mlr-org · be-marc · Oct 14, 2025 · Oct 13, 2025 · Oct 13, 2025 · Oct 13, 2025
diff --git a/README.md b/README.md
@@ -21,21 +21,22 @@ You can read the rendered version of the book in either:
 To render the book yourself, follow these steps:
 
 1. Clone this repository (https://github.com/mlr-org/mlr3book.git) and navigate to the `mlr3book` directory.
-2. Pull the docker image `docker pull mlrorgdocker/mlr3-book`.
+2. Pull the docker image `docker pull mlrorg/mlr3-book`.
 3. Preview the book with
 
 ```bash
 docker run --name mlr3book \
- -v $(pwd):/book \
+ -v $(pwd):/mlr3book_latest \
  --rm \
  -p 8888:8888 \
- mlrorg/mlr3-book quarto preview book/book --port 8888 --host 0.0.0.0 --no-browser
+ mlrorg/mlr3-book quarto preview mlr3book_latest/book --port 8888 --host 0.0.0.0 --no-browser
 ```
 
 This command mounts your current directory into the docker container, allowing quarto to render the book and serve it on port 8888.
 Access the preview at `http://0.0.0.0:8888`.
 
 Make your changes locally and preview them with the above command.
+Add `--cache-refresh` to the command to refresh the cache.
 Once you are happy with your changes, open a pull request.
 The pull request will include a preview of your changes
 

diff --git a/book/chapters/appendices/errata.qmd b/book/chapters/appendices/errata.qmd
@@ -26,6 +26,7 @@ This appendix lists changes to the online version of this book to chapters inclu
 * Renamed `TuningInstanceMultiCrit` to `TuningInstanceBatchMultiCrit`.
 * Renamed `Tuner` to `TunerBatch`.
 * Replaced reference to `Param` with `Domain`.
+* Replace `lrn("surv.coxtime")` with `lrn("classif.mlp")`.
 
 ## 5. Advanced Tuning Methods and Black Box Optimization
 

diff --git a/book/chapters/chapter4/hyperparameter_optimization.qmd b/book/chapters/chapter4/hyperparameter_optimization.qmd
@@ -804,34 +804,35 @@ search_space = ps(
 ```
 
 In other cases, we may need to tune two or more 'pseudoparameters' that do not exist in our learner's parameter set but are required to tune a vector parameter.
-For example, say we want to tune the architecture of a `r index('neural network')`, in which we need to decide the number of layers and the number of nodes in each layer, this is the case in the `num_nodes` hyperparameter in `lrn("surv.coxtime")` (we use this learner as it provides a useful template for this sort of transformation, interested readers can read about survival analysis in @sec-survival).
-In this case, the learner expects a vector where each element of the vector corresponds to the number of nodes in a layer and the length of the vector is the number of layers.
+For example, say we want to tune the architecture of a `r index('neural network')`, in which we need to decide the number of layers and the number of nodes in each layer, this is the case in the `neurons` hyperparameter in `lrn("classif.mlp")` from the `mlr3torch` package.
+In this case, the learner expects a vector where each element of the vector corresponds to the number of neurons in a layer and the length of the vector is the number of layers.
 We could then tune this as follows:
 
 ```{r hyperparameter_optimization-047}
 search_space = ps(
   num_layers = p_int(lower = 1, upper = 20),
-  num_nodes_per_layer = p_int(4, 64),
+  num_neurons_per_layer = p_int(4, 64),
   .extra_trafo = function(x, param_set) {
-    x$num_nodes = rep(x$num_nodes_per_layer, x$num_layers)
+    x$neurons= rep(x$num_neurons_per_layer, x$num_layers)
     x$num_layers = NULL
-    x$num_nodes_per_layer = NULL
+    x$num_neurons_per_layer = NULL
     x
   }
 )
 ```
 
-Here we are tuning the pseudo-parameter `num_layers` between `1` and `20`, then tuning the pseudo-parameter `num_nodes_per_layer` between `4` and `64`, then combining these into a vector called `num_nodes` (the real hyperparameter) and removing the pseudo-parameters.
+Here we are tuning the pseudo-parameter `num_layers` between `1` and `20`, then tuning the pseudo-parameter `num_neurons_per_layer` between `4` and `64`, then combining these into a vector called `neurons` (the real hyperparameter) and removing the pseudo-parameters.
 
 ```{r hyperparameter_optimization-048}
-search_space$trafo(list(num_layers = 4, num_nodes_per_layer = 12))
+search_space$trafo(list(num_layers = 4, num_neurons_per_layer = 12))
 ```
 
 Even though this transformation looks complex, it only affects one of the hyperparameters (and does not need access to others), so we could include it in the learner using `to_tune()` by passing the whole `ParamSet` object:
 
 ```{r hyperparameter_optimization-049}
-learner = lrn("surv.coxtime")
-learner$param_set$set_values(num_nodes = to_tune(search_space))
+library(mlr3torch)
+learner = lrn("classif.mlp")
+learner$param_set$set_values(neurons = to_tune(search_space))
 learner$param_set$search_space()
 ```
 

diff --git a/book/common/_setup.qmd b/book/common/_setup.qmd
@@ -14,6 +14,8 @@ lgr::get_logger("mlr3oml")$set_threshold("warn")
 
 igraph::igraph_options(vertex.label.color = "black")
 
+here::i_am("book/common/_setup.qmd")
+
 options(width = 73, digits = 4)
 
 # https://github.com/mlr-org/miesmuschel/blob/master/R/zzz.R

diff --git a/book/common/_utils.qmd b/book/common/_utils.qmd
@@ -40,12 +40,12 @@ citeas = function(chaptitle) {
   %s. (2024). %s. In Bischl B, Sonabend R, Kotthoff L, Lang M, (Eds.), *Applied Machine Learning Using mlr3 in R*. CRC Press. https://mlr3book.mlr-org.com/%s.', authors_short, chaptitle, chaphtml)
 
   tex = sprintf('
-  @incollection{citekey, 
-    author = "%s", 
+  @incollection{citekey,
+    author = "%s",
     title = "%s",
     booktitle = "Applied Machine Learning Using {m}lr3 in {R}",
     publisher = "CRC Press", year = "2024",
-    editor = "Bernd Bischl and Raphael Sonabend and Lars Kotthoff and Michel Lang", 
+    editor = "Bernd Bischl and Raphael Sonabend and Lars Kotthoff and Michel Lang",
     url = "https://mlr3book.mlr-org.com/%s"
   }',
   paste0(authors, collapse = " and "), chaptitle, chaphtml)