Documentation

• Common Base Classes
  • BaseAgent
  • Experiment
• Agent
  • SupervisedAgent
  • ICMAgent
• Environment
  • ChickAIEnvWrapper
  • ParsingEnv
  • DVSWrapper
  • ObservationWrapper
• Networks
  • CustomResnet10CNN
  • CustomResnet18CNN
  • SegmentAnything
  • FrozenViT
  • FrozenSimCLR
  • Ego4D
  • DinoV2
• Callback
  • CustomEvalCallback
  • HParamCallback
  • SupervisedSaveBestModelCallback
  • IntrinsicRewardCallback

utils.average_in_episode_three_region(log, column='agent.x', transient=90)

Train performance

Parameters:

• log (_type_) – _description_

• column (str, optional) – _description_. Defaults to ‘ChickAgent.x’.

• transient (int, optional) – _description_. Defaults to 90.

Returns:

_description_

Return type:

_type_

utils.debug_logger(name, loglevel=20)

Create a logger with the specified name and log level.

Parameters:

• name (str) – The name of the logger.

• loglevel (int, optional) – The log level for the logger. Defaults to logging.INFO.

Returns:

The created logger.

Return type:

logging.Logger

utils.moving_average(values, window)

Smooth values by doing a moving average :param values: (numpy array) :param window: (int) :return: (numpy array)

utils.omegaconf_to_dict(d: DictConfig) → Dict

Converts an omegaconf DictConfig to a python Dict, respecting variable interpolation.

utils.port_in_use(port)

Check if a given port is already in use.

Parameters:

port (int) – The port number to check.

Returns:

True if the port is in use, False otherwise.

Return type:

bool

utils.save_configuration(args, log_dir, filename='configuration.json')

Save the configuration arguments to a JSON file.

Parameters:

• args – The configuration arguments.

• log_dir – The directory where the JSON file will be saved.

• filename – The name of the JSON file (default is ‘configuration.json’).

Returns:

None