update readme. move the files to correct directory

README.md

@@ -3,10 +3,11 @@
 ## Introduction
 Our model is a domain-independent user simulator, which means it is not based on any domain-dependent freatures and the output representation is also domain-independent. Therefore, it can easily adapt to a new domain, without additional feature engineering and model retraining.
 
-The code of TUS is in `convlab2/policy/tus` and I also create a rule-based DST of user (`convlab2/dst/rule/multiwoz/dst.py`) based on the rule-based DST in `convlab2/dst/rule/multiwoz/dst.py`.
+The code of TUS is in `convlab2/policy/tus` and a rule-based DST of user is also created in `convlab2/dst/rule/multiwoz/dst.py` based on the rule-based DST in `convlab2/dst/rule/multiwoz/dst.py`.
 
 ## How to run the model
 ### Train the user simulator
+`python3 convlab2/policy/tus/multiwoz/train.py --user_config convlab2/policy/tus/multiwoz/exp/default.json`
 
 ### Train a dialogue policy with TUS