2018-07-01 00:05:08 -07:00
RLlib: Scalable Reinforcement Learning
======================================
2017-09-12 23:38:21 -07:00
2018-07-01 00:05:08 -07:00
RLlib is an open-source library for reinforcement learning that offers both a collection of reference algorithms and scalable primitives for composing new ones.
2017-12-06 18:17:51 -08:00
2018-07-01 00:05:08 -07:00
.. image :: rllib-stack.svg
2017-12-06 18:17:51 -08:00
2018-07-01 00:05:08 -07:00
Learn more about RLlib's design by reading the `ICML paper <https://arxiv.org/abs/1712.09381> `__ .
2018-03-17 14:45:04 -07:00
2017-12-08 01:57:19 -08:00
Installation
------------
2018-07-01 00:05:08 -07:00
RLlib has extra dependencies on top of `` ray `` . First, you'll need to install either `PyTorch <http://pytorch.org/> `__ or `TensorFlow <https://www.tensorflow.org> `__ . Then, install the Ray RLlib module:
2018-06-10 10:29:12 -07:00
.. code-block :: bash
pip install tensorflow # or tensorflow-gpu
2018-07-01 00:05:08 -07:00
pip install ray[rllib]
2018-06-10 10:29:12 -07:00
You might also want to clone the Ray repo for convenient access to RLlib helper scripts:
.. code-block :: bash
2018-01-19 10:08:45 -08:00
git clone https://github.com/ray-project/ray
2018-07-01 00:05:08 -07:00
cd ray/python/ray/rllib
2017-12-08 01:57:19 -08:00
2018-07-01 00:05:08 -07:00
Training APIs
-------------
* `Command-line <rllib-training.html> `__
* `Python API <rllib-training.html#python-api> `__
* `REST API <rllib-training.html#rest-api> `__
2018-06-10 10:29:12 -07:00
2018-07-01 00:05:08 -07:00
Environments
------------
* `RLlib Environments Overview <rllib-env.html> `__
* `OpenAI Gym <rllib-env.html#openai-gym> `__
2018-07-08 18:46:52 -07:00
* `Vectorized <rllib-env.html#vectorized> `__
2018-07-01 00:05:08 -07:00
* `Multi-Agent <rllib-env.html#multi-agent> `__
* `Serving (Agent-oriented) <rllib-env.html#serving> `__
* `Offline Data Ingest <rllib-env.html#offline-data> `__
* `Batch Asynchronous <rllib-env.html#batch-asynchronous> `__
Algorithms
----------
* `Ape-X Distributed Prioritized Experience Replay <rllib-algorithms.html#ape-x-distributed-prioritized-experience-replay> `__
* `Asynchronous Advantage Actor-Critic <rllib-algorithms.html#asynchronous-advantage-actor-critic> `__
* `Deep Deterministic Policy Gradients <rllib-algorithms.html#deep-deterministic-policy-gradients> `__
* `Deep Q Networks <rllib-algorithms.html#deep-q-networks> `__
* `Evolution Strategies <rllib-algorithms.html#evolution-strategies> `__
* `Policy Gradients <rllib-algorithms.html#policy-gradients> `__
* `Proximal Policy Optimization <rllib-algorithms.html#proximal-policy-optimization> `__
Models and Preprocessors
2018-07-08 18:46:52 -07:00
------------------------
2018-07-01 00:05:08 -07:00
* `RLlib Models and Preprocessors Overview <rllib-models.html> `__
* `Built-in Models and Preprocessors <rllib-models.html#built-in-models-and-preprocessors> `__
* `Custom Models <rllib-models.html#custom-models> `__
* `Custom Preprocessors <rllib-models.html#custom-preprocessors> `__
2018-07-08 18:46:52 -07:00
RLlib Concepts
--------------
* `Policy Graphs <rllib-concepts.html> `__
* `Policy Evaluation <rllib-concepts.html#policy-evaluation> `__
* `Policy Optimization <rllib-concepts.html#policy-optimization> `__
2018-07-01 00:05:08 -07:00
Package Reference
-----------------
* `ray.rllib.agents <rllib-package-ref.html#module-ray.rllib.agents> `__
* `ray.rllib.env <rllib-package-ref.html#module-ray.rllib.env> `__
* `ray.rllib.evaluation <rllib-package-ref.html#module-ray.rllib.evaluation> `__
* `ray.rllib.models <rllib-package-ref.html#module-ray.rllib.models> `__
* `ray.rllib.optimizers <rllib-package-ref.html#module-ray.rllib.optimizers> `__
* `ray.rllib.utils <rllib-package-ref.html#module-ray.rllib.utils> `__
