# ANN: LearningStrategies.jl

**URL:** <https://discourse.julialang.org/t/ann-learningstrategies-jl/2385>\
**Category:** Community\
**Tags:** package, announcement\
**Created:** [March 1, 2017, 4:23pm UTC](https://discourse.julialang.org/t/ann-learningstrategies-jl/2385 "2017-03-01T16:23:25Z")\
**Posts on this page:** 1\
**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, 4:23pm UTC](https://discourse.julialang.org/t/ann-learningstrategies-jl/2385/1 "2017-03-01T16:23:25Z")

</div>

[LearningStrategies](https://github.com/JuliaML/LearningStrategies.jl) is a modular framework which can be used to create custom iterative algorithms with very little boilerplate code. At its core is a `MetaLearner` which can be composed of many (possibly recursive) learning strategies. It forms the basis of [StochasticOptimization](https://github.com/JuliaML/StochasticOptimization.jl) (which I hope to clean up and register soon), and the episode iteration in [Reinforce](https://github.com/JuliaML/Reinforce.jl).