Update README.md

README.md

@@ -22,6 +22,9 @@ model-index:
 
   # **Q-Learning** Agent playing **FrozenLake-v1**
   This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
+  Compared to the 4x4 training model, I increased max_steps to increase likelyhood of finding the goal during exploration. That still did not give a good solution.
+  Then I decreased decay rate to allow for more exploration and increased learning rate. But mostly it was the lower decay rate that improved the result. 
+  
   
   ## Usage
   ```python