class
EmbodiedTaskBase class for embodied tasks. 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.
Contents
- Reference
- 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 get_action_name(self, action_index: int)
- def overwrite_sim_config(self, sim_config: habitat.config.default.Config, episode: typing.Type[dataset.Episode]) -> habitat.config.default.Config
- Update config merging information from
sim_config
andepisode
. - def reset(self, episode: typing.Type[dataset.Episode])
- def seed(self, seed: int) -> None
- def step(self, action: typing.Union[int, typing.Dict[str, typing.Any]], episode: typing.Type[dataset.Episode])
Special methods
- def __init__(self, config: habitat.config.default.Config, sim: simulator.Simulator, dataset: typing.Optional[dataset.Dataset] = None) -> None
Properties
- action_space: gym.core.Space get
- is_episode_active get
Data
- measurements: Measurements = None
- sensor_suite: simulator.SensorSuite = None
Method documentation
def habitat. core. embodied_task. EmbodiedTask. overwrite_sim_config(self,
sim_config: habitat.config.default.Config,
episode: typing.Type[dataset.Episode]) -> habitat.config.default.Config
Update config merging information from sim_config
and
episode
.
Parameters | |
---|---|
sim_config | config for simulator. |
episode | current episode. |