mdp_playground.spaces.image_continuous.ImageContinuous

class mdp_playground.spaces.image_continuous.ImageContinuous(feature_space, term_spaces=None, width=100, height=100, circle_radius=5, target_point=None, relevant_indices=[0, 1], seed=None, grid_shape=None, dtype=<class 'numpy.uint8'>)[source]

Bases: gym.spaces.box.Box

A space that maps a continuous 1- or 2-D space 1-to-1 to images so that the images may be used as representations for corresponding continuous environments.

get_concatenated_image(continuous_obs)[source]

Gets an image representation for a given feature space observation

Parameters

  • feature_space (Gym.spaces.Box) – The feature space to which this class associates images as external observations

  • term_spaces (list of Gym.spaces.Box) – Sub-spaces of the feature space which are terminal

  • width (int) – The width of the image

  • height (int) – The height of the image

  • circle_radius (int) – The radius of the circle which represents the agent and target point

  • target_point (np.array) –

  • relevant_indices (list) –

  • grid_shape (tuple of length 2) –

  • seed (int) – Seed for this space

__init__(feature_space, term_spaces=None, width=100, height=100, circle_radius=5, target_point=None, relevant_indices=[0, 1], seed=None, grid_shape=None, dtype=<class 'numpy.uint8'>)[source]
Parameters

  • feature_space (Gym.spaces.Box) – The feature space to which this class associates images as external observations

  • term_spaces (list of Gym.spaces.Box) – Sub-spaces of the feature space which are terminal

  • width (int) – The width of the image

  • height (int) – The height of the image

  • circle_radius (int) – The radius of the circle which represents the agent and target point

  • target_point (np.array) –

  • relevant_indices (list) –

  • grid_shape (tuple of length 2) –

  • seed (int) – Seed for this space

Methods

__init__(feature_space[, term_spaces, …])

param feature_space

The feature space to which this class associates images as external

contains(x)

Return boolean specifying if x is a valid member of this space

convert_to_pixel(position)

from_jsonable(sample_n)

Convert a JSONable data type to a batch of samples from this space.

generate_image(position[, relevant])

param position

get_concatenated_image(obs)

Gets the “stitched together” image made from images corresponding to each continuous sub-space within the continuous space, concatenated along the X-axis.

is_bounded([manner])

sample()

Generates a single random sample inside of the Box.

seed([seed])

Seed the PRNG of this space.

to_jsonable(sample_n)

Convert a batch of samples from this space to a JSONable data type.
contains(x)[source]

Return boolean specifying if x is a valid member of this space

convert_to_pixel(position)[source]
from_jsonable(sample_n)[source]

Convert a JSONable data type to a batch of samples from this space.

generate_image(position, relevant=True)[source]
Parameters

position (np.array) –

get_concatenated_image(obs)[source]

Gets the “stitched together” image made from images corresponding to each continuous sub-space within the continuous space, concatenated along the X-axis.

sample()[source]

Generates a single random sample inside of the Box.

In creating a sample of the box, each coordinate is sampled according to the form of the interval:

  • [a, b] : uniform distribution

  • [a, oo) : shifted exponential distribution

  • (-oo, b] : shifted negative exponential distribution

  • (-oo, oo) : normal distribution

seed(seed=None)

Seed the PRNG of this space.

to_jsonable(sample_n)[source]

Convert a batch of samples from this space to a JSONable data type.

mdp_playground.spaces.image_continuous mdp_playground.spaces.image_multi_discrete