diff --git a/Notes on Papers/Formal requirements elicitation with FRET.md b/Notes on Papers/Formal requirements elicitation with FRET.md
index d9e64ba5c..c8820f39f 100644
--- a/Notes on Papers/Formal requirements elicitation with FRET.md	
+++ b/Notes on Papers/Formal requirements elicitation with FRET.md	
@@ -14,7 +14,7 @@ Really I don't think they contribute much here than an explanation of what's
 going on.
 
 **Clarity:** 
-
+Easy to read. 
 
 # Second Pass
 **What is the main thrust?**
diff --git a/Notes on Papers/Runtime Safety Assurance Using Reinforcement Learning.md b/Notes on Papers/Runtime Safety Assurance Using Reinforcement Learning.md
new file mode 100644
index 000000000..8c0886087
--- /dev/null
+++ b/Notes on Papers/Runtime Safety Assurance Using Reinforcement Learning.md	
@@ -0,0 +1,30 @@
+# First Pass
+**Category:** 
+Simulation paper that talks about using a recovery controller in combination 
+with a nominal controller that is learned.
+
+**Context:** 
+Drones
+
+**Correctness:** 
+Not very. They do really well in the intro and methodology, but shit hits the fan
+when it comes to the results.
+
+**Contributions:** 
+
+
+**Clarity:** 
+
+# Second Pass
+**What is the main thrust?**
+
+**What is the supporting evidence?**
+
+**What are the key findings?**
+
+# Third Pass
+**Recreation Notes:**
+
+**Hidden Findings:**
+
+**Weak Points? Strong Points?**