,1,…,n-1}.
-
default_value
¶ Return the default value of the spaceself.
This is always just 0.
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
n
¶ Return the number of elements in the Discrete space.
-
-
class
akro.
Tuple
(*components)[source]¶ Bases:
akro.space.Space
A Tuple of Spaces which produces samples which are Tuples of samples.
-
components
¶ Each of the spaces making up this Tuple space.
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
Subpackages¶
Submodules¶
akro.box module¶
A Space representing a rectangular region of space.
-
class
akro.box.
Box
(low, high, shape=None, dtype=<class 'numpy.float32'>)[source]¶ Bases:
akro.space.Space
A box in R^n.
Each coordinate is bounded above and below.
-
bounds
¶ Return a 2-tuple containing the lower and upper bounds.
-
dtype
¶ Return the dtype of samples contained in this Space.
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
new_tensor_variable
(name, extra_dims)[source]¶ Create a tensor variable given the name and extra dimensions.
Parameters: - name – name of the variable
- extra_dims – extra dimensions in the front
Returns: the created tensor variable
-
shape
¶ Return the shape of samples contained in this Space.
-
akro.dict module¶
Cartesian product of multiple named Spaces (also known as a dict of Spaces).
This Space produces samples which are dicts, where the values of those dicts are drawn from the values of this Space.
-
class
akro.dict.
Dict
(spaces)[source]¶ Bases:
akro.space.Space
A dictionary of simpler spaces, e.g. Discrete, Box.
- Example usage:
- self.observation_space = spaces.Dict({“position”: spaces.Discrete(2),
- “velocity”: spaces.Discrete(3)})
-
flat_dim
¶ Return a flat dimension of the dict space.
- Returns:
- flat_dim (int)
-
from_jsonable
(sample_n)[source]¶ Convert information from a JSON format into a list.
- Returns:
- ret (list)
akro.discrete module¶
A space representing a selection between a finite number of items.
-
class
akro.discrete.
Discrete
(n)[source]¶ Bases:
akro.space.Space
{0,1,…,n-1}.
-
default_value
¶ Return the default value of the spaceself.
This is always just 0.
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
n
¶ Return the number of elements in the Discrete space.
-
akro.space module¶
The abstract base class for all Space types.
-
class
akro.space.
Space
[source]¶ Bases:
object
Provides a classification state spaces and action spaces.
Allows you to write generic code that applies to any Environment. E.g. to choose a random action.
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
akro.tuple module¶
Cartesian product of multiple Spaces (also known as a tuple of Spaces).
This Space produces samples which are Tuples, where the elments of those Tuples are drawn from the components of this Space.
-
class
akro.tuple.
Tuple
(*components)[source]¶ Bases:
akro.space.Space
A Tuple of Spaces which produces samples which are Tuples of samples.
-
components
¶ Each of the spaces making up this Tuple space.
-
flat_dim
¶ Return the length of the flattened vector of the space.
-