# ANN: Reinforce.jl

**URL:** <https://discourse.julialang.org/t/ann-reinforce-jl/2386>\
**Category:** Community\
**Tags:** package, announcement\
**Created:** [March 1, 2017, 4:29pm UTC](https://discourse.julialang.org/t/ann-reinforce-jl/2386 "2017-03-01T16:29:45Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![tbreloff](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/tbreloff/32/68_2.png) [@tbreloff](https://discourse.julialang.org/u/tbreloff)\
**Post date:** [March 1, 2017, 4:29pm UTC](https://discourse.julialang.org/t/ann-reinforce-jl/2386/1 "2017-03-01T16:29:45Z")

</div>

[Reinforce](https://github.com/JuliaML/Reinforce.jl) is an interface/toolset for Reinforcement Learning in Julia. It is intended to connect general modular environments, policies, and solvers with a simple interface. Episode iteration and custom algorithms are easy to create and apply to many types of environments. Both MDP and POMDP problems can be supported.

In addition to a few toy environments included in the package, there are wrappers for [OpenAI’s gym/universe](https://github.com/JuliaML/OpenAIGym.jl) and [Atari games](https://github.com/JuliaML/AtariAlgos.jl).

---

<div class="post-metadata">

**Author:** ![mkborregaard](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/mkborregaard/32/556_2.png) [@mkborregaard](https://discourse.julialang.org/u/mkborregaard)\
**Post date:** [March 2, 2017, 7:40am UTC](https://discourse.julialang.org/t/ann-reinforce-jl/2386/2 "2017-03-02T07:40:04Z")

</div>

It’s a pretty amazing machine-learning toolkit you guys at JuliaML are building. How does one go about starting to learn how to use all of that?  
There is a docs repo that looks like it may be expanded in the future [https://juliaml.github.io/](https://juliaml.github.io/) and of course one could always clone the repos and start hacking but I am hoping there is a shortcut 🙂