schola.scripts.sb3.settings.SB3ScriptArgs

class schola.scripts.sb3.settings.SB3ScriptArgs(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, timesteps=3000, pbar=False, disable_eval=False, enable_tensorboard=False, log_dir=’./logs’, log_freq=10, callback_verbosity=0, schola_verbosity=0, sb3_verbosity=1, save_replay_buffer=False, save_vecnormalize=False, resume_from=None, load_vecnormalize=None, load_replay_buffer=None, reset_timestep=False, policy_parameters=None, critic_parameters=None, activation=ActivationFunctionEnum.ReLU, algorithm_settings=<factory>, plugins=<factory>)[source]

Bases: ScriptArgs

Top level dataclass for configuring the script arguments used in the SB3 launcher. This dataclass extends ScriptArgs and includes various settings for training algorithms, logging, and other configurations. It allows for easy customization of the training process by specifying parameters such as timesteps, logging options, network architectures, and algorithm-specific settings.

Methods

__init__([enable_checkpoints, …])
make_unreal_connection()	Create an Unreal Engine connection based on the script arguments.

Attributes

activation	Activation function to use in the policy and critic networks.
callback_verbosity	Verbosity level for callbacks.
checkpoint_dir	Enable saving checkpoints.
critic_parameters	A list of layer widths representing the critic (value function) network architecture.
disable_eval	Whether to disable running evaluation after training.
disable_script	Flag indicating if the autolaunch script setting in the Unreal Engine Schola Plugin should be disabled.
enable_checkpoints	Enable saving checkpoints
enable_tensorboard	Whether to enable TensorBoard logging.
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
load_replay_buffer	Path to a saved replay buffer to load when resuming training.
load_vecnormalize	Path to a saved vector normalization statistics file to load when resuming training.
log_dir	Directory to save TensorBoard logs.
log_freq	Frequency of logging training metrics to TensorBoard.
map	Map to load when launching a standalone Unreal Engine process
name_prefix
name_prefix_override	Override the name prefix for the checkpoint files (e.g. SAC, PPO, etc.).
pbar	Whether to display a progress bar during training.
policy_parameters	A list of layer widths representing the policy network architecture.
port	Port to connect to the Unreal Engine process, if None an open port will be automatically selected when running standalone.
reset_timestep	Whether to reset the internal timestep counter when resuming training from a saved model.
resume_from	Path to a saved model to resume training from.
save_final_policy	Whether to save the final policy after training is complete.
save_freq	Frequency with which to save checkpoints.
save_replay_buffer	Whether to save the replay buffer when saving a checkpoint.
save_vecnormalize	Whether to save the vector normalization statistics when saving a checkpoint.
sb3_verbosity	Verbosity level for Stable Baselines3 logging.
schola_verbosity	Verbosity level for Schola-specific logging.
timesteps	Total number of timesteps to train the agent.
algorithm_settings	The settings for the training algorithm to use.
plugins	A list of Plugins that can be used to extend the behaviour of launch.py

Parameters:

• enable_checkpoints (bool)

• checkpoint_dir (str)

• save_freq (int)

• name_prefix_override (str)

• export_onnx (bool)

• save_final_policy (bool)

• launch_unreal (bool)

• port (int | None)

• executable_path (str | None)

• headless (bool)

• map (str | None)

• fps (int | None)

• disable_script (bool)

• timesteps (int)

• pbar (bool)

• disable_eval (bool)

• enable_tensorboard (bool)

• log_dir (str)

• log_freq (int)

• callback_verbosity (int)

• schola_verbosity (int)

• sb3_verbosity (int)

• save_replay_buffer (bool)

• save_vecnormalize (bool)

• resume_from (str)

• load_vecnormalize (str)

• load_replay_buffer (str)

• reset_timestep (bool)

• policy_parameters (List[int])

• critic_parameters (List[int])

• activation (ActivationFunctionEnum)

• algorithm_settings (PPOSettings | SACSettings)

• plugins (List[Sb3LauncherExtension])

__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, timesteps=3000, pbar=False, disable_eval=False, enable_tensorboard=False, log_dir=’./logs’, log_freq=10, callback_verbosity=0, schola_verbosity=0, sb3_verbosity=1, save_replay_buffer=False, save_vecnormalize=False, resume_from=None, load_vecnormalize=None, load_replay_buffer=None, reset_timestep=False, policy_parameters=None, critic_parameters=None, activation=ActivationFunctionEnum.ReLU, algorithm_settings=<factory>, plugins=<factory>)

Parameters:

• enable_checkpoints (bool)

• checkpoint_dir (str)

• save_freq (int)

• name_prefix_override (str | None)

• export_onnx (bool)

• save_final_policy (bool)

• launch_unreal (bool)

• port (int | None)

• executable_path (str | None)

• headless (bool)

• map (str | None)

• fps (int | None)

• disable_script (bool)

• timesteps (int)

• pbar (bool)

• disable_eval (bool)

• enable_tensorboard (bool)

• log_dir (str)

• log_freq (int)

• callback_verbosity (int)

• schola_verbosity (int)

• sb3_verbosity (int)

• save_replay_buffer (bool)

• save_vecnormalize (bool)

• resume_from (str | None)

• load_vecnormalize (str | None)

• load_replay_buffer (str | None)

• reset_timestep (bool)

• policy_parameters (List[int] | None)

• critic_parameters (List[int] | None)

• activation (ActivationFunctionEnum)

• algorithm_settings (PPOSettings | SACSettings)

• plugins (List[Sb3LauncherExtension])

Return type:

None

activation: ActivationFunctionEnum = ‘relu’

Activation function to use in the policy and critic networks. This determines the non-linear activation function applied to each layer of the neural networks. Common options include ReLU, Tanh, and Sigmoid. The choice of activation function can affect the performance of the model and may depend on the specific characteristics of the environment. Default is ReLU, but you can choose others based on your needs.

algorithm_settings: PPOSettings | SACSettings

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.

callback_verbosity: int = 0

Verbosity level for callbacks. This controls the level of detail in the output from any callbacks used during training.

critic_parameters: List[int] = None

A list of layer widths representing the critic (value function) network architecture. This defines the number of neurons in each hidden layer of the critic network. For example, [64, 64] would create a critic network with two hidden layers, each containing 64 neurons. This is only applicable for algorithms that use a critic (e.g., SAC). If set to None, it will use the default architecture defined by the algorithm.

disable_eval: bool = False

Whether to disable running evaluation after training. When set to True, it will skip evaluation after training completes.

enable_tensorboard: bool = False

Whether to enable TensorBoard logging.

load_replay_buffer: str = None

Path to a saved replay buffer to load when resuming training. This allows for loading a previously saved replay buffer, which can be useful for continuing training with the same set of experiences. The path should point to a valid replay buffer file created by Stable Baselines3. If set to None, it will not load any replay buffer, and a new one will be created instead.

load_vecnormalize: str = None

Path to a saved vector normalization statistics file to load when resuming training. This allows for loading the normalization statistics from a previous training session, ensuring that the observations are normalized consistently when resuming training. If set to None, it will not load any vector normalization statistics.

log_dir: str = ‘./logs’

Directory to save TensorBoard logs.

log_freq: int = 10

Frequency of logging training metrics to TensorBoard. This determines how often (in terms of training steps) the training metrics will be logged to TensorBoard. A value of 10 means that every 10 training steps, the metrics will be recorded.

property name_prefix

pbar: bool = False

Whether to display a progress bar during training. Requires TQDM and Rich to be installed.

plugins: List[Sb3LauncherExtension]

A list of Plugins that can be used to extend the behaviour of launch.py

policy_parameters: List[int] = None

A list of layer widths representing the policy network architecture. This defines the number of neurons in each hidden layer of the policy network. For example, [64, 64] would create a policy network with two hidden layers, each containing 64 neurons. If set to None, it will use the default architecture defined by the algorithm.

reset_timestep: bool = False

Whether to reset the internal timestep counter when resuming training from a saved model. When set to True, it will reset the timestep counter to 0.

resume_from: str = None

Path to a saved model to resume training from. This allows for continuing training from a previously saved checkpoint. The path should point to a valid model file created by Stable Baselines3. If set to None, training will start from scratch.

save_replay_buffer: bool = False

Whether to save the replay buffer when saving a checkpoint. This allows for resuming training from the same state of the replay buffer.

save_vecnormalize: bool = False

Whether to save the vector normalization statistics when saving a checkpoint. This is useful for environments where observations need to be normalized, and it allows for consistent normalization when resuming training.

sb3_verbosity: int = 1

Verbosity level for Stable Baselines3 logging. This controls the level of detail in the output from Stable Baselines3 components during training.

schola_verbosity: int = 0

Verbosity level for Schola-specific logging. This controls the level of detail in the output from Schola-related components during training.

timesteps: int = 3000

Total number of timesteps to train the agent. This is the total number of environment steps that will be used for training. This should be set based on the complexity of the environment and the desired training duration. A higher value will typically lead to better performance but will also increase training time.