garage.tf.models.cnn_mlp_merge_model

CNN and MLP Merge Model.

class CNNMLPMergeModel(filters, strides, hidden_sizes=(256, ), output_dim=1, action_merge_layer=-2, name=None, padding='SAME', max_pooling=False, pool_strides=(2, 2), pool_shapes=(2, 2), cnn_hidden_nonlinearity=tf.nn.relu, cnn_hidden_w_init=tf.initializers.glorot_uniform(seed=deterministic.get_tf_seed_stream()), cnn_hidden_b_init=tf.zeros_initializer(), hidden_nonlinearity=tf.nn.relu, hidden_w_init=tf.initializers.glorot_uniform(seed=deterministic.get_tf_seed_stream()), hidden_b_init=tf.zeros_initializer(), output_nonlinearity=None, output_w_init=tf.initializers.glorot_uniform(seed=deterministic.get_tf_seed_stream()), output_b_init=tf.zeros_initializer(), layer_normalization=False)

Bases: garage.tf.models.model.Model

Inheritance diagram of garage.tf.models.cnn_mlp_merge_model.CNNMLPMergeModel

Convolutional neural network followed by a Multilayer Perceptron.

Combination of a CNN Model (optionally with max pooling) and an MLP Merge model. The CNN accepts the state as an input, while the MLP accepts the CNN’s output and the action as inputs.

Parameters:
  • filters (Tuple[Tuple[int, Tuple[int, int]], ..]) – Number and dimension of filters. For example, ((3, (3, 5)), (32, (3, 3))) means there are two convolutional layers. The filter for the first layer have 3 channels and its shape is (3 x 5), while the filter for the second layer have 32 channels and its shape is (3 x 3).
  • strides (tuple[int]) – The stride of the sliding window. For example, (1, 2) means there are two convolutional layers. The stride of the filter for first layer is 1 and that of the second layer is 2.
  • hidden_sizes (tuple[int]) – Output dimension of dense layer(s). For example, (32, 32) means the MLP of this q-function consists of two hidden layers, each with 32 hidden units.
  • output_dim (int) – Dimension of the network output.
  • action_merge_layer (int) – The index of layers at which to concatenate action inputs with the network. The indexing works like standard python list indexing. Index of 0 refers to the input layer (observation input) while an index of -1 points to the last hidden layer. Default parameter points to second layer from the end.
  • name (str) – Model name, also the variable scope.
  • padding (str) – The type of padding algorithm to use, either ‘SAME’ or ‘VALID’.
  • max_pooling (bool) – Boolean for using max pooling layer or not.
  • pool_shapes (tuple[int]) – Dimension of the pooling layer(s). For example, (2, 2) means that all the pooling layers have shape (2, 2).
  • pool_strides (tuple[int]) – The strides of the pooling layer(s). For example, (2, 2) means that all the pooling layers have strides (2, 2).
  • cnn_hidden_nonlinearity (callable) – Activation function for intermediate dense layer(s) in the CNN. It should return a tf.Tensor. Set it to None to maintain a linear activation.
  • cnn_hidden_w_init (callable) – Initializer function for the weight of intermediate dense layer(s) in the CNN. Function should return a tf.Tensor.
  • cnn_hidden_b_init (callable) – Initializer function for the bias of intermediate dense layer(s) in the CNN. Function should return a tf.Tensor.
  • hidden_nonlinearity (callable) – Activation function for intermediate dense layer(s) in the MLP. It should return a tf.Tensor. Set it to None to maintain a linear activation.
  • hidden_w_init (callable) – Initializer function for the weight of intermediate dense layer(s) in the MLP. The function should return a tf.Tensor.
  • hidden_b_init (callable) – Initializer function for the bias of intermediate dense layer(s) in the MLP. The function should return a tf.Tensor.
  • output_nonlinearity (callable) – Activation function for output dense layer in the MLP. It should return a tf.Tensor. Set it to None to maintain a linear activation.
  • output_w_init (callable) – Initializer function for the weight of output dense layer(s) in the MLP. The function should return a tf.Tensor.
  • output_b_init (callable) – Initializer function for the bias of output dense layer(s) in the MLP. The function should return a tf.Tensor.
  • layer_normalization (bool) – Bool for using layer normalization or not.
parameters

Parameters of the model.

Returns:Parameters
Return type:np.ndarray
name

Name (str) of the model.

This is also the variable scope of the model.

Returns:Name of the model.
Return type:str
input

Default input of the model.

When the model is built the first time, by default it creates the ‘default’ network. This property creates a reference to the input of the network.

Returns:Default input of the model.
Return type:tf.Tensor
output

Default output of the model.

When the model is built the first time, by default it creates the ‘default’ network. This property creates a reference to the output of the network.

Returns:Default output of the model.
Return type:tf.Tensor
inputs

Default inputs of the model.

When the model is built the first time, by default it creates the ‘default’ network. This property creates a reference to the inputs of the network.

Returns:Default inputs of the model.
Return type:list[tf.Tensor]
outputs

Default outputs of the model.

When the model is built the first time, by default it creates the ‘default’ network. This property creates a reference to the outputs of the network.

Returns:Default outputs of the model.
Return type:list[tf.Tensor]
state_info_specs

State info specification.

Returns:
keys and shapes for the information related to the
module’s state when taking an action.
Return type:List[str]
state_info_keys

State info keys.

Returns:
keys for the information related to the module’s state
when taking an input.
Return type:List[str]
network_input_spec(self)

Network input spec.

Returns:List of key(str) for the network inputs.
Return type:list[str]
build(self, *inputs, name=None)

Build a Network with the given input(s).

* Do not call tf.global_variable_initializers() after building a model as it will reassign random weights to the model. The parameters inside a model will be initialized when calling build(). *

It uses the same, fixed variable scope for all Networks, to ensure parameter sharing. Different Networks must have an unique name.

Parameters:
  • inputs (list[tf.Tensor]) – Tensor input(s), recommended to be positional arguments, for example, def build(self, state_input, action_input, name=None).
  • name (str) – Name of the model, which is also the name scope of the model.
Raises:

ValueError – When a Network with the same name is already built.
Returns:

Output tensors of the model with the given

inputs.
Return type:

list[tf.Tensor]
network_output_spec(self)

Network output spec.

Returns:List of key(str) for the network outputs.
Return type:list[str]
reset(self, do_resets=None)

Reset the module.

This is effective only to recurrent modules. do_resets is effective only to vectoried modules.

For a vectorized modules, do_resets is an array of boolean indicating which internal states to be reset. The length of do_resets should be equal to the length of inputs.

Parameters:do_resets (numpy.ndarray) – Bool array indicating which states to be reset.
terminate(self)

Clean up operation.

get_trainable_vars(self)

Get trainable variables.

Returns:
A list of trainable variables in the current
variable scope.
Return type:List[tf.Variable]
get_global_vars(self)

Get global variables.

Returns:
A list of global variables in the current
variable scope.
Return type:List[tf.Variable]
get_regularizable_vars(self)

Get all network weight variables in the current scope.

Returns:
A list of network weight variables in the
current variable scope.
Return type:List[tf.Variable]
get_params(self)

Get the trainable variables.

Returns:
A list of trainable variables in the current
variable scope.
Return type:List[tf.Variable]
get_param_shapes(self)

Get parameter shapes.

Returns:A list of variable shapes.
Return type:List[tuple]
get_param_values(self)

Get param values.

Returns:
Values of the parameters evaluated in
the current session
Return type:np.ndarray
set_param_values(self, param_values)

Set param values.

Parameters:param_values (np.ndarray) – A numpy array of parameter values.
flat_to_params(self, flattened_params)

Unflatten tensors according to their respective shapes.

Parameters:flattened_params (np.ndarray) – A numpy array of flattened params.
Returns:
A list of parameters reshaped to the
shapes specified.
Return type:List[np.ndarray]