Skip to content
Branch: master
Find file History
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
..
Failed to load latest commit information.
agents
contrib MADDPG implementation in RLlib (#5348) Aug 6, 2019
env [rllib] Try moving RLlib to top level dir (#5324) Aug 6, 2019
evaluation [rllib] Tracing for eager tensorflow policies with `tf.function` (#5705) Sep 17, 2019
examples [rllib] Tracing for eager tensorflow policies with `tf.function` (#5705) Sep 17, 2019
models [rllib] Properly flatten 2-d observations as input to FCnet (#5733) Sep 19, 2019
offline [rllib] Fix output API when lz4 not installed (#5421) Aug 10, 2019
optimizers [rllib] Eager execution for centralized critic example, fix simple op… Sep 11, 2019
policy [rllib] Tracing for eager tensorflow policies with `tf.function` (#5705) Sep 17, 2019
tests [rllib] Properly flatten 2-d observations as input to FCnet (#5733) Sep 19, 2019
tuned_examples [rllib] Try moving RLlib to top level dir (#5324) Aug 6, 2019
utils [core worker] Python core worker object interface (#5272) Sep 13, 2019
README.md MADDPG implementation in RLlib (#5348) Aug 6, 2019
__init__.py MADDPG implementation in RLlib (#5348) Aug 6, 2019
asv.conf.json [rllib] Try moving RLlib to top level dir (#5324) Aug 6, 2019
rollout.py [rllib] Try moving RLlib to top level dir (#5324) Aug 6, 2019
scripts.py [rllib] Try moving RLlib to top level dir (#5324) Aug 6, 2019
train.py

README.md

RLlib: Scalable Reinforcement Learning

RLlib is an open-source library for reinforcement learning that offers both high scalability and a unified API for a variety of applications.

For an overview of RLlib, see the documentation.

If you've found RLlib useful for your research, you can cite the paper as follows:

@inproceedings{liang2018rllib,
    Author = {Eric Liang and
              Richard Liaw and
              Robert Nishihara and
              Philipp Moritz and
              Roy Fox and
              Ken Goldberg and
              Joseph E. Gonzalez and
              Michael I. Jordan and
              Ion Stoica},
    Title = {{RLlib}: Abstractions for Distributed Reinforcement Learning},
    Booktitle = {International Conference on Machine Learning ({ICML})},
    Year = {2018}
}

Development Install

You can develop RLlib locally without needing to compile Ray by using the setup-dev.py script. This sets up links between the rllib dir in your git repo and the one bundled with the ray package. When using this script, make sure that your git branch is in sync with the installed Ray binaries (i.e., you are up-to-date on master and have the latest wheel installed.)

You can’t perform that action at this time.