Skip to content

Sb3TrainScriptSettings

Full path: schola.scripts.sb3.train.settings.Sb3TrainScriptSettings

Top level dataclass for configuring the script arguments used in the SB3 launcher.

Sb3TrainScriptSettings(training_settings = <factory>,
                       logging_settings = <factory>,
                       resume_settings = <factory>,
                       checkpoint_settings = <factory>,
                       network_architecture_settings = <factory>,
                       algorithm_settings = <factory>,
                       environment_settings = <factory>)

Parameters

  • training_settings (Annotated)

  • logging_settings (Annotated)

  • resume_settings (Annotated)

  • checkpoint_settings (Annotated)

  • network_architecture_settings (Annotated)

  • algorithm_settings (Annotated)

  • environment_settings (Annotated)

Methods

init

__init__(training_settings = <factory>, logging_settings = <factory>,
         resume_settings = <factory>, checkpoint_settings = <factory>,
         network_architecture_settings = <factory>,
         algorithm_settings = <factory>, environment_settings = <factory>)

Parameters

  • training_settings (Annotated)

  • logging_settings (Annotated)

  • resume_settings (Annotated)

  • checkpoint_settings (Annotated)

  • network_architecture_settings (Annotated)

  • algorithm_settings (Annotated)

  • environment_settings (Annotated)

Attributes

algorithm_settings

algorithm_settings

The settings for the training algorithm to use. This can be either PPOSettings or SACSettings, depending on the chosen algorithm. This property allows for easy switching between different algorithms (e.g., PPO or SAC) by simply changing the instance of the settings class. The default is PPOSettings, which is suitable for most environments unless specified otherwise.

checkpoint_settings

checkpoint_settings

Settings for enabling checkpointing and configuring the checkpoint directory.

environment_settings

environment_settings

Settings for the environment to use during training

logging_settings

logging_settings

Settings for enabling logging and configuring the logging directory.

network_architecture_settings

network_architecture_settings

Settings for configuring the neural network architecture used for training.

resume_settings

resume_settings

Settings for resuming training from a checkpoint.

training_settings

training_settings

Timesteps, progress bar, and evaluation options for the training run.

name_prefix

name_prefix