diff --git a/doc/api_list.rst b/doc/api_list.rst
index 97db5241..8ad597eb 100644
--- a/doc/api_list.rst
+++ b/doc/api_list.rst
@@ -35,6 +35,8 @@ Options: ::
   -m <model_file>      :  Path of the model dump file. On default, the model file name is 'train_file' + '.model'. 
                           If we set this value to 'none', the xLearn will not dump the model checkpoint.
 
+  -pre <pre-model>     :  Path of the pre-trained model. This can be used for online learning. 
+
   -t <txt_model_file>  :  Path of the TEXT model checkpoint file. On default, we do not set this option
                           and xLearn will not dump the TEXT model.
                                                                             
diff --git a/doc/command_line.rst b/doc/command_line.rst
index d3572b9b..fcb85c8b 100644
--- a/doc/command_line.rst
+++ b/doc/command_line.rst
@@ -132,6 +132,14 @@ FFM: ::
   v_3_2: 0.109711 0.102996 0.227222 0.248076
   v_3_3: 0.144264 0.0409806 0.17463 0.083712
 
+Online Learning
+----------------------------------------
+xLearn can supoort online learning, which can train new data based on the pre-trained model. User can use the ``-pre`` option to specify the file path of pre-trained model. For example: ::
+
+  ./xlearn_train ./small_train.txt -s 0 -pre ./pre_model
+
+Note that, xLearn can only uses the binary model, not the TXT model.
+
 Prediction Output
 ----------------------------------------
 
diff --git a/doc/news.md b/doc/news.md
index 310a048a..78f6a175 100644
--- a/doc/news.md
+++ b/doc/news.md
@@ -1,9 +1,14 @@
 ## What's New
 
+ - 2018-11-22 xLearn 0.4.0 version release. Main update:
+
+    * Fix bugs in previous version
+    * Add online learning for xLearn
+
  - 2018-11-10 xLearn 0.3.8 version release. Main update:
 
-   * Fix bugs in previous version.
-   * Update early-stop mechanism.
+    * Fix bugs in previous version.
+    * Update early-stop mechanism.
 
  - 2018-11-08. xLearn gets 2000 star! Congs!
 
@@ -50,4 +55,4 @@
     * New Documents
     * Faster FTRL algorithm
 
- - 2017-11-24 The first version (0.1.0) of xLearn release !
+ - 2017-11-24 The first version (0.1.0) of xLearn release !
\ No newline at end of file
diff --git a/doc/python_package.rst b/doc/python_package.rst
index eac6e33f..73029c8e 100644
--- a/doc/python_package.rst
+++ b/doc/python_package.rst
@@ -18,7 +18,7 @@ If you install xLearn Python package successfully, you will see: ::
       >  <| |___|  __/ (_| | |  | | | |
      /_/\_\_____/\___|\__,_|_|  |_| |_|
 
-        xLearn   -- 0.38 Version --
+        xLearn   -- 0.40 Version --
   -------------------------------------------------------------------------
 
 Quick Start
@@ -186,6 +186,22 @@ FFM: ::
   v_3_2: 0.109711 0.102996 0.227222 0.248076
   v_3_3: 0.144264 0.0409806 0.17463 0.083712
 
+Online Learning
+----------------------------------------
+xLearn can supoort online learning, which can train new data based on the pre-trained model. User can use the ``setPreModel`` API to specify the file path of pre-trained model. For example: ::
+
+   import xlearn as xl
+
+   ffm_model = xl.create_ffm()
+   ffm_model.setTrain("./small_train.txt")
+   ffm_model.setValidate("./small_test.txt")  
+   ffm_model.setPreModel("./pre_model")
+   param = {'task':'binary', 'lr':0.2, 'lambda':0.002} 
+            
+   ffm_model.fit(param, "./model.out") 
+
+Note that, xLearn can only uses the binary model, not the TXT model.
+
 Choose Machine Learning Algorithm
 ----------------------------------------
 
diff --git a/src/solver/checker.cc b/src/solver/checker.cc
index 178e8443..034b8025 100644
--- a/src/solver/checker.cc
+++ b/src/solver/checker.cc
@@ -67,7 +67,6 @@ std::string Checker::option_help() const {
                           not dump the model checkpoint after training. 
 
   -pre <pre-model>     :  Path of the pre-trained model. This can be used for online learning. 
-                          (Under developing)
 
   -t <txt_model_file>  :  Path of the txt model checkpoint file. On default, this option is empty 
                           and xLearn will not dump the txt model.