concepts.benchmark.algorithm_env.graph_env.GraphPathEnv#

class GraphPathEnv[source]#

Bases: GraphEnvBase

Env for Finding a path from starting node to the destination.

Methods

close()

Override close in your subclass to perform any necessary cleanup.

generate_data(nr_data_points)

get_state()

make(n, dist_range[, p, directed, ...])

oracle_policy(state)

Oracle policy: Swap the first two numbers that are not sorted.

render([mode])

Renders the environment.

reset(**kwargs)

Restart the environment.

reset_nr_nodes(nr_nodes)

seed([seed])

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

step(action)

Move to the target node from the current node if has_edge(current -> target).

Attributes

action_space

dist

graph

The generated graph.

metadata

np_random

Initializes the np_random field if not done already.

observation_space

reward_range

spec

unwrapped

Completely unwrap this env.
__init__(nr_nodes, dist_range, p=0.5, directed=False, gen_method='edge', np_random=None, seed=None)[source]#

Initialize the environment.

Parameters:

  • nr_nodes (int) – the number of nodes in the graph.

  • dist_range (Tuple[int, int]) – the sampling range of distance between starting node and the destination.

  • p (float) – parameter for random generation. (Default: 0.5) - (edge method): The probability that an edge doesn’t exist in directed graph. - (dnc method): Control the range of the sample of out-degree. - other methods: Unused.

  • directed (bool) – directed or Undirected graph. Default: False (undirected)

  • gen_method (str) – use which method to randomly generate a graph. - ‘edge’: By sampling the existence of each edge. - ‘dnc’: Sample out-degree (\(m\)) of each node, and link to the nearest neighbors in the unit square. - ‘list’: generate a chain-like graph.

  • np_random (RandomState | None) – random state. If None, a new random state will be created based on the seed.

  • seed (int | None) – random seed. If None, a randomly chosen seed will be used.

__new__(**kwargs)#
close()#

Override close in your subclass to perform any necessary cleanup.

Environments will automatically close() themselves when garbage collected or when the program exits.

generate_data(nr_data_points)[source]#
Parameters:

nr_data_points (int)

get_state()[source]#
classmethod make(n, dist_range, p=0.5, directed=False, gen_method='edge', seed=None)[source]#
Parameters:
Return type:

Env

oracle_policy(state)[source]#

Oracle policy: Swap the first two numbers that are not sorted.

abstract render(mode='human')#

Renders the environment.

The set of supported modes varies per environment. (And some third-party environments may not support rendering at all.) By convention, if mode is:

  • human: render to the current display or terminal and return nothing. Usually for human consumption.

  • rgb_array: Return an numpy.ndarray with shape (x, y, 3), representing RGB values for an x-by-y pixel image, suitable for turning into a video.

  • ansi: Return a string (str) or StringIO.StringIO containing a terminal-style text representation. The text can include newlines and ANSI escape sequences (e.g. for colors).

Note

Make sure that your class’s metadata ‘render_modes’ key includes

the list of supported modes. It’s recommended to call super() in implementations to use the functionality of this method.

Parameters:

mode (str) – the mode to render with

Example:

class MyEnv(Env):

metadata = {‘render_modes’: [‘human’, ‘rgb_array’]}

def render(self, mode=’human’):
if mode == ‘rgb_array’:

return np.array(…) # return RGB frame suitable for video

elif mode == ‘human’:

… # pop up a window and render

else:

super(MyEnv, self).render(mode=mode) # just raise an exception

reset(**kwargs)[source]#

Restart the environment.

reset_nr_nodes(nr_nodes)[source]#
Parameters:

nr_nodes (int)

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>

step(action)[source]#

Move to the target node from the current node if has_edge(current -> target).

property action_space#
property dist: int#
property graph#

The generated graph.

metadata = {'render_modes': []}#
property np_random: RandomState#

Initializes the np_random field if not done already.

property observation_space#
reward_range = (-inf, inf)#
spec = None#
property unwrapped: Env#

Completely unwrap this env.

Returns:

The base non-wrapped gym.Env instance

Return type:

gym.Env

On this page