trinity.explorer.workflow_runner module

The Workflow Runner Module.

class trinity.explorer.workflow_runner.Status(ok: bool, metric: dict[str, float], message: str | None = None)[source]

Bases: object

Status of the task running result.

ok: bool

metric: dict[str, float]

message: str | None = None

__init__(ok: bool, metric: dict[str, float], message: str | None = None) → None

class trinity.explorer.workflow_runner.WorkflowRunner(config: Config, model: InferenceModel, auxiliary_models: List[InferenceModel] | None = None, runner_id: int | None = None)[source]

Bases: object

A Ray remote actor to run the workflow and generate experiences.

__init__(config: Config, model: InferenceModel, auxiliary_models: List[InferenceModel] | None = None, runner_id: int | None = None) → None[source]

is_alive()[source]

run_task(task: Task, repeat_times: int = 1, run_id_base: int = 0) → Tuple[Status, List[Experience]][source]: Run the task and return the states.