schola.scripts.ray.settings.RLlibScriptArgs
Class Definition
class schola.scripts.ray.settings.RLlibScriptArgs(enable_checkpoints=False, checkpoint_dir='./ckpt', save_freq=100000, name_prefix_override=None, export_onnx=False, save_final_policy=False, launch_unreal=False, port=None, executable_path=None, headless=False, map=None, fps=None, disable_script=False, training_settings=, algorithm_settings=, logging_settings=, resume_settings=, network_architecture_settings=, resource_settings=, plugins=)Bases: ScriptArgs
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.
Parameters
enable_checkpoints
Type: bool
checkpoint_dir
Type: str
save_freq
Type: int
name_prefix_override
Type: str | None
export_onnx
Type: bool
save_final_policy
Type: bool
launch_unreal
Type: bool
port
Type: int | None
executable_path
Type: str | None
headless
Type: bool
map
Type: str | None
fps
Type: int | None
disable_script
Type: bool
training_settings
Type: TrainingSettings
algorithm_settings
Type: PPOSettings | APPOSettings | IMPALASettings
logging_settings
Type: LoggingSettings
resume_settings
Type: ResumeSettings
network_architecture_settings
Type: NetworkArchitectureSettings
resource_settings
Type: ResourceSettings
plugins
Type: List[RLLibLauncherExtension]
Attributes
algorithm_settings
Type: PPOSettings | APPOSettings | IMPALASettings
checkpoint_dir
Enable saving checkpoints.
disable_script
Flag indicating if the autolaunch script setting in the Unreal Engine Schola Plugin should be disabled.
enable_checkpoints
Enable saving checkpoints
executable_path
Path to the standalone executable, when launching a standalone Environment
export_onnx
Whether to export the model to ONNX format instead of just saving a checkpoint.
fps
Fixed FPS to use when running standalone, if None no fixed timestep is used
headless
Flag indicating if the standalone Unreal Engine process should run in headless mode
launch_unreal
Flag indicating if the script should launch a standalone Unreal Engine process
logging_settings
Type: LoggingSettings
map
Map to load when launching a standalone Unreal Engine process
name_prefix_override
Override the name prefix for the checkpoint files (e.g. SAC, PPO, etc.).
network_architecture_settings
Type: NetworkArchitectureSettings
plugins
Type: List[RLLibLauncherExtension]
port
Port to connect to the Unreal Engine process, if None an open port will be automatically selected when running standalone.
resource_settings
Type: ResourceSettings
resume_settings
Type: ResumeSettings
save_final_policy
Whether to save the final policy after training is complete.
save_freq
Frequency with which to save checkpoints.
training_settings
Type: TrainingSettings
Methods
__init__
__init__(enable_checkpoints=False, checkpoint_dir='./ckpt', save_freq=100000, name_prefix_override=None, export_onnx=False, save_final_policy=False, launch_unreal=False, port=None, executable_path=None, headless=False, map=None, fps=None, disable_script=False, training_settings=, algorithm_settings=, logging_settings=, resume_settings=, network_architecture_settings=, resource_settings=, plugins=)Return type: None
make_unreal_connection
make_unreal_connection()Create an Unreal Engine connection based on the script arguments.