This class is a PyTorch Model implementing the MLP based feature extractor for 1-D or 2-D state values. More...

Inheritance diagram for rlpack.models._mlp_feature_extractor._MlpFeatureExtractor:

Collaboration diagram for rlpack.models._mlp_feature_extractor._MlpFeatureExtractor:

Public Member Functions
def	__init__ (self, int sequence_length, List[int] hidden_sizes, Activation activation=pytorch.nn.ReLU(), float dropout=0.5)
	Initialize MlpFeatureExtractor model. More...

pytorch.Tensor	forward (self, pytorch.Tensor x)
	The forwards method of the nn.Module. More...

Data Fields
	activation
	The input activation function. More...

	dropout
	The input dropout probability. More...

	hidden_sizes
	The input hidden sizes for each layer. More...

	linear_module_dict
	The ModuleDict of Linear Layers. More...

	num_blocks
	The number of layers/blocks of MLP. More...

	sequence_length
	The input sequence length of expected tensor. More...

Detailed Description

This class is a PyTorch Model implementing the MLP based feature extractor for 1-D or 2-D state values.

Constructor & Destructor Documentation

◆ init()

def rlpack.models._mlp_feature_extractor._MlpFeatureExtractor.__init__	(		self,
		int	sequence_length,
		List[int]	hidden_sizes,
		Activation	activation = `pytorch.nn.ReLU()`,
		float	dropout = `0.5`
	)

Initialize MlpFeatureExtractor model.

Parameters

sequence_length	int: The sequence length of the expected tensor.
hidden_sizes	List[int]: The list of hidden sizes for each layer.
activation	Activation: The activation function class for the model. Must be an initialized activation object from PyTorch's nn (torch.nn) module.
dropout	float: The dropout to be used in the final Linear (FC) layer.

Member Function Documentation

◆ forward()

pytorch.Tensor rlpack.models._mlp_feature_extractor._MlpFeatureExtractor.forward	(		self,
		pytorch.Tensor	x
	)

The forwards method of the nn.Module.

Parameters

x	pytorch.Tensor: The model input.

Returns: pytorch.Tensor: The model output (logits).

Field Documentation

◆ activation

rlpack.models._mlp_feature_extractor._MlpFeatureExtractor.activation

The input activation function.

◆ dropout

rlpack.models._mlp_feature_extractor._MlpFeatureExtractor.dropout

The input dropout probability.

◆ hidden_sizes

rlpack.models._mlp_feature_extractor._MlpFeatureExtractor.hidden_sizes

The input hidden sizes for each layer.

◆ linear_module_dict

rlpack.models._mlp_feature_extractor._MlpFeatureExtractor.linear_module_dict

The ModuleDict of Linear Layers.

◆ num_blocks

rlpack.models._mlp_feature_extractor._MlpFeatureExtractor.num_blocks

The number of layers/blocks of MLP.

◆ sequence_length

rlpack.models._mlp_feature_extractor._MlpFeatureExtractor.sequence_length

The input sequence length of expected tensor.

Public Member Functions

Data Fields