concepts.benchmark.blocksworld.blocksworld_env.ToGroundBind2ndBlockWorldEnv#

class ToGroundBind2ndBlockWorldEnv[source]#

Bases: ToGroundBlockWorldEnv

Methods

`close`()	Override close in your subclass to perform any necessary cleanup.
`get_current_state`()
`render`([mode])	Renders the environment.
`reset`(**kwargs)	Reset the environment.
`reset_nr_blocks`(nr_blocks)	Reset the number of blocks.
`seed`([seed])	Sets the seed for this env's random number generator(s).
`step`(action)	Run one timestep of the environment's dynamics.

Attributes

`action_space`
`metadata`
`np_random`	Initializes the np_random field if not done already.
`nr_objects`	Get the number of objects in the environment.
`observation_space`
`reward_range`
`spec`
`unwrapped`	Completely unwrap this env.
`world`	The current blocksworld.
`is_over`	Whether the current episode is over.
`cached_result`	The result of the current episode.

__init__(nr_blocks, random_order=False, prob_unchanged=0.0, prob_fall=0.0, np_random=None, seed=None)#

Initialize the blocksworld environment.

Parameters:

nr_blocks (int) – number of blocks.
random_order (bool) – randomly permute the indexes of the blocks. This option prevents the models from memorizing the configurations.
prob_unchanged (float) – the probability of not changing the state.
prob_fall (float) – the probability of falling to the ground.
np_random (RandomState | None)
seed (int | None)

__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.

get_current_state()#

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)#: Reset the environment. This function first generates a random blocksworld, and then returns the current state.

reset_nr_blocks(nr_blocks)#

Reset the number of blocks.

Parameters:: nr_blocks (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]#

Run one timestep of the environment’s dynamics. When end of episode is reached, you are responsible for calling reset() to reset this environment’s state.

Accepts an action and returns a tuple (observation, reward, done, info).

Parameters:: action – an action provided by the environment
Returns:: agent’s observation of the current environment reward: amount of reward returned after previous action done: whether the episode has ended, in which case further step() calls will return undefined results info: contains auxiliary diagnostic information (helpful for debugging, and sometimes learning)
Return type:: observation

property action_space#

cached_result: Tuple[float, bool] | None#: The result of the current episode. It is a tuple of (reward, is_over).

is_over: bool#: Whether the current episode is over.

metadata = {'render_modes': []}#

property np_random: RandomState#: Initializes the np_random field if not done already.

property nr_objects#: Get the number of objects in the environment.

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

world: BlockWorld#: The current blocksworld.