akro package¶
A library containing types of Spaces.
-
class
akro.
Space
(shape=None, dtype=None)[source]¶ Bases:
abc.ABC
,gym.spaces.space.Space
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.
-
concat
(other)[source]¶ Concatenate with another space of the same type.
Parameters: other (Space) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Space
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flatten
(x)[source]¶ Return a flattened observation x.
Parameters: x ( Iterable
) – The object to flatten.Returns: An array of x collapsed into one dimension. Return type: np.ndarray
-
flatten_n
(xs)[source]¶ Return flattened observations xs.
Parameters: xs ( Iterable
) – The object to reshape and flattenReturns: - An array of xs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - Tensor object with the same properties as
the Dict where the shape is modified by batch_dims.
Return type: tf.Tensor
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - Tensor object with the
same properties as the Dict where the shape is modified by batch_dims.
Return type: theano.tensor.TensorVariable
-
-
class
akro.
Box
(low, high, shape=None, dtype=<class 'numpy.float32'>)[source]¶ Bases:
gym.spaces.box.Box
,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.
-
concat
(other)[source]¶ Concatenate with another Box space.
Note that the dimension of both boxes will be flatten.
Parameters: other (Box) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Box
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flatten
(x)[source]¶ Return a flattened observation x.
Parameters: ( (x) – obj:’Iterable`): The object to flatten. Returns: An array of x collapsed into one dimension. Return type: np.ndarray
-
flatten_n
(obs)[source]¶ Return flattened observations obs.
Parameters: obs ( Iterable
) – The object to reshape and flattenReturns: - An array of obs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - Tensor object with the same properties as
the Box where the shape is modified by batch_dims.
Return type: tf.Tensor
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - Tensor object with the
same properties as the Box where the shape is modified by batch_dims.
Return type: theano.tensor.TensorVariable
-
-
class
akro.
Dict
(spaces=None, **kwargs)[source]¶ Bases:
gym.spaces.dict.Dict
,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)})
-
concat
(other)[source]¶ Concatenate with another Dict space.
If a key exists in both Dict, the two associated spaces will be concat. If a key exists in only one Dict, the associated space will be copied to the new Dict.
Parameters: other (Dict) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Dict
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flat_dim_with_keys
(keys)[source]¶ Return a flat dimension of the spaces specified by the keys.
Returns: sum (int)
-
flatten
(x)[source]¶ Return an observation of x with collapsed values.
Parameters: x ( Iterable
) – The object to flatten.Returns: - A Dict where each value is collapsed into a single dimension.
- Keys are unchanged.
Return type: Dict
-
flatten_n
(xs)[source]¶ Return flattened observations xs.
Parameters: xs ( Iterable
) – The object to reshape and flattenReturns: - An array of xs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
flatten_with_keys
(x, keys)[source]¶ Return flattened obs of spaces specified by the keys using x.
Returns: list
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - Tensor object with the same properties as
the Dict where the shape is modified by batch_dims.
Return type: tf.Tensor
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - Tensor object with the
same properties as the Dict where the shape is modified by batch_dims.
Return type: theano.tensor.TensorVariable
-
unflatten
(x)[source]¶ Return an unflattened observation x.
Parameters: x ( Iterable
) – The object to unflatten.Returns: collections.OrderedDict
-
class
akro.
Discrete
(n)[source]¶ Bases:
gym.spaces.discrete.Discrete
,akro.space.Space
{0,1,…,n-1}.
-
concat
(other)[source]¶ Concatenate with another space of the same type.
Parameters: other (Space) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Space
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flatten
(x)[source]¶ Return a flattened observation x.
Parameters: x ( Iterable
) – The object to flatten.Returns: An array of x collapsed into one dimension. Return type: np.ndarray
-
flatten_n
(xs)[source]¶ Return flattened observations xs.
Parameters: xs ( Iterable
) – The object to reshape and flattenReturns: - An array of xs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - Tensor object with the same properties as
the Discrete obj where the shape is modified by batch_dims.
Return type: tf.Tensor
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - Tensor object with the
same properties as the Discrete obj where the shape is modified by batch_dims..
Return type: theano.tensor.TensorVariable
-
unflatten
(x)[source]¶ Return an unflattened observation x.
Parameters: x ( Iterable
) – The object to unflatten.Returns: An array of x in the shape of self.shape. Return type: np.ndarray
-
-
class
akro.
Image
(shape)[source]¶ Bases:
akro.box.Box
An Image, represented by a Box of at most three dimensions.
This class allows us to type check the observation input and decide whether to normalize. Each dimension must have pixel values between [0, 255].
Parameters: shape (tuple) – Shape of the observation. The shape cannot have more than 3 dimensions.
-
class
akro.
Tuple
(spaces)[source]¶ Bases:
gym.spaces.tuple.Tuple
,akro.space.Space
A Tuple of Spaces which produces samples which are Tuples of samples.
-
concat
(other)[source]¶ Concatenate with another Tuple space.
Parameters: other (Tuple) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Tuple
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flatten
(x)[source]¶ Return a flattened observation x.
Parameters: x ( Iterable
) – The object to flatten.Returns: An array of x collapsed into one dimension. Return type: np.ndarray
-
flatten_n
(obs)[source]¶ Return flattened observations obs.
Parameters: obs ( Iterable
) – The object to reshape and flattenReturns: - An array of obs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - A tuple of Tensor objects converted
from each Space in self.spaces. Each Tensor’s shape is modified by batch_dims.
Return type: tuple(tf.Tensor)
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - A tuple of Tensor objects converted
from each Space in self.spaces. Each Tensor’s shape is modified by batch_dims.
Return type: theano.tensor.TensorVariable
-
-
akro.
from_gym
(space, is_image=False)[source]¶ Convert a gym.space to an akro.space.
Parameters: - space (
gym.Space
) – The Space object to convert. - is_image (boolean) – True if input is an image, False otherwise. This is False by default.
Returns: - The gym.Space object converted to an
akro.Space object.
Return type: - space (
-
akro.
concat
(first, second)[source]¶ Concatenate two spaces of the same type.
Parameters: Returns: A concatenated space.
Return type:
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:
gym.spaces.box.Box
,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.
-
concat
(other)[source]¶ Concatenate with another Box space.
Note that the dimension of both boxes will be flatten.
Parameters: other (Box) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Box
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flatten
(x)[source]¶ Return a flattened observation x.
Parameters: ( (x) – obj:’Iterable`): The object to flatten. Returns: An array of x collapsed into one dimension. Return type: np.ndarray
-
flatten_n
(obs)[source]¶ Return flattened observations obs.
Parameters: obs ( Iterable
) – The object to reshape and flattenReturns: - An array of obs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - Tensor object with the same properties as
the Box where the shape is modified by batch_dims.
Return type: tf.Tensor
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - Tensor object with the
same properties as the Box where the shape is modified by batch_dims.
Return type: theano.tensor.TensorVariable
-
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=None, **kwargs)[source]¶ Bases:
gym.spaces.dict.Dict
,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)})
-
concat
(other)[source]¶ Concatenate with another Dict space.
If a key exists in both Dict, the two associated spaces will be concat. If a key exists in only one Dict, the associated space will be copied to the new Dict.
Parameters: other (Dict) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Dict
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flat_dim_with_keys
(keys)[source]¶ Return a flat dimension of the spaces specified by the keys.
Returns: sum (int)
-
flatten
(x)[source]¶ Return an observation of x with collapsed values.
Parameters: x ( Iterable
) – The object to flatten.Returns: - A Dict where each value is collapsed into a single dimension.
- Keys are unchanged.
Return type: Dict
-
flatten_n
(xs)[source]¶ Return flattened observations xs.
Parameters: xs ( Iterable
) – The object to reshape and flattenReturns: - An array of xs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
flatten_with_keys
(x, keys)[source]¶ Return flattened obs of spaces specified by the keys using x.
Returns: list
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - Tensor object with the same properties as
the Dict where the shape is modified by batch_dims.
Return type: tf.Tensor
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - Tensor object with the
same properties as the Dict where the shape is modified by batch_dims.
Return type: theano.tensor.TensorVariable
-
unflatten
(x)[source]¶ Return an unflattened observation x.
Parameters: x ( Iterable
) – The object to unflatten.Returns: collections.OrderedDict
akro.discrete module¶
A space representing a selection between a finite number of items.
-
class
akro.discrete.
Discrete
(n)[source]¶ Bases:
gym.spaces.discrete.Discrete
,akro.space.Space
{0,1,…,n-1}.
-
concat
(other)[source]¶ Concatenate with another space of the same type.
Parameters: other (Space) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Space
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flatten
(x)[source]¶ Return a flattened observation x.
Parameters: x ( Iterable
) – The object to flatten.Returns: An array of x collapsed into one dimension. Return type: np.ndarray
-
flatten_n
(xs)[source]¶ Return flattened observations xs.
Parameters: xs ( Iterable
) – The object to reshape and flattenReturns: - An array of xs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - Tensor object with the same properties as
the Discrete obj where the shape is modified by batch_dims.
Return type: tf.Tensor
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - Tensor object with the
same properties as the Discrete obj where the shape is modified by batch_dims..
Return type: theano.tensor.TensorVariable
-
unflatten
(x)[source]¶ Return an unflattened observation x.
Parameters: x ( Iterable
) – The object to unflatten.Returns: An array of x in the shape of self.shape. Return type: np.ndarray
-
akro.image module¶
A Space representing an RGB Image.
-
class
akro.image.
Image
(shape)[source]¶ Bases:
akro.box.Box
An Image, represented by a Box of at most three dimensions.
This class allows us to type check the observation input and decide whether to normalize. Each dimension must have pixel values between [0, 255].
Parameters: shape (tuple) – Shape of the observation. The shape cannot have more than 3 dimensions.
akro.requires module¶
Decorators used for calling tensorflow and theano functions safely.
akro.space module¶
The abstract base class for all Space types.
-
class
akro.space.
Space
(shape=None, dtype=None)[source]¶ Bases:
abc.ABC
,gym.spaces.space.Space
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.
-
concat
(other)[source]¶ Concatenate with another space of the same type.
Parameters: other (Space) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Space
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flatten
(x)[source]¶ Return a flattened observation x.
Parameters: x ( Iterable
) – The object to flatten.Returns: An array of x collapsed into one dimension. Return type: np.ndarray
-
flatten_n
(xs)[source]¶ Return flattened observations xs.
Parameters: xs ( Iterable
) – The object to reshape and flattenReturns: - An array of xs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - Tensor object with the same properties as
the Dict where the shape is modified by batch_dims.
Return type: tf.Tensor
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - Tensor object with the
same properties as the Dict where the shape is modified by batch_dims.
Return type: theano.tensor.TensorVariable
-
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
(spaces)[source]¶ Bases:
gym.spaces.tuple.Tuple
,akro.space.Space
A Tuple of Spaces which produces samples which are Tuples of samples.
-
concat
(other)[source]¶ Concatenate with another Tuple space.
Parameters: other (Tuple) – A space to be concatenated with this space. Returns: A concatenated space. Return type: Tuple
-
flat_dim
¶ Return the length of the flattened vector of the space.
-
flatten
(x)[source]¶ Return a flattened observation x.
Parameters: x ( Iterable
) – The object to flatten.Returns: An array of x collapsed into one dimension. Return type: np.ndarray
-
flatten_n
(obs)[source]¶ Return flattened observations obs.
Parameters: obs ( Iterable
) – The object to reshape and flattenReturns: - An array of obs in a shape inferred by the size of
- its first element.
Return type: np.ndarray
-
to_tf_placeholder
(name, batch_dims)[source]¶ Create a tensor placeholder from the Space object.
Parameters: Returns: - A tuple of Tensor objects converted
from each Space in self.spaces. Each Tensor’s shape is modified by batch_dims.
Return type: tuple(tf.Tensor)
-
to_theano_tensor
(name, batch_dims)[source]¶ Create a theano tensor from the Space object.
Parameters: Returns: - A tuple of Tensor objects converted
from each Space in self.spaces. Each Tensor’s shape is modified by batch_dims.
Return type: theano.tensor.TensorVariable
-