d3rlpy.encoders.PixelEncoderFactory¶

class d3rlpy.encoders.PixelEncoderFactory(filters=None, feature_size=512, activation='relu', use_batch_norm=False)[source]¶

Pixel encoder factory class.

This is the default encoder factory for image observation.

Parameters:	filters (list) – list of tuples consisting with `(filter_size, kernel_size, stride)`. If None, `Nature DQN`-based architecture is used. feature_size (int) – the last linear layer size. activation (str) – activation function name. use_batch_norm (bool) – flag to insert batch normalization layers.

filters¶

list of tuples consisting with (filter_size, kernel_size, stride).

Type:	list

feature_size¶

the last linear layer size.

Type:	int

activation¶

activation function name.

Type:	str

use_batch_norm¶

flag to insert batch normalization layers.

Type:	bool

Methods

create(observation_shape, action_size=None, discrete_action=False)[source]¶

Returns PyTorch’s enocder module.

Parameters:	observation_shape (tuple) – 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:	torch.nn.Module

get_params(deep=False)[source]¶

Returns encoder parameters.

Parameters:	deep (bool) – flag to deeply copy the parameters.
Returns:	encoder parameters.
Return type:	dict

get_type()¶

Returns encoder type.

Returns:	encoder type.
Return type:	str

Attributes