nip.factory._build_components_for_rl_trainer

nip.factory._build_components_for_rl_trainer#

nip.factory._build_components_for_rl_trainer(hyper_params: HyperParameters, settings: ExperimentSettings, protocol_handler: ProtocolHandler, train_dataset: Dataset, test_dataset: Dataset, agents: dict[str, Agent], get_scenario_class: Callable[[type], type]) → dict[str, Environment | CombinedBody | CombinedPolicyHead | CombinedValueHead][source]#

Build the additional components needed for an RL trainer.

Parameters:

  • hyper_params (HyperParameters) – The parameters for the experiment.

  • settings (ExperimentSettings) – The settings for the experiment.

  • protocol_handler (ProtocolHandler) – The protocol handler for the experiment.

  • train_dataset (Dataset) – The train dataset for the experiment.

  • test_dataset (Dataset) – The test dataset for the experiment.

  • agents (dict[str, Agent]) – The agents for the experiment.

  • get_scenario_class (Callable[[type], type]) – A function to get the class for a component based on the scenario and base class.

Returns:

additional_rl_components (dict[str, Any]) – The additional components needed for an RL trainer.