Module: tf_agents.distributions.utils
Stay organized with collections
Save and categorize content based on your preferences.
Utilities related to distributions.
Classes
class DistributionSpecV2
: Describes a tfp.distribution.Distribution using nested parameters.
class Params
: The (recursive) parameters of objects exposing the parameters
property.
class SquashToSpecNormal
: Scales an input normalized action distribution to match spec bounds.
Functions
assert_specs_are_compatible(...)
: Checks that the output of network.create_variables
matches a spec.
get_parameters(...)
: Creates a recursive Params
object from value
.
make_from_parameters(...)
: Creates an instance of type value.type_
with the parameters in value
.
merge_to_parameters_from_dict(...)
: Merges dict matching data of parameters_to_dict(value)
to a new Params
.
parameters_to_dict(...)
: Converts value
to a nested dict
(excluding all type_
info).
scale_distribution_to_spec(...)
: Scales the given distribution to the bounds of the given spec.
Other Members |
absolute_import
|
Instance of __future__._Feature
|
division
|
Instance of __future__._Feature
|
print_function
|
Instance of __future__._Feature
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-04-26 UTC.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# Module: tf_agents.distributions.utils\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/distributions/utils.py) |\n\nUtilities related to distributions.\n\nClasses\n-------\n\n[`class DistributionSpecV2`](../../tf_agents/distributions/utils/DistributionSpecV2): Describes a tfp.distribution.Distribution using nested parameters.\n\n[`class Params`](../../tf_agents/distributions/utils/Params): The (recursive) parameters of objects exposing the `parameters` property.\n\n[`class SquashToSpecNormal`](../../tf_agents/distributions/utils/SquashToSpecNormal): Scales an input normalized action distribution to match spec bounds.\n\nFunctions\n---------\n\n[`assert_specs_are_compatible(...)`](../../tf_agents/distributions/utils/assert_specs_are_compatible): Checks that the output of [`network.create_variables`](../../tf_agents/networks/network/create_variables) matches a spec.\n\n[`get_parameters(...)`](../../tf_agents/distributions/utils/get_parameters): Creates a recursive `Params` object from `value`.\n\n[`make_from_parameters(...)`](../../tf_agents/distributions/utils/make_from_parameters): Creates an instance of type `value.type_` with the parameters in `value`.\n\n[`merge_to_parameters_from_dict(...)`](../../tf_agents/distributions/utils/merge_to_parameters_from_dict): Merges dict matching data of `parameters_to_dict(value)` to a new `Params`.\n\n[`parameters_to_dict(...)`](../../tf_agents/distributions/utils/parameters_to_dict): Converts `value` to a nested `dict` (excluding all `type_` info).\n\n[`scale_distribution_to_spec(...)`](../../tf_agents/distributions/utils/scale_distribution_to_spec): Scales the given distribution to the bounds of the given spec.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Other Members ------------- ||\n|-----------------|-----------------------------------|\n| absolute_import | Instance of `__future__._Feature` |\n| division | Instance of `__future__._Feature` |\n| print_function | Instance of `__future__._Feature` |\n\n\u003cbr /\u003e"]]