gfn.envs.preprocessors

Submodules

• gfn.envs.preprocessors.base
• gfn.envs.preprocessors.hot

Package Contents

Classes

EnumPreprocessor	Preprocessor applicable to environments with discrete states.
IdentityPreprocessor	Simple preprocessor applicable to environments with uni-dimensional states.
KHotPreprocessor	Base class for Preprocessors. The goal is to transform tensors representing raw states
OneHotPreprocessor	Base class for Preprocessors. The goal is to transform tensors representing raw states
Preprocessor	Base class for Preprocessors. The goal is to transform tensors representing raw states

class gfn.envs.preprocessors.EnumPreprocessor(get_states_indices)

Bases: Preprocessor

Preprocessor applicable to environments with discrete states.

Parameters

get_states_indices (Callable[[gfn.containers.States], OutputTensor]) –

name = EnumPreprocessor

preprocess(states)

class gfn.envs.preprocessors.IdentityPreprocessor(output_shape)

Bases: Preprocessor

Simple preprocessor applicable to environments with uni-dimensional states. This is the default preprocessor used.

Parameters

output_shape (Tuple[int]) –

name = IdentityPreprocessor

preprocess(states)

Parameters

states (gfn.containers.States) –

Return type

OutputTensor

class gfn.envs.preprocessors.KHotPreprocessor(height, ndim, get_states_indices)

Bases: gfn.envs.preprocessors.base.Preprocessor

Base class for Preprocessors. The goal is to transform tensors representing raw states to tensors that can be used as input to neural networks.

Parameters

• height (int) –

• ndim (int) –

• get_states_indices (Callable[[gfn.containers.states.States], OutputTensor]) –

name = k_hot

preprocess(states)

class gfn.envs.preprocessors.OneHotPreprocessor(n_states, get_states_indices)

Bases: gfn.envs.preprocessors.base.Preprocessor

Base class for Preprocessors. The goal is to transform tensors representing raw states to tensors that can be used as input to neural networks.

Parameters

• n_states (int) –

• get_states_indices (Callable[[gfn.containers.states.States], OutputTensor]) –

name = one_hot

preprocess(states)

class gfn.envs.preprocessors.Preprocessor(output_shape)

Bases: abc.ABC

Base class for Preprocessors. The goal is to transform tensors representing raw states to tensors that can be used as input to neural networks.

Parameters

output_shape (Tuple[int]) –

name :str = Preprocessor

__call__(states)

Parameters

states (gfn.containers.States) –

Return type

OutputTensor

__repr__()

Return repr(self).

abstract preprocess(states)

Parameters

states (gfn.containers.States) –

Return type

OutputTensor