- module config
- module env
module embodied_task Implements tasks and measurements needed for training and benchmarking of
- class Action An action that can be performed by an agent solving a task in environment.
For example for navigation task action classes will be:
MoveForwardAction, TurnLeftAction, TurnRightAction. The action can use
Taskmembers to pass a state to another action, as well as keep own state and reset when new episode starts.
- class EmbodiedTask Base class for embodied tasks.
EmbodiedTaskholds definition of a task that agent needs to solve: action space, observation space, measures, simulator usage.
EmbodiedTaskhas reset() and step() methods that are called by
EmbodiedTaskis the one of main dimensions for the framework extension. Once new embodied task is introduced implementation of
EmbodiedTaskis a formal definition of the task that opens opportunity for others to propose solutions and include it into benchmark results.
- class Measure Represents a measure that provides measurement on top of environment and task.
- class Measurements Represents a set of Measures, with each Measure being identified through a unique id.
- class Metrics Dictionary containing measurements.
- class SimulatorTaskAction An
EmbodiedTaskaction that is wrapping simulator action.
- class Action An action that can be performed by an agent solving a task in environment. For example for navigation task action classes will be:
module dataset Implements dataset functionality to be used
habitat.core.datasetabstracts over a collection of
habitat.core.Episode. Each episode consists of a single instantiation of a
- class ActionSpaceConfiguration
- class AgentState
- class BumpSensor
- class DepthSensor
- class Observations Dictionary containing sensor observations
- class RGBSensor
- class SemanticSensor
- class Sensor Represents a sensor that provides data from the environment to agent.
- class SensorSuite Represents a set of sensors, with each sensor being identified through a unique id.
- class ShortestPathPoint
- class Simulator Basic simulator class for habitat. New simulators to be added to habtiat must derive from this class and implement the abstarct methods.
module registry Registry is central source of truth in Habitat.
- class Registry
- class ThreadedVectorEnv Provides same functionality as VectorEnv, the only difference is it runs in a multi-thread setup inside a single process.
- class VectorEnv Vectorized environment which creates multiple processes where each process runs its own environment. Main class for parallelization of training and evaluation.
- class _ReadWrapper Convenience wrapper to track if a connection to a worker process should have something to read.
- class _WriteWrapper Convenience wrapper to track if a connection to a worker process can be written to safely. In other words, checks to make sure the result returned from the last write was read.
- class Agent Abstract class for defining agents which act inside core.env.Env.
- class Benchmark Benchmark for evaluating agents in environments.