diff --git a/README.md b/README.md
index ce0b76d..aa8dd4f 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,7 @@
 
 Implementation of <a href="https://arxiv.org/abs/2207.06881">Recurrent Memory Transformer</a> <a href="https://openreview.net/forum?id=Uynr3iPhksa">(openreview)</a> in Pytorch. They had <a href="https://arxiv.org/abs/2304.11062">a short follow up paper</a> recently that demonstrated it was able to copy information across 1 million tokens at the very least.
 
-There is no doubt in my mind that RMT would make a stronger RL agent than <a href="https://sites.google.com/view/adaptive-agent/">AdA</a>, which is just a Transformer-XL
+There is no doubt in my mind that RMT would make a stronger RL agent than <a href="https://sites.google.com/view/adaptive-agent/">AdA</a>, which is just a Transformer-XL - Update: <a href="https://arxiv.org/abs/2306.09459">Recurrent Memory Decision Transformer</a> 
 
 <a href="https://www.youtube.com/watch?v=4Cclp6yPDuw">Yannic Kilcher paper review</a>