diff --git a/.gitmodules b/.gitmodules
index ec66eee..423230a 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -3,10 +3,10 @@
 	url = https://git.ias.informatik.tu-darmstadt.de/common/experiment_launcher.git
 [submodule "deps/motion_planning_baselines"]
 	path = deps/motion_planning_baselines
-	url = git@github.com:anindex/motion_planning_baselines.git
+	url = https://github.com/anindex/motion_planning_baselines.git
 [submodule "deps/torch_robotics"]
 	path = deps/torch_robotics
-	url = git@github.com:anindex/torch_robotics.git
+	url = https://github.com/anindex/torch_robotics.git
 [submodule "deps/storm"]
 	path = deps/storm
-	url = git@github.com:jacarvalho/storm.git
+	url = https://github.com/jacarvalho/storm.git
diff --git a/README.md b/README.md
index d7ac1d7..deaaa03 100644
--- a/README.md
+++ b/README.md
@@ -27,10 +27,27 @@ If you have any questions please let me know -- [joao@robot-learning.de](mailto:
 ---
 ## Installation
 
-Download [IsaacGym Preview 4](https://developer.nvidia.com/isaac-gym) and extract it under `deps/isaacgym`. 
+Pre-requisites:
+- Ubuntu 20.04 (maybe works with other OS)
+- [miniconda](https://docs.conda.io/projects/miniconda/en/latest/index.html)
+
+Clone this repository with
+```bash
+cd ~
+git clone --recurse-submodules https://github.com/jacarvalho/mpd-public.git
+cd mpd-public
+```
+
+Download [IsaacGym Preview 4](https://developer.nvidia.com/isaac-gym) and extract it under `deps/isaacgym`
+```bash
+mv ~/Downloads/IsaacGym_Preview_4_Package.tar.gz ~/mpd-public/deps/
+cd ~/mpd-public/deps
+tar -xvf IsaacGym_Preview_4_Package.tar.gz
+```
 
 Run the bash setup script to install everything.
 ```
+cd ~/mpd-public
 bash setup.sh
 ```
 
@@ -40,9 +57,13 @@ bash setup.sh
 To try out the MPD inference, first download the data and the trained models. 
 
 ```bash
-gdown 1mmJAFg6M2I1OozZcyueKp_AP0HHkCq2k
+conda activate mpd
+```
+
+```bash
+gdown --id 1mmJAFg6M2I1OozZcyueKp_AP0HHkCq2k
 tar -xvf data_trajectories.tar.gz
-gdown 1I66PJ5QudCqIZ2Xy4P8e-iRBA8-e2zO1
+gdown --id 1I66PJ5QudCqIZ2Xy4P8e-iRBA8-e2zO1
 tar -xvf data_trained_models.tar.gz
 ```
 
@@ -73,6 +94,10 @@ The results will be saved under `data_trained_models/[model_id]/results_inferenc
 
 We recommend running the follwowing in a SLURM cluster.
 
+```bash
+conda activate mpd
+```
+
 To regenerate the data:
 ```bash
 cd scripts/generate_data
diff --git a/requirements.txt b/requirements.txt
index d6147cd..c7ea5f3 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,4 @@
-numpy==1.19.5
+numpy
 tensorboard
 tqdm
 ConfigArgParse
diff --git a/setup.sh b/setup.sh
index a46393d..b801289 100644
--- a/setup.sh
+++ b/setup.sh
@@ -8,9 +8,6 @@ if [ ! -d $ISAACGYM_DIR ]; then
   exit
 fi
 
-git submodule update --init --recursive --remote --progress
-
-
 export SKLEARN_ALLOW_DEPRECATED_SKLEARN_PACKAGE_INSTALL=True
 
 eval "$(~/miniconda3/bin/conda shell.bash hook)"
@@ -49,4 +46,5 @@ cd ${ROOT_DIR} && pip install -e .
 conda remove --force ncurses --yes
 
 conda install -c "conda-forge/label/cf202003" gdown --yes
+pip install --upgrade --no-cache-dir gdown