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.
-