eta_utility.eta_x.common.policies module

class eta_utility.eta_x.common.policies.NoPolicy(*args, squash_output: bool = False, **kwargs)

Bases: BasePolicy

No Policy allows for the creation of agents which do not use neural networks. It does not implement any of the typical policy functions but is a simple interface that can be used and ignored. There is no need to worry about the implementation details of policies.

forward(*args: Any, **kwargs: Any) → None

No Policy allows for the creation of agents which do not use neural networks. It does not implement any of the typical policy functions but is a simple interface that can be used and ignored. There is no need to worry about the implementation details of policies.

state_dict(*, destination: dict[str, Any] | None = None, prefix: str = '', keep_vars: bool = False) → dict[str, Any]

Returns a dictionary containing a whole state of the module. The dictionary is empty in NoPolicy.

Parameters:

• destination – If provided, the state will be updated into the dictionary and the same object returned.

• prefix – Prefix added to parameter and buffer names when composing keys in state_dict.

• keep_vars – Determine, which variables will be detached from torch.autograd.

Returns:

Dictionary with the module/policy state.

load_state_dict(state_dict: dict[str, Any] | None = None, strict=True) → None

Loads the state dictionary. Since the dictionary is always empty, this method doesn’t do anything in NoPolicy.

state_dict (dict): a dict containing parameters and

persistent buffers.

strict (bool, optional): whether to strictly enforce that the keys

in state_dict match the keys returned by this module’s state_dict() function. Default: True