How to use caret functions to achieve the same results as this for loop? Classification Random Forest caret

I want to run monte carlo cv 100 times on my data, my data is 2 class classification I want to use the caret package to achieve the same thing, mainly I'm confused about how to average the results of accuracy for example using caret?

# Initialize data for Binary classification
dataset$ID <- factor(dataset$ID)

# Initialize number of iterations
num_iter=100 

# Vectors to store results
acc_vec<-c()

# Function with for loop

    rf <- function(dataset)
    {
      for (i in 1:num_iter)
      {
        trainIndex <-createDataPartition(dataset$ID, p=0.8,list=FALSE)
        dataset_train <-dataset[trainIndex, ]
        dataset_test <-dataset[-trainIndex, ]
        rf <- randomForest(ID~., data=dataset_train, importance=TRUE) 
        x_test <- dataset_test[, -1]
        y_test <- dataset_test$ID

        predictions <- predict(rf, x_test)

        acc_vec <- append(acc_vec, accuracy(actual= y_test, predicted= predictions))

      }

      print(mean(acc_vec))
    }

from Recent Questions - Stack Overflow https://ift.tt/3i9fsIT
https://ift.tt/eA8V8J