No description
Find a file
Philipp Moritz 791bee343f [rllib] Implement GAE for PPO (#849)
* make information available for GAE

* buggy version of GAE estimator

* fix

* add more logging and reweight losses

* fix logging

* fix loss

* adapt advantage calculation

* update gae

* standardize returns

* don't normalize td lambda ret

* fix

* don't standardize advantages

* do standardization earlier

* different standardization

* initializer

* drop into the debugger

* fix tensorflow broadcasting bug

* vf clipping

* don't standardize tdlambdaret

* different standardization

* use huber loss for value function

* refactor -- first half

* it runs

* fix

* update

* documentation

* linting and tests

* fix linting

* naming

* fix

* linting

* fix

* remove prefix madness

* fixes

* fix

* add value function example

* fix linting

* remove newline
2017-08-23 20:35:47 -07:00
.travis Test building wheels in Travis. (#852) 2017-08-21 23:48:20 -07:00
cmake/Modules Changes to build to fix creation of wheels. (#840) 2017-08-21 17:49:35 -07:00
doc Initial fault tolerance documentation. (#845) 2017-08-19 17:38:14 -07:00
docker Be more precise which boost dependencies are needed. (#823) 2017-08-07 20:02:48 -07:00
examples Test example applications and rllib in jenkins tests. (#707) 2017-07-16 18:51:33 +00:00
python [rllib] Implement GAE for PPO (#849) 2017-08-23 20:35:47 -07:00
site Add note about adaptively launching tasks in blog post. (#582) 2017-05-20 23:19:42 -07:00
src Changes to build to fix creation of wheels. (#840) 2017-08-21 17:49:35 -07:00
test [rllib] Implement GAE for PPO (#849) 2017-08-23 20:35:47 -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] Make Pong-v0 + EvolutionStrategies work by sharing preprocessors with PPO (#848) 2017-08-21 18:51:49 -07:00
.travis.yml Test building wheels in Travis. (#852) 2017-08-21 23:48:20 -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 Fix installation instruction for ubuntu 14.04 (#805) 2017-08-02 18:14:14 -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 Expand API documentation. (#375) 2017-03-17 16:48:25 -07:00

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.

View the `documentation`_.

.. _`documentation`: http://ray.readthedocs.io/en/latest/index.html