EpisodeIterator class
Episode Iterator class that gives options for how a list of episodes should be iterated.
Some options are desirable for better internal simulator performance.
More context: simulator suffers overhead when switching between scenes, therefore episodes of the same scene should be consecutively loaded. However, if too many consecutive episodes from same scene are feed into RL model, the model will risk overfitting that scene. Therefore it’s better to load same scene consecutively and switch once a number threshold is reached.
Currently supports the following features:
- Cycling: when all episodes are iterated, cycle back to start instead of throwing StopIteration.
- Cycling with shuffle: when cycling back, shuffle episodes groups grouped by scene.
- Group by scene: episodes of same scene will be grouped and loaded consecutively.
- Set max scene repeat: set a number threshold on how many episodes from the same scene can be loaded consecutively.
- Sample episodes: sample the specified number of episodes.
Static methods
- def _randomize_value(value: int, value_range: float) -> int
- Generates a random int from a uniform distribution centered at value within the provided range of variance.
Methods
- def _forced_scene_switch(self) -> None
- Internal method to switch the scene. Moves remaining episodes from current scene to the end and switch to next scene episodes.
- def _forced_scene_switch_if(self) -> None
- Triggers switching scenes and re-organizes the Episode queue if the maximum number of repetitions or steps per-scene has been reached.
- def _group_scenes(self, episodes: typing.Union[typing.Sequence[Episode], typing.List[Episode], numpy.ndarray]) -> typing.List[T]
- Internal method that groups episodes by scene Groups will be ordered by the order their first episode’s appearance in the list of episodes.
- def _set_shuffle_intervals(self) -> None
- Sets or samples the maximum number of repeated episodes for a scene before shuffling.
- def _shuffle(self) -> None
- Internal method that shuffles the remaining episodes. If
self.group_by_sceneis true, then shuffle groups of scenes. - def set_next_episode_by_id(self, episode_id: str) -> None
- Set the next episode to run by episode ID. The new episode will be loading upon resetting the simulator.
- def set_next_episode_by_index(self, episode_index: int) -> None
- Set the next episode to run by episode index. The new episode will be loading upon resetting the simulator.
- def step_taken(self) -> None
- Increments the step counter.
Special methods
- def __class_getitem__(...)
- Represent a PEP 585 generic type
- def __init__(self, episodes: typing.Sequence[T], cycle: bool = True, shuffle: bool = False, group_by_scene: bool = True, max_scene_repeat_episodes: int = -1, max_scene_repeat_steps: int = -1, num_episode_sample: int = -1, step_repetition_range: float = 0.2, seed: typing.Optional[int] = None) -> None
- def __iter__(self) -> EpisodeIterator
- def __next__(self) -> Episode
- Main logic for handling how episodes iterate.
- def __subclasshook__(C)
Method documentation
def habitat.
Generates a random int from a uniform distribution centered at value within the provided range of variance.
| Parameters | |
|---|---|
| value | The int mean of the distribution for the sample. |
| value_range | The float [0,1] which indicates the range of the sampling distribution as a ratio of the mean. For example, value_range==0.1 would produce a uniformly sampled value with a maximum 10% deviation of the mean [value*0.9, value*1.1]. |
| Returns | The randomly sampled value from the distribution. |
def habitat.
Internal method that groups episodes by scene Groups will be ordered by the order their first episode’s appearance in the list of episodes.
| Parameters | |
|---|---|
| episodes | The Episodes to group and re-order. |
| Returns | The Episodes grouped and re-orderd by scene. |
So if the episodes list shuffled before calling this method, the scenes will be in a random order.
def habitat.
Set the next episode to run by episode ID. The new episode will be loading upon resetting the simulator.
| Parameters | |
|---|---|
| episode_id | The desired id string for the next Episode queued by the iterator. |
def habitat.
Set the next episode to run by episode index. The new episode will be loading upon resetting the simulator.
| Parameters | |
|---|---|
| episode_index | The desired index for the next Episode queued by the iterator. |
def habitat.
Represent a PEP 585 generic type
E.g. for t = list[int], t.__origin__ is list and t.__args__ is (int,).
def habitat.
| Parameters | |
|---|---|
| episodes | list of episodes. |
| cycle | if True, cycle back to first episodes when
StopIteration. |
| shuffle | if True, shuffle scene groups when cycle. No
effect if cycle is set to False. Will shuffle grouped scenes
if group_by_scene is True. |
| group_by_scene | if True, group episodes from same scene. |
| max_scene_repeat_episodes | threshold of how many episodes from the same
scene can be loaded consecutively. -1 for no limit |
| max_scene_repeat_steps | threshold of how many steps from the same
scene can be taken consecutively. -1 for no limit |
| num_episode_sample | number of episodes to be sampled. -1
for no sampling. |
| step_repetition_range | The maximum number of steps within each scene is uniformly drawn from [1 - step_repeat_range, 1 + step_repeat_range] * max_scene_repeat_steps on each scene switch. This stops all workers from swapping scenes at the same time |
| seed | Provide an option random seed (for numpy and random module) to make shuffling behavior deterministic. |