d3rlpy.models.encoders.VectorEncoderFactory

class d3rlpy.models.encoders.VectorEncoderFactory(hidden_units=None, activation='relu', use_batch_norm=False, dropout_rate=None, use_dense=False)

Vector encoder factory class.

This is the default encoder factory for vector observation.

Parameters

• hidden_units (list) – list of hidden unit sizes. If None, the standard architecture with [256, 256] is used.

• activation (str) – activation function name.

• use_batch_norm (bool) – flag to insert batch normalization layers.

• use_dense (bool) – flag to use DenseNet architecture.

• dropout_rate (float) – dropout probability.

Methods

create(observation_shape)

Returns PyTorch’s state enocder module.

Parameters

observation_shape (Sequence[int]) – observation shape.

Returns

an enocder object.

Return type

d3rlpy.models.torch.encoders.VectorEncoder

create_with_action(observation_shape, action_size, discrete_action=False)

Returns PyTorch’s state-action enocder module.

Parameters

• observation_shape (Sequence[int]) – observation shape.

• action_size (int) – action size. If None, the encoder does not take action as input.

• discrete_action (bool) – flag if action-space is discrete.

Returns

an enocder object.

Return type

d3rlpy.models.torch.encoders.VectorEncoderWithAction

get_params(deep=False)

Returns encoder parameters.

Parameters

deep (bool) – flag to deeply copy the parameters.

Returns

encoder parameters.

Return type

Dict[str, Any]

get_type()

Returns encoder type.

Returns

encoder type.

Return type

str

Attributes

TYPE: ClassVar[str] = 'vector'