OS: Ubuntu 16.04 / x86_64
python version: 3.6
pytorch : 0.4.0
MuJoCo version: 150

sudo apt install -y build-essential autoconf libtool pkg-config python-opengl python-pil \
python-pyrex python-pyside.qtopengl idle-python2.7 qt4-dev-tools qt4-designer libqtgui4 \
libqtcore4 libqt4-xml libqt4-test libqt4-script libqt4-network libqt4-dbus python-qt4 python-qt4-gl \
libgle3 python-dev libgl1-mesa-dev libgl1-mesa-glx libosmesa6-dev python3-scipy libglew-dev patchelf

replace pgtravel with your favor name.

$ virtualenv pgtravel -p python3.6
$ source pgtravel/bin/activate

git clone https://github.com/openai/gym.git
cd gym
pip install -e .

1. Download MuJoCo-pro 150 version. download
2. Unzip mjpro150_linux.zip file to $HOME/.mujoco/mjpro150/
   • successful structure is below:
   • 
3. Setup Environment Variable
   • Write below command in ~/.bashrc file

   •   export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$HOME/.mujoco/mjpro150/bin

4. Get 30-day Trial license

• Obtain a computer id using the getid_linux program.
  • 
• Obtain the Mujoco license with the computer id.
  • 
• After successful submission, you get an e-mail from 'Roboti LLC Licensing' containing the trial license file mjkey.txt. Be careful not to leak.
  • Submit result
  • 
  • E-mail from 'Roboti LLC Licensing'
  • 
• Download mjkey.txt from the email and move it to ~/.mujoco/
  • 
• [Optional] Test Activation Key

  •   $ cp mjkey.txt ~/.mujoco/mjpro150/bin/  
      cd $HOME/.mujoco/mjpro150/bin 
      ./simulate
    

$ git clone https://github.com/openai/mujoco-py.git
$ cd mujoco-py
$ python3 setup.py install

[Optional] Test mujoco-py

$ python3
>> import mujoco_py
>> import gym
>> env = gym.make('Hopper-v2')  # or 'Humanoid-v2' 
>> env.render()

• If CompileError about gcc or cython raises, then, try to re-install mujoco-py.

pip3 install http:https://download.pytorch.org/whl/cpu/torch-0.4.0-cp36-cp36m-linux_x86_64.whl 
pip3 install torchvision

$ git clone https://github.com/reinforcement-learning-kr/pg_travel
$ pip install tensorboardX
$ pip install tensorflow

It's helpful references for me to make shared folder in virtualbox.

• https://askubuntu.com/questions/161759/how-to-access-a-shared-folder-in-virtualbox
• https://extrememanual.net/10063

$ sudo gpasswd -a [user_name] vboxsf