Skip to content
forked from ryanjulian/rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

License

Notifications You must be signed in to change notification settings

TaoChenOSU/rllab

This branch is 5 commits ahead of, 25 commits behind ryanjulian/rllab:integration.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

846ecf0 · Apr 20, 2018
Apr 14, 2017
Sep 30, 2016
Nov 20, 2017
Apr 20, 2018
Apr 20, 2018
Apr 20, 2018
Mar 31, 2018
Jul 18, 2017
Apr 25, 2017
Apr 24, 2016
Mar 25, 2018
May 21, 2016
Apr 18, 2018
Apr 24, 2016
Oct 17, 2016
Apr 24, 2016
Mar 31, 2018
Nov 20, 2017
Apr 18, 2018
Apr 19, 2018
Apr 19, 2018
Apr 19, 2018
Apr 19, 2018
Apr 19, 2018
Apr 19, 2018

Repository files navigation

Docs Circle CI License Join the chat at https://gitter.im/rllab/rllab

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms. It includes a wide range of continuous control tasks plus implementations of the following algorithms:

rllab is fully compatible with OpenAI Gym. See here for instructions and examples.

rllab only officially supports Python 3.5+. For an older snapshot of rllab sitting on Python 2, please use the py2 branch.

rllab comes with support for running reinforcement learning experiments on an EC2 cluster, and tools for visualizing the results. See the documentation for details.

The main modules use Theano as the underlying framework, and we have support for TensorFlow under sandbox/rocky/tf.

Documentation

Documentation is available online: https://rllab.readthedocs.org/en/latest/.

Citing rllab

If you use rllab for academic research, you are highly encouraged to cite the following paper:

Credits

rllab was originally developed by Rocky Duan (UC Berkeley / OpenAI), Peter Chen (UC Berkeley), Rein Houthooft (UC Berkeley / OpenAI), John Schulman (UC Berkeley / OpenAI), and Pieter Abbeel (UC Berkeley / OpenAI). The library is continued to be jointly developed by people at OpenAI and UC Berkeley.

Slides

Slides presented at ICML 2016: https://www.dropbox.com/s/rqtpp1jv2jtzxeg/ICML2016_benchmarking_slides.pdf?dl=0

About

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 88.4%
  • Jupyter Notebook 7.9%
  • JavaScript 1.5%
  • HTML 0.8%
  • Ruby 0.6%
  • CSS 0.4%
  • Other 0.4%