mirror of
https://github.com/vale981/ray
synced 2025-03-06 02:21:39 -05:00
f9b71a8bf6
This PR consolidates both #21667 and #21759 (look there for features), but improves on them in the following way: - [x] we reverted renaming of existing projects `tune`, `rllib`, `train`, `cluster`, `serve`, `raysgd` and `data` so that links won't break. I think my consolidation efforts with the `ray-` prefix were a little overeager in that regard. It's better like this. Only the creation of `ray-core` was a necessity, and some files moved into the `rllib` folder, so that should be relatively benign. - [x] Additionally, we added Algolia `docsearch`, screenshot below. This is _much_ better than our current search. Caveat: there's a sphinx dependency that needs to be replaced (`sphinx-tabs`) by another, newer one (`sphinx-panels`), as the former prevents loading of the `algolia.js` library. Will follow-up in the next PR (hoping this one doesn't get re-re-re-re-reverted).
35 lines
1.3 KiB
ReStructuredText
35 lines
1.3 KiB
ReStructuredText
.. _policy-reference-docs:
|
|
|
|
Policies
|
|
========
|
|
|
|
The :py:class:`~ray.rllib.policy.policy.Policy` class contains functionality to compute
|
|
actions for decision making in an environment, as well as computing loss(es) and gradients,
|
|
updating a neural network model as well as postprocessing a collected environment trajectory.
|
|
One or more :py:class:`~ray.rllib.policy.policy.Policy` objects sit inside a
|
|
:py:class:`~ray.rllib.evaluation.RolloutWorker`'s :py:class:`~ray.rllib.policy.policy_map.PolicyMap` and
|
|
are - if more than one - are selected based on a multi-agent ``policy_mapping_fn``,
|
|
which maps agent IDs to a policy ID.
|
|
|
|
.. https://docs.google.com/drawings/d/1eFAVV1aU47xliR5XtGqzQcdvuYs2zlVj1Gb8Gg0gvnc/edit
|
|
.. figure:: ../images/policy_classes_overview.svg
|
|
:align: left
|
|
|
|
**RLlib's Policy class hierarchy:** Policies are deep-learning framework
|
|
specific as they hold functionality to handle a computation graph (e.g. a
|
|
TensorFlow 1.x graph in a session). You can define custom policy behavior
|
|
by sub-classing either of the available, built-in classes, depending on your
|
|
needs.
|
|
|
|
|
|
Policy API Reference
|
|
--------------------
|
|
|
|
.. toctree::
|
|
:maxdepth: 1
|
|
|
|
policy/policy.rst
|
|
policy/tf_policies.rst
|
|
policy/torch_policy.rst
|
|
policy/custom_policies.rst
|
|
|