diff --git a/R/adjust_significance_level.R b/R/adjust_significance_level.R
index a9c916f..6e8bec0 100644
--- a/R/adjust_significance_level.R
+++ b/R/adjust_significance_level.R
@@ -29,7 +29,7 @@
 #' # ...
 #' 
 #' # Simulation-based adjustment of the significance level using `allocation_rule`
-#' \dontrun{
+#' \donttest{
 #' adjusted_alpha <- adjust_significance_level(
 #'   allocation_rule, models,
 #'   N_total = 150, N_ini = rep(10, 5), N_block = 10,
diff --git a/R/learn_allocation_rule.R b/R/learn_allocation_rule.R
index 4387cf5..624658f 100644
--- a/R/learn_allocation_rule.R
+++ b/R/learn_allocation_rule.R
@@ -65,7 +65,7 @@
 #' 
 #' # We obtain an optimal adaptive allocation rule by executing 
 #' # `learn_allocation_rule()` with the `models`.
-#' \dontrun{
+#' \donttest{
 #' allocation_rule <- learn_allocation_rule(
 #'   models,
 #'   N_total = 150, N_ini = rep(10, 5), N_block = 10, Delta = 1.3,
@@ -85,7 +85,7 @@
 #' )
 #' 
 #' # Then, we specify the argument `rl_models` in `learn_allocation_rule` function.
-#' \dontrun{
+#' \donttest{
 #' allocation_rule <- learn_allocation_rule(
 #'   models,
 #'   N_total = 150, N_ini = rep(10, 5), N_block = 10, Delta = 1.3,
diff --git a/R/rl_config_set.R b/R/rl_config_set.R
index 337a577..3276888 100644
--- a/R/rl_config_set.R
+++ b/R/rl_config_set.R
@@ -27,14 +27,14 @@
 #' @return A list of reinforcement learning configuration parameters
 #' 
 #' @examples
-#' \dontrun{
+#' \donttest{
 #' allocation_rule <- learn_allocation_rule(
 #'   models, 
 #'   N_total = 150, N_ini = rep(10, 5), N_block = 10, Delta = 1.3,
 #'   outcome_type = "continuous", sd_normal = sqrt(4.5), 
 #'   seed = 123, 
-#'   # We change `iter` to 200 and `cores` for reinforcement learning to 8
-#'   rl_config = rl_config_set(iter = 200, cores = 8), 
+#'   # We change `iter` to 200 and `cores` for reinforcement learning to 2
+#'   rl_config = rl_config_set(iter = 200, cores = 2), 
 #'   alpha = 0.025
 #' )
 #' } 
diff --git a/R/rl_dnn_config.R b/R/rl_dnn_config.R
index b38d89d..1ee6a2d 100644
--- a/R/rl_dnn_config.R
+++ b/R/rl_dnn_config.R
@@ -14,7 +14,7 @@
 #' @return A list of DNN configuration parameters
 #' 
 #' @examples
-#' \dontrun{
+#' \donttest{
 #' allocation_rule <- learn_allocation_rule(
 #'   models, 
 #'   N_total = 150, N_ini = rep(10, 5), N_block = 10, Delta = 1.3,
diff --git a/R/simulate_one_trial.R b/R/simulate_one_trial.R
index de9f645..91354f7 100644
--- a/R/simulate_one_trial.R
+++ b/R/simulate_one_trial.R
@@ -37,7 +37,7 @@
 #'        the estimated target dose, and the MAE.
 #' 
 #' @examples
-#' \dontrun{  
+#' \donttest{  
 #' # We computed `allocation_rule` and `adjusted_alpha`
 #' # ...
 #' 
diff --git a/man/adjust_significance_level.Rd b/man/adjust_significance_level.Rd
index ac24acf..99f5866 100644
--- a/man/adjust_significance_level.Rd
+++ b/man/adjust_significance_level.Rd
@@ -60,7 +60,7 @@ Adjust Significance Level on a Simulation Basis
 # ...
 
 # Simulation-based adjustment of the significance level using `allocation_rule`
-\dontrun{
+\donttest{
 adjusted_alpha <- adjust_significance_level(
   allocation_rule, models,
   N_total = 150, N_ini = rep(10, 5), N_block = 10,
diff --git a/man/learn_allocation_rule.Rd b/man/learn_allocation_rule.Rd
index 45c236b..7fb32b0 100644
--- a/man/learn_allocation_rule.Rd
+++ b/man/learn_allocation_rule.Rd
@@ -112,7 +112,7 @@ models <- DoseFinding::Mods(
 
 # We obtain an optimal adaptive allocation rule by executing 
 # `learn_allocation_rule()` with the `models`.
-\dontrun{
+\donttest{
 allocation_rule <- learn_allocation_rule(
   models,
   N_total = 150, N_ini = rep(10, 5), N_block = 10, Delta = 1.3,
@@ -132,7 +132,7 @@ rl_models <- DoseFinding::Mods(
 )
 
 # Then, we specify the argument `rl_models` in `learn_allocation_rule` function.
-\dontrun{
+\donttest{
 allocation_rule <- learn_allocation_rule(
   models,
   N_total = 150, N_ini = rep(10, 5), N_block = 10, Delta = 1.3,
diff --git a/man/rl_config_set.Rd b/man/rl_config_set.Rd
index 9c01c26..d51e410 100644
--- a/man/rl_config_set.Rd
+++ b/man/rl_config_set.Rd
@@ -57,14 +57,14 @@ Mainly settings for the arguments of the training() function.
 Not compatible with the new API stack introduced in Ray 2.10.0.
 }
 \examples{
-\dontrun{
+\donttest{
 allocation_rule <- learn_allocation_rule(
   models, 
   N_total = 150, N_ini = rep(10, 5), N_block = 10, Delta = 1.3,
   outcome_type = "continuous", sd_normal = sqrt(4.5), 
   seed = 123, 
-  # We change `iter` to 200 and `cores` for reinforcement learning to 8
-  rl_config = rl_config_set(iter = 200, cores = 8), 
+  # We change `iter` to 200 and `cores` for reinforcement learning to 2
+  rl_config = rl_config_set(iter = 200, cores = 2), 
   alpha = 0.025
 )
 } 
diff --git a/man/rl_dnn_config.Rd b/man/rl_dnn_config.Rd
index 7a781ca..06aade3 100644
--- a/man/rl_dnn_config.Rd
+++ b/man/rl_dnn_config.Rd
@@ -29,7 +29,7 @@ DNN (deep neural network) configuration for reinforcement learning.
 For detail, see Section 3.2.6 of the original paper.
 }
 \examples{
-\dontrun{
+\donttest{
 allocation_rule <- learn_allocation_rule(
   models, 
   N_total = 150, N_ini = rep(10, 5), N_block = 10, Delta = 1.3,
diff --git a/man/simulate_one_trial.Rd b/man/simulate_one_trial.Rd
index 7b1af22..4c2dd9a 100644
--- a/man/simulate_one_trial.Rd
+++ b/man/simulate_one_trial.Rd
@@ -74,7 +74,7 @@ the estimated target dose, and the MAE.
 Simulate One Trial Using an Obtained Optimal Adaptive Allocation Rule
 }
 \examples{
-\dontrun{  
+\donttest{  
 # We computed `allocation_rule` and `adjusted_alpha`
 # ...