multiml.agent.basic.sequential module

SequentialAgent module.

class multiml.agent.basic.sequential.SequentialAgent(differentiable=None, diff_pretrain=False, diff_task_args=None, num_trials=None, **kwargs)

Bases: BaseAgent

Agent execute sequential tasks.

Examples

>>> task0 = your_task0
>>> task1 = your_task1
>>> task2 = your_task2
>>>
>>> agent = SequentialAgent(storegate=storegate,
>>>                         task_scheduler=[task0, task1, task2],
>>>                         metric=your_metric)
>>> agent.execute()
>>> agent.finalize()

__init__(differentiable=None, diff_pretrain=False, diff_task_args=None, num_trials=None, **kwargs)

Initialize sequential agent.

Parameters:

differentiable (str) – keras or pytorch. If differentiable is given, ConnectionTask() is created based on sequential tasks. If differentiable is None (default), sequential tasks are executed step by step.
diff_pretrain (bool) – If True, each subtask is trained before creating ConnectionTask()`.
diff_task_args (dict) – arbitrary args passed to ConnectionTask().
num_trials (ine) – number of trials. Average value of trials is used as final metric.

property result: Return result of execution.

execute(): Execute sequential agent.

finalize(): Finalize sequential agent.

execute_subtasktuples(subtasktuples, counter): Execute given subtasktuples.

execute_pipeline(subtasktuples, counter, trial=None): Execute pipeline.

execute_differentiable(subtasktuples, counter, trial=None): Execute connection model.