reagent/training/ranking/seq2slate_sim_trainer.py [67:85]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(
        self,
        seq2slate_net: Seq2SlateTransformerNet,
        params: Seq2SlateParameters = field(  # noqa: B008
            default_factory=Seq2SlateParameters
        ),
        baseline_net: Optional[BaselineNet] = None,
        baseline_warmup_num_batches: int = 0,
        policy_optimizer: Optimizer__Union = field(  # noqa: B008
            default_factory=Optimizer__Union.default
        ),
        baseline_optimizer: Optimizer__Union = field(  # noqa: B008
            default_factory=Optimizer__Union.default
        ),
        policy_gradient_interval: int = 1,
        print_interval: int = 100,
        calc_cpe: bool = False,
        reward_network: Optional[nn.Module] = None,
    ) -> None:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



reagent/training/ranking/seq2slate_trainer.py [24:42]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(
        self,
        seq2slate_net: Seq2SlateTransformerNet,
        params: Seq2SlateParameters = field(  # noqa: B008
            default_factory=Seq2SlateParameters
        ),
        baseline_net: Optional[BaselineNet] = None,
        baseline_warmup_num_batches: int = 0,
        policy_optimizer: Optimizer__Union = field(  # noqa: B008
            default_factory=Optimizer__Union.default
        ),
        baseline_optimizer: Optimizer__Union = field(  # noqa: B008
            default_factory=Optimizer__Union.default
        ),
        policy_gradient_interval: int = 1,
        print_interval: int = 100,
        calc_cpe: bool = False,
        reward_network: Optional[nn.Module] = None,
    ) -> None:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -