{"id":18520136,"url":"https://github.com/mlr-org/mlr3mbo","last_synced_at":"2025-10-12T14:41:18.191Z","repository":{"id":36499992,"uuid":"212462939","full_name":"mlr-org/mlr3mbo","owner":"mlr-org","description":"Flexible Bayesian Optimization in R","archived":false,"fork":false,"pushed_at":"2024-11-28T08:51:55.000Z","size":13930,"stargazers_count":25,"open_issues_count":25,"forks_count":1,"subscribers_count":10,"default_branch":"main","last_synced_at":"2024-12-07T16:34:28.288Z","etag":null,"topics":["automl","bayesian-optimization","bbotk","black-box-optimization","cran","gaussian-process","hpo","hyperparameter","hyperparameter-optimization","hyperparameter-tuning","machine-learning","mlr3","model-based-optimization","optimization","optimizer","r","r-package","random-forest","tuning"],"latest_commit_sha":null,"homepage":"https://mlr3mbo.mlr-org.com","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mlr-org.png","metadata":{"funding":{"github":"mlr-org"},"files":{"readme":"README.Rmd","changelog":"NEWS.md","contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-10-02T23:44:40.000Z","updated_at":"2024-11-28T08:49:25.000Z","dependencies_parsed_at":"2023-02-18T06:15:42.870Z","dependency_job_id":"7aee57d5-b503-4350-8baf-7cea01cef3b2","html_url":"https://github.com/mlr-org/mlr3mbo","commit_stats":null,"previous_names":[],"tags_count":10,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlr-org%2Fmlr3mbo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlr-org%2Fmlr3mbo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlr-org%2Fmlr3mbo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlr-org%2Fmlr3mbo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlr-org","download_url":"https://codeload.github.com/mlr-org/mlr3mbo/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":230423563,"owners_count":18223435,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["automl","bayesian-optimization","bbotk","black-box-optimization","cran","gaussian-process","hpo","hyperparameter","hyperparameter-optimization","hyperparameter-tuning","machine-learning","mlr3","model-based-optimization","optimization","optimizer","r","r-package","random-forest","tuning"],"created_at":"2024-11-06T17:18:43.406Z","updated_at":"2025-10-12T14:41:18.118Z","avatar_url":"https://github.com/mlr-org.png","language":"R","funding_links":["https://github.com/sponsors/mlr-org"],"categories":[],"sub_categories":[],"readme":"---\noutput: github_document\n---\n\n```{r, include = FALSE}\nlgr::get_logger(\"mlr3\")$set_threshold(\"warn\")\nlgr::get_logger(\"bbotk\")$set_threshold(\"warn\")\n```\n\n# mlr3mbo\n\nPackage website: [release](https://mlr3mbo.mlr-org.com/) | [dev](https://mlr3mbo.mlr-org.com/dev/)\n\n\u003c!-- badges: start --\u003e\n[![r-cmd-check](https://github.com/mlr-org/mlr3mbo/actions/workflows/r-cmd-check.yml/badge.svg)](https://github.com/mlr-org/mlr3mbo/actions/workflows/r-cmd-check.yml)\n[![CRANstatus](https://www.r-pkg.org/badges/version/mlr3mbo)](https://cran.r-project.org/package=mlr3mbo)\n[![StackOverflow](https://img.shields.io/badge/stackoverflow-mlr3-orange.svg)](https://stackoverflow.com/questions/tagged/mlr3)\n[![Mattermost](https://img.shields.io/badge/chat-mattermost-orange.svg)](https://lmmisld-lmu-stats-slds.srv.mwn.de/mlr_invite/)\n\u003c!-- badges: end --\u003e\n\nA new R6 and much more modular implementation for single- and multi-objective Bayesian Optimization.\n\n## Get Started\n\nThe best entry point to get familiar with `mlr3mbo` is provided via the [Bayesian Optimization](https://mlr3book.mlr-org.com/chapters/chapter5/advanced_tuning_methods_and_black_box_optimization.html#sec-bayesian-optimization) chapter in the `mlr3book`.\n\n## Design\n\n`mlr3mbo` is built modular relying on the following [R6](https://cran.r-project.org/package=R6) classes:\n\n* `Surrogate`: Surrogate Model\n* `AcqFunction`: Acquisition Function\n* `AcqOptimizer`: Acquisition Function Optimizer\n\nBased on these, Bayesian Optimization (BO) loops can be written, see, e.g., `bayesopt_ego` for sequential single-objective BO.\n\n`mlr3mbo` also provides an `OptimizerMbo` class behaving like any other `Optimizer` from the [bbotk](https://cran.r-project.org/package=bbotk) package as well as\na `TunerMbo` class behaving like any other `Tuner` from the [mlr3tuning](https://cran.r-project.org/package=mlr3tuning) package.\n\n`mlr3mbo` uses sensible defaults for the `Surrogate`, `AcqFunction`, `AcqOptimizer`, and even the `loop_function`.\nSee `?mbo_defaults` for more details.\n\n## Simple Optimization Example\n\nMinimize the two-dimensional Branin function via sequential BO using a GP as surrogate and EI as acquisition function optimized via a local serch:\n\n```{r, message = FALSE}\nlibrary(bbotk)\nlibrary(mlr3mbo)\nlibrary(mlr3learners)\nset.seed(1)\n\nfun = function(xdt) {\n  y = branin(xdt[[\"x1\"]], xdt[[\"x2\"]])\n  data.table(y = y)\n}\n\ndomain = ps(\n  x1 = p_dbl(-5, 10),\n  x2 = p_dbl(0, 15)\n)\n\ncodomain = ps(\n  y = p_dbl(tags = \"minimize\")\n)\n\nobjective = ObjectiveRFunDt$new(\n  fun = fun,\n  domain = domain,\n  codomain = codomain\n)\n\ninstance = oi(\n  objective = objective,\n  terminator = trm(\"evals\", n_evals = 25)\n)\n\nsurrogate = srlrn(lrn(\"regr.km\", control = list(trace = FALSE)))\n\nacq_function = acqf(\"ei\")\n\nacq_optimizer = acqo(\n  opt(\"local_search\", n_initial_points = 10, initial_random_sample_size = 1000, neighbors_per_point = 10),\n  terminator = trm(\"evals\", n_evals = 2000)\n)\n\noptimizer = opt(\"mbo\",\n  loop_function = bayesopt_ego,\n  surrogate = surrogate,\n  acq_function = acq_function,\n  acq_optimizer = acq_optimizer\n)\n\noptimizer$optimize(instance)\n```\n\nWe can quickly visualize the contours of the objective function (on log scale) as well as the sampling behavior of our BO run (lighter blue colours indicating points that were evaluated in later stages of the optimization process; the first batch is given by the initial design).\n\n```{r, eval = FALSE}\nlibrary(ggplot2)\ngrid = generate_design_grid(instance$search_space, resolution = 1000L)$data\ngrid[, y := branin(x1 = x1, x2 = x2)]\n\nggplot(aes(x = x1, y = x2, z = log(y)), data = grid) +\n  geom_contour(colour = \"black\") +\n  geom_point(aes(x = x1, y = x2, colour = batch_nr), data = instance$archive$data) +\n  labs(x =  expression(x[1]), y = expression(x[2])) +\n  theme_minimal() +\n  theme(legend.position = \"bottom\")\n```\n\nNote that you can also use `bb_optimize` as a shorthand instead of constructing an optimization instance.\n\n## Simple Tuning Example\n\n```{r, message = FALSE}\nlibrary(mlr3)\nlibrary(mlr3learners)\nlibrary(mlr3tuning)\nlibrary(mlr3mbo)\nset.seed(1)\n\ntask = tsk(\"pima\")\n\nlearner = lrn(\"classif.rpart\", cp = to_tune(lower = 1e-04, upper = 1, logscale = TRUE))\n\ninstance = tune(\n  tuner = tnr(\"mbo\"),\n  task = task,\n  learner = learner,\n  resampling = rsmp(\"holdout\"),\n  measure = msr(\"classif.ce\"),\n  term_evals = 10)\n\ninstance$result\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlr-org%2Fmlr3mbo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmlr-org%2Fmlr3mbo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlr-org%2Fmlr3mbo/lists"}