yawning_titan.envs.specific.graph_explore.GraphExplore#

class yawning_titan.envs.specific.graph_explore.GraphExplore[source]#

Bases: Env

A custom environment that follows the gym interface spec.

This environment emulates a network and enables an agent to select which node to visit, if it is not possible to move to the node the agent is denied the move.

Initialise environment.

Methods

close

Remove all open visualisations.

render

Render the environment to the screen so that it can be played in realtime.

reset

Reset the initial game configurations.

seed

Sets the seed for this env's random number generator(s).

step

Execute one time step within the environment.

Attributes

metadata = {'render.modes': ['human']}#
NODES = 10#
random_seed = 1010#
GAME_MAX = 1000#
visualisation = None#
action_space = None#
observation_space = None#
reward_range = (-inf, inf)#
step(action)[source]#

Execute one time step within the environment.

reset()[source]#

Reset the initial game configurations.

render(mode='live', close=False)[source]#

Render the environment to the screen so that it can be played in realtime.

close()[source]#

Remove all open visualisations.

seed(seed=None)#

Sets the seed for this env’s random number generator(s).

Note

Some environments use multiple pseudorandom number generators. We want to capture all such seeds used in order to ensure that there aren’t accidental correlations between multiple generators.

Returns:

Returns the list of seeds used in this env’s random

number generators. The first value in the list should be the “main” seed, or the value which a reproducer should pass to ‘seed’. Often, the main seed equals the provided ‘seed’, but this won’t be true if seed=None, for example.

Return type:

list<bigint>

spec = None#
property unwrapped#

Completely unwrap this env.

Returns:

The base non-wrapped gym.Env instance

Return type:

gym.Env