RLlibScriptArgs

Full path: schola.scripts.rllib.settings.RLlibScriptArgs

schola.scripts.rllib.settings.RLlibScriptArgs

RLlibScriptArgs

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

Bases: object

Top level dataclass for RLlib script arguments. This class aggregates all the settings required for configuring the RLlib training process. It includes settings for training, algorithms, logging, resuming from checkpoints, network architecture, and resource allocation. This allows for a comprehensive configuration of the RLlib training job in a structured manner.

Methods

Item	Description
init	—

Attributes

Item	Description
training_settings	Settings for configuring the training process.
algorithm_settings	Settings for configuring the training algorithm to use.
logging_settings	Settings for enabling logging and configuring the logging directory.
resume_settings	Settings for resuming training from a checkpoint.
network_architecture_settings	Settings for configuring the neural network architecture used for training.
resource_settings	Settings for configuring the resource allocation for the training process.
checkpoint_settings	Settings for checkpoints
environment_settings	Settings for the environment to use during training

Parameters

training_settings (Annotated[TrainingSettings, Parameter(group=('Training Arguments',))])

algorithm_settings (Annotated[PPOSettings | SACSettings | APPOSettings | IMPALASettings, Parameter(parse=False, show=False)])

logging_settings (Annotated[LoggingSettings, Parameter(group=('Logging Arguments',))])

resume_settings (Annotated[ResumeSettings, Parameter(group=('Resume Arguments',))])

network_architecture_settings (Annotated[NetworkArchitectureSettings, Parameter(group=('Network Architecture Arguments',))])

resource_settings (Annotated[ResourceSettings, Parameter(group=('Resource Arguments',))])

checkpoint_settings (Annotated[CheckpointArgs, Parameter(group=('Checkpoint Arguments',))])

environment_settings (Annotated[EnvironmentArgs, Parameter(name=('*',), group=('Environment Arguments',))])

init

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

Parameters

training_settings (Annotated[TrainingSettings, Parameter(group=('Training Arguments',))])

algorithm_settings (Annotated[PPOSettings | SACSettings | APPOSettings | IMPALASettings, Parameter(parse=False, show=False)])

logging_settings (Annotated[LoggingSettings, Parameter(group=('Logging Arguments',))])

resume_settings (Annotated[ResumeSettings, Parameter(group=('Resume Arguments',))])

network_architecture_settings (Annotated[NetworkArchitectureSettings, Parameter(group=('Network Architecture Arguments',))])

resource_settings (Annotated[ResourceSettings, Parameter(group=('Resource Arguments',))])

checkpoint_settings (Annotated[CheckpointArgs, Parameter(group=('Checkpoint Arguments',))])

environment_settings (Annotated[EnvironmentArgs, Parameter(name=('*',), group=('Environment Arguments',))])

Returns

None

---

algorithm_settings

algorithm_settings: Annotated[
    PPOSettings | SACSettings | APPOSettings | IMPALASettings,
    Parameter(parse=False, show=False),
]

Settings for configuring the training algorithm to use.

---

checkpoint_settings

checkpoint_settings: Annotated[CheckpointArgs, Parameter(group="Checkpoint Arguments")]

Settings for checkpoints

---

environment_settings

environment_settings: Annotated[
    EnvironmentArgs, Parameter(name="*", group="Environment Arguments")
]

Settings for the environment to use during training

---

logging_settings

logging_settings: Annotated[LoggingSettings, Parameter(group="Logging Arguments")]

Settings for enabling logging and configuring the logging directory.

---

network_architecture_settings

network_architecture_settings: Annotated[
    NetworkArchitectureSettings, Parameter(group="Network Architecture Arguments")
]

Settings for configuring the neural network architecture used for training.

---

resource_settings

resource_settings: Annotated[ResourceSettings, Parameter(group="Resource Arguments")]

Settings for configuring the resource allocation for the training process.

---

resume_settings

resume_settings: Annotated[ResumeSettings, Parameter(group="Resume Arguments")]

Settings for resuming training from a checkpoint.

---

training_settings

training_settings: Annotated[TrainingSettings, Parameter(group="Training Arguments")]

Settings for configuring the training process.

---