wassname/ray: An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library. - ray

mirror of https://github.com/wassname/ray.git synced 2026-07-11 09:30:55 +08:00

T

Eric Liang 9f3a4fce50 [rllib] Parallelize sample collection and gradient computation in DQN (#746 )

* wip

* works with cartpole

* lint

* fix pg

* comment

* action dist rename

* preprocessor

* fix test

* typo

* fix the action[0] nonsense

* revert

* satisfy the lint

* wip

* wip

* works with cartpole

* lint

* fix pg

* comment

* action dist rename

* preprocessor

* fix test

* typo

* fix the action[0] nonsense

* revert

* satisfy the lint

* Minor indentation changes.

* fix merge

* add humanoid

* initial dqn refactor

* remove tfutil

* fix calls

* fix tf errors 1

* closer

* runs now

* lint

* tensorboard graph

* fix linting

* more 4 space

* fix

* fix linT

* more lint

* oops

* es parity

* remove example.py

* fix training bug

* add cartpole demo

* try fixing cartpole

* allow model options, configure cartpole

* debug

* simplify

* no dueling

* avoid out of file handles

* Test dqn in jenkins.

* Minor formatting.

* lint

* fix py3

* fix issue

* remove chekcpoint

* revert

* Fixit

* sanity check configs

* update cuda

* fix

* parallel gradient computation

* update

* upd

* bug

* upd

* always record training stats

* fix

* comments

* revert assert

* add gpu mask

* fofset

* a tie

* Merge

* fix

* fix

* fix examples

* A3C -> DQN

* fix dqn test

* remove submodule

* fix linting

2017-09-29 00:06:51 -07:00

.travis

[rllib] user defined preprocessor (#985 )

2017-09-16 15:53:19 -07:00

cmake/Modules

Changes to build to fix creation of wheels. (#840 )

2017-08-21 17:49:35 -07:00

doc

fix installation instructions (#999 )

2017-09-27 13:48:23 -07:00

docker

Pin opencv-python version to 3.2.0.8 in dockerfile. (#926 )

2017-09-03 23:51:59 -07:00

examples

Resnet Example Uses tf.Datasets now (#960 )

2017-09-20 14:14:04 -07:00

python

[rllib] Parallelize sample collection and gradient computation in DQN (#746 )

2017-09-29 00:06:51 -07:00

site

Fix ray website (#963 )

2017-09-11 23:11:15 -07:00

src

Replaced ObjectWaitRequests with unordered map (#990 )

2017-09-28 15:29:26 -07:00

test

[rllib] Parallelize sample collection and gradient computation in DQN (#746 )

2017-09-29 00:06:51 -07:00

vsprojects

Windows compatibility (#57 )

2016-11-22 17:04:24 -08:00

.clang-format

Implement object table notification subscriptions and switch to using Redis modules for object table. (#134 )

2016-12-18 18:19:02 -08:00

.editorconfig

Update Windows support (#317 )

2016-07-28 13:11:13 -07:00

.gitignore

[rllib] Fix issues with PPO model restoration (#1018 )

2017-09-28 13:12:06 -07:00

.style.yapf

Make Monitor remove dead Redis entries from exiting drivers. (#994 )

2017-09-26 00:11:38 -07:00

.travis.yml

Make Monitor remove dead Redis entries from exiting drivers. (#994 )

2017-09-26 00:11:38 -07:00

build-docker.sh

Fix build-docker.sh bug (#515 )

2017-05-06 18:57:08 -07:00

build.sh

Changes to build to fix creation of wheels. (#840 )

2017-08-21 17:49:35 -07:00

CMakeLists.txt

Rebase Ray on latest arrow (remove numbuf from Ray). (#910 )

2017-09-04 22:58:49 -07:00

LICENSE

[rllib] Basic port of baselines/deepq to rllib (#709 )

2017-07-07 18:37:00 +00:00

pylintrc

adding pylint (#233 )

2016-07-08 12:39:11 -07:00

Ray.sln

Windows compatibility (#57 )

2016-11-22 17:04:24 -08:00

README.rst

Fix ray website (#963 )

2017-09-11 23:11:15 -07:00

README.rst

Ray
===

.. image:: https://travis-ci.org/ray-project/ray.svg?branch=master
    :target: https://travis-ci.org/ray-project/ray

.. image:: https://readthedocs.org/projects/ray/badge/?version=latest
    :target: http://ray.readthedocs.io/en/latest/?badge=latest

|

Ray is a flexible, high-performance distributed execution framework.

Installation
------------

- Ray can be installed on Linux and Mac with ``pip install ray``.
- To build Ray from source, see the instructions for `Ubuntu`_ and `Mac`_.

.. _`Ubuntu`: http://ray.readthedocs.io/en/latest/install-on-ubuntu.html
.. _`Mac`: http://ray.readthedocs.io/en/latest/install-on-macosx.html


More Information
----------------

- `Mailing List`_
- `Documentation`_
- `Blog`_
- `HotOS paper`_

.. _`Mailing List`: https://groups.google.com/forum/#!forum/ray-dev
.. _`Documentation`: http://ray.readthedocs.io/en/latest/index.html
.. _`Blog`: https://ray-project.github.io/
.. _`HotOS paper`: https://arxiv.org/abs/1703.03924

Description

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

Readme Multiple Licenses 111 MiB

Languages

Python 56.6%

C++ 28.8%

Java 8.5%

TypeScript 1.7%

Starlark 1.4%

Other 2.8%