diff --git a/README.md b/README.md
index 24f86ad..7bfee0f 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-**Edit a file, create a new file, and clone from Bitbucket in under 2 minutes**
+<!-- **Edit a file, create a new file, and clone from Bitbucket in under 2 minutes**
 
 When you're done, you can delete the content in this README and update the file with details for others getting started with your repository.
 
@@ -42,14 +42,33 @@ Use these steps to clone from SourceTree, our client for using the repository co
 3. When you see the **Clone New** dialog in SourceTree, update the destination path and name if you’d like to and then click **Clone**.
 4. Open the directory you just created to see your repository’s files.
 
-Now that you're more familiar with your Bitbucket repository, go ahead and add a new file locally. You can [push your change back to Bitbucket with SourceTree](https://confluence.atlassian.com/x/iqyBMg), or you can [add, commit,](https://confluence.atlassian.com/x/8QhODQ) and [push from the command line](https://confluence.atlassian.com/x/NQ0zDQ).
-# SOFA
-This repository is the implementation of SOFA, the Simulator for OFfline leArning and evaluation.
-
-### Files in the folder
-
-### Required packages
+Now that you're more familiar with your Bitbucket repository, go ahead and add a new file locally. You can [push your change back to Bitbucket with SourceTree](https://confluence.atlassian.com/x/iqyBMg), or you can [add, commit,](https://confluence.atlassian.com/x/8QhODQ) and [push from the command line](https://confluence.atlassian.com/x/NQ0zDQ). -->
 
-### Running the code
-
-### More details
+# SOFA
+This repository is the implementation of [SOFA](https://staff.fnwi.uva.nl/m.derijke/wp-content/papercite-data/pdf/huang-2020-keeping.pdf), the Simulator for OFfline leArning and evaluation.
+> Keeping Dataset Biases out of the Simulation: A Debiased Simulator for Reinforcement Learning based Recommender Systems. Jin Huang, Harrie Oosterhuis, Maarten de Rijke, Herke van Hoof. Recsys 2020.
+
+<!-- ### Files in the folder -->
+
+<!-- ### Required packages -->
+
+## Running the code
+```
+$ cd examples
+$ python run_dqn.py
+```
+
+## More details
+We also provide the details of DQN-based Policy used in experiments and the related hyperparamters (See Appendix).
+
+## Cite
+If you use our code, please cite our paper:
+```
+@inproceedings{huang2020keeping,
+  title={Keeping Dataset Biases out of the Simulation: A Debiased Simulator for Reinforcement Learning based Recommender Systems},
+  author={Huang, Jin and Oosterhuis, Harrie and de Rijke, Maarten and van Hoof, Herke},
+  booktitle={Fourteenth ACM Conference on Recommender Systems},
+  pages={190--199},
+  year={2020}
+}
+```
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..2afb22e
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,96 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: linux-64
+_libgcc_mutex=0.1=main
+_tflow_select=2.1.0=gpu
+absl-py=0.8.1=py36_0
+astor=0.8.0=py36_0
+attrs=19.3.0=py_0
+blas=1.0=mkl
+c-ares=1.15.0=h7b6447c_1001
+ca-certificates=2019.11.27=0
+certifi=2019.11.28=py36_0
+cffi=1.13.2=py36h2e261b9_0
+cudatoolkit=9.2=0
+cudnn=7.6.4=cuda9.2_0
+cupti=9.2.148=0
+cycler=0.10.0=py36_0
+dbus=1.13.12=h746ee38_0
+expat=2.2.6=he6710b0_0
+fontconfig=2.13.0=h9420a91_0
+freetype=2.9.1=h8a8886c_1
+gast=0.3.2=py_0
+glib=2.63.1=h5a9c865_0
+grpcio=1.16.1=py36hf8bcb03_1
+gst-plugins-base=1.14.0=hbbd80ab_1
+gstreamer=1.14.0=hb453b48_1
+h5py=2.9.0=py36h7918eee_0
+hdf5=1.10.4=hb1b8bf9_0
+icu=58.2=h9c2bf20_1
+importlib_metadata=1.3.0=py36_0
+intel-openmp=2019.4=243
+joblib=0.14.1=py_0
+jpeg=9b=h024ee3a_2
+keras-applications=1.0.8=py_0
+keras-preprocessing=1.1.0=py_1
+kiwisolver=1.1.0=py36he6710b0_0
+libedit=3.1.20181209=hc058e9b_0
+libffi=3.2.1=hd88cf55_4
+libgcc-ng=9.1.0=hdf63c60_0
+libgfortran-ng=7.3.0=hdf63c60_0
+libpng=1.6.37=hbc83047_0
+libprotobuf=3.10.1=hd408876_0
+libstdcxx-ng=9.1.0=hdf63c60_0
+libuuid=1.0.3=h1bed415_2
+libxcb=1.13=h1bed415_1
+libxml2=2.9.9=hea5a465_1
+markdown=3.1.1=py36_0
+matplotlib=3.1.1=py36h5429711_0
+mkl=2019.4=243
+mkl-service=2.3.0=py36he904b0f_0
+mkl_fft=1.0.15=py36ha843d7b_0
+mkl_random=1.1.0=py36hd6b4f25_0
+more-itertools=8.0.2=py_0
+ncurses=6.1=he6710b0_1
+ninja=1.9.0=py36hfd86e86_0
+numpy=1.16.0=py36h7e9f1db_1
+numpy-base=1.16.0=py36hde5b4d6_1
+openssl=1.1.1d=h7b6447c_3
+packaging=20.0=py_0
+pandas=0.25.3=py36he6710b0_0
+pcre=8.43=he6710b0_0
+pip=19.3.1=py36_0
+pluggy=0.13.1=py36_0
+protobuf=3.10.1=py36he6710b0_0
+py=1.8.1=py_0
+pycparser=2.19=py36_0
+pyparsing=2.4.6=py_0
+pyqt=5.9.2=py36h05f1152_2
+pytest=5.3.2=py36_0
+python=3.6.9=h265db76_0
+python-dateutil=2.8.1=py_0
+pytorch=1.3.1=py3.6_cuda9.2.148_cudnn7.6.3_0
+pytz=2019.3=py_0
+qt=5.9.7=h5867ecd_1
+readline=7.0=h7b6447c_5
+recnn=0.1=pypi_0
+scikit-learn=0.22=py36hd81dba3_0
+scipy=1.3.1=py36h7c811a0_0
+setuptools=41.6.0=py36_0
+sip=4.19.8=py36hf484d3e_0
+six=1.13.0=py36_0
+sqlite=3.30.1=h7b6447c_0
+tensorboard=1.12.2=py36he6710b0_0
+tensorflow=1.12.0=gpu_py36he74679b_0
+tensorflow-base=1.12.0=gpu_py36had579c0_0
+tensorflow-gpu=1.12.0=h0d30ee6_0
+termcolor=1.1.0=py36_1
+tk=8.6.8=hbc83047_0
+tornado=6.0.3=py36h7b6447c_0
+tqdm=4.40.2=py_0
+wcwidth=0.1.7=py36_0
+werkzeug=0.16.0=py_0
+wheel=0.33.6=py36_0
+xz=5.2.4=h14c3975_4
+zipp=0.6.0=py_0
+zlib=1.2.11=h7b6447c_3