Any issues that are filed in rllib_contrib
will be solved best-effort by the community and there is no expectation of maintenance by the RLlib team.
The api surface between algorithms in rllib_contrib and current versions of ray / rllib is not guaranteed. This means that any apis that are used in rllib_contrib could potentially become modified/removed in newer version of ray/rllib. You should check the version of ray that an algorithm is using before making any modifications, and refer to that documentation / release on github.
We will generally accept contributions to this repo that meet any of the following criteria:
We will not accept contributions that generally add a significant maintenance burden. In this case users should instead make their own repo with their contribution, using the same guidelines as this repo, and the RLlib team can help to market/promote it in the ray docs.
If users would like to contribute a new algorithm tor rllib_contrib, they should follow these steps:
README.md
file that describes the algorithm and its usecases.rllib_contrib
, and then a RLlib maintainer will review it and help you set up your testing to integrate with the CI of this repo.Regarding unit tests and long running tests: