pistarlab.tasks package

Submodules

pistarlab.tasks.matask module

class pistarlab.tasks.matask.MultiAgentRunner(**kwargs)

Bases: pistarlab.task_runner.TaskRunner

config = {'agents': {}, 'env_kwargs': {}, 'env_spec_id': None, 'player_assignments': {}, 'session_config': {}}
displayed_name = ''
plugin_id = 'builtin'
run()
spec_id = 'multiagent'
task: pistarlab.task.Task
version = '0.0.1-dev'
pistarlab.tasks.matask.get_agent_space_map(player_to_agent_map, player_space_map)

pistarlab.tasks.tune_default module

class pistarlab.tasks.tune_default.TuneDefaultRunner(**kwargs)

Bases: pistarlab.task_runner.TaskRunner

run()
task: pistarlab.task.Task
class pistarlab.tasks.tune_default.TuneTrainable(config=None, logger_creator=None)

Bases: ray.tune.trainable.Trainable

cleanup()

Subclasses should override this for any cleanup on stop.

If any Ray actors are launched in the Trainable (i.e., with a RLlib trainer), be sure to kill the Ray actor process here.

You can kill a Ray actor by calling actor.__ray_terminate__.remote() on the actor.

New in version 0.8.7.

setup(config)

Subclasses should override this for custom initialization.

New in version 0.8.7.

Parameters

config (dict) – Hyperparameters and other configs given. Copy of self.config.

step()

Subclasses should override this to implement train().

The return value will be automatically passed to the loggers. Users can also return tune.result.DONE or tune.result.SHOULD_CHECKPOINT as a key to manually trigger termination or checkpointing of this trial. Note that manual checkpointing only works when subclassing Trainables.

New in version 0.8.7.

Returns

A dict that describes training progress.

Module contents