Update README.md

README.md

@@ -60,4 +60,4 @@ This model is nearing SOTA performance for the Freeway environment: https://www.
 
 The composite score at 10 million timesteps is ~32 which is only two points off SOTA of 34. It appears that with PPO even after 2BN timesteps performance can only reach 33.6 - https://huggingface.co/edbeeching/atari_2B_atari_freeway_3333
 
-I suspect that as with QR-DQN the SAC and TQC models can reach 34 - they just need more training to do so. I may create a QR-DQN model later to see but this environment is nearly SOTA solved and will not be the focus of many future experiments. 
+I suspect that as with QR-DQN the SAC and TQC models can reach 34 - they just need more training to do so. I actually found that my QR-DQN model was inferior to SAC alone at 10 million timesteps although I didn't seed the model so cannot be 100% sure at this point.