EmbodiedTask class
Base class for embodied task. EmbodiedTask holds definition of
a task that agent needs to solve: action space, observation space,
measures, simulator usage. EmbodiedTask has reset() and
step() methods that are called by Env. EmbodiedTask is the
one of main dimensions for the framework extension. Once new embodied task
is introduced implementation of EmbodiedTask is a formal definition of
the task that opens opportunity for others to propose solutions and
include it into benchmark results.
- Args:
- config: config for the task. sim: reference to the simulator for calculating task observations. dataset: reference to dataset for task instance level information.
- data measurements:
- set of task measures.
- data sensor_suite:
- suite of task sensors.
Methods
- def add_perf_timing(self, *args, **kwargs)
- def get_action_name(self, action_index: typing.Union[int, numpy.integer])
- def overwrite_sim_config(self, sim_config: DictConfig, episode: dataset.Episode) -> DictConfig
- Update config merging information from
sim_configandepisode. - def reset(self, episode: dataset.Episode)
- def seed(self, seed: int) -> None
- def step(self, action: typing.Dict[str, typing.Any], episode: dataset.Episode)
Special methods
- def __init__(self, config: DictConfig, sim: simulator.Simulator, dataset: typing.Optional[dataset.Dataset] = None)
Properties
- action_space: gym.spaces.space.Space get
- is_episode_active get
Data
- measurements: Measurements = None
- sensor_suite: simulator.SensorSuite = None
Method documentation
def habitat.
Update config merging information from sim_config and
episode.
| Parameters | |
|---|---|
| sim_config | config for simulator. |
| episode | current episode. |