ml.rl.training.ranking package

Submodules

ml.rl.training.ranking.ranking_trainer module

class ml.rl.training.ranking.ranking_trainer.RankingTrainer

Bases: object

load_state_dict(state_dict)
state_dict()
train(training_batch: ml.rl.types.PreprocessedTrainingBatch) → None
warm_start_components() → List[str]

The trainer should specify what members to save and load

ml.rl.training.ranking.seq2slate_trainer module

class ml.rl.training.ranking.seq2slate_trainer.Seq2SlateTrainer(seq2slate_net: ml.rl.models.seq2slate.Seq2SlateTransformerNet, baseline_net: ml.rl.models.seq2slate.BaselineNet, parameters: ml.rl.parameters.Seq2SlateTransformerParameters, eval_parameters: ml.rl.parameters.EvaluationParameters, minibatch_size: int, use_gpu: bool = False)

Bases: ml.rl.training.ranking.ranking_trainer.RankingTrainer

train(training_batch: ml.rl.types.PreprocessedTrainingBatch)
warm_start_components()

The trainer should specify what members to save and load

Module contents