Philipp MoritzandRobert Nishihara 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
2017-08-23 20:35:47 -07:00
2016-11-22 17:04:24 -08:00
2016-07-28 13:11:13 -07:00
2017-05-06 18:57:08 -07:00
2016-07-08 12:39:11 -07:00
2016-11-22 17:04:24 -08:00
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
S
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%