reagent.model_managers.parametric package
Submodules
reagent.model_managers.parametric.parametric_dqn module
- class reagent.model_managers.parametric.parametric_dqn.ParametricDQN(state_preprocessing_options: Optional[reagent.workflow.types.PreprocessingOptions] = None, action_preprocessing_options: Optional[reagent.workflow.types.PreprocessingOptions] = None, state_float_features: Optional[List[Tuple[int, str]]] = None, action_float_features: Optional[List[Tuple[int, str]]] = None, reader_options: Optional[reagent.workflow.types.ReaderOptions] = None, eval_parameters: reagent.core.parameters.EvaluationParameters = <factory>, trainer_param: reagent.training.parameters.ParametricDQNTrainerParameters = <factory>, net_builder: reagent.net_builder.unions.ParametricDQNNetBuilder__Union = <factory>)
Bases:
reagent.model_managers.parametric_dqn_base.ParametricDQNBase- build_serving_module(trainer_module: reagent.training.reagent_lightning_module.ReAgentLightningModule, normalization_data_map: Dict[str, reagent.core.parameters.NormalizationData]) torch.nn.modules.module.Module
Optionaly, implement this method if you only have one model for serving
- build_trainer(normalization_data_map: Dict[str, reagent.core.parameters.NormalizationData], use_gpu: bool, reward_options: Optional[reagent.workflow.types.RewardOptions] = None) reagent.training.parametric_dqn_trainer.ParametricDQNTrainer
Implement this to build the trainer, given the config
TODO: This function should return ReAgentLightningModule & the dictionary of modules created
- property rl_parameters
- trainer_param: reagent.training.parameters.ParametricDQNTrainerParameters
Module contents
- class reagent.model_managers.parametric.ParametricDQN(state_preprocessing_options: Optional[reagent.workflow.types.PreprocessingOptions] = None, action_preprocessing_options: Optional[reagent.workflow.types.PreprocessingOptions] = None, state_float_features: Optional[List[Tuple[int, str]]] = None, action_float_features: Optional[List[Tuple[int, str]]] = None, reader_options: Optional[reagent.workflow.types.ReaderOptions] = None, eval_parameters: reagent.core.parameters.EvaluationParameters = <factory>, trainer_param: reagent.training.parameters.ParametricDQNTrainerParameters = <factory>, net_builder: reagent.net_builder.unions.ParametricDQNNetBuilder__Union = <factory>)
Bases:
reagent.model_managers.parametric_dqn_base.ParametricDQNBase- build_serving_module(trainer_module: reagent.training.reagent_lightning_module.ReAgentLightningModule, normalization_data_map: Dict[str, reagent.core.parameters.NormalizationData]) torch.nn.modules.module.Module
Optionaly, implement this method if you only have one model for serving
- build_trainer(normalization_data_map: Dict[str, reagent.core.parameters.NormalizationData], use_gpu: bool, reward_options: Optional[reagent.workflow.types.RewardOptions] = None) reagent.training.parametric_dqn_trainer.ParametricDQNTrainer
Implement this to build the trainer, given the config
TODO: This function should return ReAgentLightningModule & the dictionary of modules created
- eval_parameters: EvaluationParameters
- property rl_parameters
- trainer_param: reagent.training.parameters.ParametricDQNTrainerParameters