qgym.spaces.dict module

This module contains the Dict space, i.e., a dictionary with fixed strings as keys and spaces as values.

Usage:
>>> from qgym.spaces import Box, Dict
>>> box1 = Box(low=0, high=20, shape=(2, 3), dtype=int)
>>> box2 = Box(low=-5, high=1, shape=(3, 2), dtype=float)
>>> Dict(box1=box1, box2=box2)
Dict(box1:Box([[0 0 0]
 [0 0 0]], [[20 20 20]
 [20 20 20]], (2, 3), int32), box2:Box([[-5. -5.]
 [-5. -5.]
 [-5. -5.]], [[1. 1.]
 [1. 1.]
 [1. 1.]], (3, 2), float64))
class qgym.spaces.dict.Dict(spaces=None, *, rng=None, **spaces_kwargs)[source]

Bases: Dict

Dictionary of other action/observation spaces for use in RL environments.

__init__(spaces=None, *, rng=None, **spaces_kwargs)[source]

Initialize a Dict space, with string valued keys and spaces inheriting from gym.Space as values.

Parameters:

  • spaces (dict[str, Space[Any]] | Sequence[tuple[str, Space[Any]]] | None) – Dictionary containing string valued keys and spaces that are to form

  • space. (this Dict)

  • rng (Generator | None) – Random number generator to be used in this space, if None a new one will be constructed.

  • spaces_kwargs (Space[Any]) – Spaces that are to form this Dict space.