Update README.md

README.md

@@ -1,10 +1,10 @@
 # Adaptive Transformers  in RL
 
-In this experiment we replicate several results from [Stabilizing Transformers for RL](https://arxiv.org/abs/1910.06764) on both [Pong](https://gym.openai.com/envs/Pong-v0/) and [rooms_select_nonmatching_object](https://github.com/deepmind/lab/tree/master/game_scripts/levels/contributed/dmlab30#select-non-matching-object) from DMLab30. 
+Official implementation of [Adaptive Transformers in RL](http://arxiv.org/abs/2004.03761)
 
-We also extend the Stable Transformer architecture with [Adaptive Attention Span](https://arxiv.org/abs/1905.07799) on a partially observable (POMDP) setting of Reinforcement Learning. To our knowledge this is one of the first attempts to stabilize and explore Adaptive Attention Span in an RL domain.
+In this work we replicate several results from [Stabilizing Transformers for RL](https://arxiv.org/abs/1910.06764) on both [Pong](https://gym.openai.com/envs/Pong-v0/) and [rooms_select_nonmatching_object](https://github.com/deepmind/lab/tree/master/game_scripts/levels/contributed/dmlab30#select-non-matching-object) from DMLab30. 
 
-The arxiv preprint for this work can be found here [Adaptive Transformers in RL](http://arxiv.org/abs/2004.03761)
+We also extend the Stable Transformer architecture with [Adaptive Attention Span](https://arxiv.org/abs/1905.07799) on a partially observable (POMDP) setting of Reinforcement Learning. To our knowledge this is one of the first attempts to stabilize and explore Adaptive Attention Span in an RL domain.
 
 ### Steps to replicate what we did on your own machine
 1. Downloading DMLab: 
@@ -48,3 +48,15 @@ python train.py --total_steps 20000000 \
 --num_actors 32 --num_learner_threads 1 --sleep_length 20 \
 --level_name rooms_select_nonmatching_object  --mem_len 200
 ```
+
+### Reference
+If you find this repository useful, do cite it with,
+```
+@article{kumar2020adaptive,
+    title={Adaptive Transformers in RL},
+    author={Shakti Kumar and Jerrod Parker and Panteha Naderian},
+    year={2020},
+    eprint={2004.03761},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}