Sb3ResumeArgs

Full path: schola.scripts.sb3.settings.Sb3ResumeArgs

schola.scripts.sb3.settings.Sb3ResumeArgs

Sb3ResumeArgs

Sb3ResumeArgs(
    resume_from=None,
    load_vecnormalize=None,
    load_replay_buffer=None,
    reset_timestep=False,
)

Bases: object

Dataclass for holding arguments related to resuming training from a saved state.

Methods

Item	Description
init	—

Attributes

Item	Description
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.
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.

Parameters

resume_from (Annotated[Path | None, Parameter(validator=(Path(exists=True, file_okay=True, dir_okay=False, ext=()),))])

load_vecnormalize (Annotated[Path | None, Parameter(validator=(Path(exists=True, file_okay=True, dir_okay=False, ext=()),))])

load_replay_buffer (Annotated[Path | None, Parameter(validator=(Path(exists=True, file_okay=True, dir_okay=False, ext=()),))])

reset_timestep (bool)

init

__init__(
    resume_from=None,
    load_vecnormalize=None,
    load_replay_buffer=None,
    reset_timestep=False,
)

Parameters

resume_from (Annotated[Path | None, Parameter(validator=(Path(exists=True, file_okay=True, dir_okay=False, ext=()),))])

load_vecnormalize (Annotated[Path | None, Parameter(validator=(Path(exists=True, file_okay=True, dir_okay=False, ext=()),))])

load_replay_buffer (Annotated[Path | None, Parameter(validator=(Path(exists=True, file_okay=True, dir_okay=False, ext=()),))])

reset_timestep (bool)

Returns

None

---

load_replay_buffer

= None load_replay_buffer: Annotated[Path | None, Parameter(validator=Path(exists=True, file_okay=True, dir_okay=False, ext=()))]

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

= None load_vecnormalize: Annotated[Path | None, Parameter(validator=Path(exists=True, file_okay=True, dir_okay=False, ext=()))]

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.

---

reset_timestep

= False reset_timestep: bool

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

= None resume_from: Annotated[Path | None, Parameter(validator=Path(exists=True, file_okay=True, dir_okay=False, ext=()))]

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.

---