habitat.Benchmark class

Benchmark for evaluating agents in environments.

Contents

Methods

def evaluate(self, agent: Agent, num_episodes: typing.Optional[int] = None) -> typing.Dict[str, float]

Special methods

def __init__(self, config_paths: typing.Optional[str] = None) -> None

Method documentation

def habitat.Benchmark.evaluate(self, agent: Agent, num_episodes: typing.Optional[int] = None) -> typing.Dict[str, float]

Parameters
agent agent to be evaluated in environment.
num_episodes count of number of episodes for which the evaluation should be run.
Returns dict containing metrics tracked by environment.

def habitat.Benchmark.__init__(self, config_paths: typing.Optional[str] = None) -> None

Parameters
config_paths file to be used for creating the environment