diff --git a/docs/index.md b/docs/index.md
index 8eb2fab83c..2031504d09 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -74,6 +74,7 @@ and how to implement new MDPs and new algorithms.
    user/concept_experiment
    user/sampling
    user/logging_plotting
+   user/evaluation
 
 .. toctree::
    :maxdepth: 2
diff --git a/docs/user/evaluation.md b/docs/user/evaluation.md
new file mode 100644
index 0000000000..80c4b568e7
--- /dev/null
+++ b/docs/user/evaluation.md
@@ -0,0 +1,31 @@
+# Evaluation
+
+garage provides two useful function to evaluate the performance of an
+algorithm, [log_performance](../_autoapi/garage/index.html#garage.log_performance)
+and [log_multitask_performance](../_autoapi/garage/index.html#garage.log_multitask_performance).
+`log_performance` is used for single-task algorithms, while
+`log_multitask_performance` is used for multi-task algorithms.
+
+The input of the both functions is [EpisodeBatch](../_autoapi/garage/index.html#garage.EpisodeBatch),
+which is a batch of episodes.
+
+These functions will evaluate algorithms in from the following aspects:
+
+- `AverageReturn`: The average return (sum of rewards in an episode) of all
+episodes.
+
+- `AverageDiscountedReturn`: The average discounted return of all episodes.
+
+- `StdReturn`: The standard deviation of undiscounted returns.
+
+- `MaxReturn`: The maximum undiscounted return.
+
+- `MinReturn`: The minimum undiscounted return.
+
+- `TerminationRate`: Terminated episodes / all episodes.
+
+- `SuccessRate` (if applicable): The rate of success among all episodes.
+
+----
+
+*This page was authored by Ruofu Wang ([@yeukfu](https://github.com/yeukfu)).*