Understand the project
Practical overview
When it fits
Use MLR3 when you want to construct machine-learning experiments programmatically in R and need reusable objects for tasks, learners, predictions and evaluation.
Who it is for
- R developers building reusable machine-learning components.
- Data scientists creating and evaluating classification or regression workflows in R.
Documented uses
- Represent data as a learning task and choose a compatible learner.
- Train a model, generate predictions and inspect performance measures.
- Run resampling experiments such as cross-validation and aggregate their results.
Before you choose
Requirements & limits
The package is available for installation from CRAN; a development version can be installed from GitHub. The repository specifies an LGPL-3.0 license.
- MLR3 is an R package, so using it requires an R development environment.
- Some learner choices are provided through separate extension packages rather than the core package.
- The project recommends the mlr3verse meta-package for installing MLR3 with important extensions.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Source-based practical guide
Install MLR3 from CRAN
Install the released MLR3 package in an R environment.
Before you start
- An R environment with access to CRAN.
Steps
Run install.packages("mlr3") in R.
Load the package with library(mlr3) when starting a workflow.
Expected outcome
The MLR3 package is installed and can be loaded in R.
Guide limitations
- This guide covers package installation and loading, not installation of learner extensions or a complete modeling workflow.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 13 October 2026
- Original website title
- mlr-org/mlr3 · Official homepage title · retained in its source language
Related options
mlr — The project describes MLR3 as the successor to the earlier mlr package.