garage.tf.models.sequential

Sequential Model.

A model composed of one or more models which are connected sequential, according to the insertion order.

class Sequential(*models, name=None)

Bases: garage.tf.models.model.Model

Sequential Model.

Parameters

• name (str) – Model name, also the variable scope.

• models (list[garage.tf.models.Model]) – The models to be connected in sequential order.

property input

input of the model by default.

Type

tf.Tensor

property output

output of the model by default.

Type

tf.Tensor

property inputs

inputs of the model by default.

Type

tf.Tensor

property outputs

outputs of the model by default.

Type

tf.Tensor

property parameters

Parameters of the model.

Returns

Parameters

Return type

np.ndarray

property name

Name (str) of the model.

This is also the variable scope of the model.

Returns

Name of the model.

Return type

str

property 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]

property 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]

build(*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_input_spec()

Network input spec.

Returns

List of key(str) for the network inputs.

Return type

list[str]

network_output_spec()

Network output spec.

Returns

List of key(str) for the network outputs.

Return type

list[str]

reset(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()

Clean up operation.

get_trainable_vars()

Get trainable variables.

Returns

A list of trainable variables in the current

variable scope.

Return type

List[tf.Variable]

get_global_vars()

Get global variables.

Returns

A list of global variables in the current

variable scope.

Return type

List[tf.Variable]

get_regularizable_vars()

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()

Get the trainable variables.

Returns

A list of trainable variables in the current

variable scope.

Return type

List[tf.Variable]

get_param_shapes()

Get parameter shapes.

Returns

A list of variable shapes.

Return type

List[tuple]

get_param_values()

Get param values.

Returns

Values of the parameters evaluated in

the current session

Return type

np.ndarray

set_param_values(param_values)

Set param values.

Parameters

param_values (np.ndarray) – A numpy array of parameter values.

flat_to_params(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]