2. Installation Guide

2.1. Recommended Environments

Ubuntu 16.04 or newer is recommended for the installation environment. Some packages fail to build on Windows.

• Ubuntu Desktop

Note

There is no guarantee that Qualia works on other environments including Windows and macOS, even if Qualia may seem to be running correctly.

2.2. Requirements

• NVIDIA CUDA GPU: Compute Capability of the GPU must be at least 3.0.

• CUDA Toolkit: Supported Versions: 8.0, 9.0, 9.1, 9.2, 10.0, and 10.1.

• Python 3.6+

Note

Qualia2.0 can be used without GPU

2.3. Install Qualia

Upgrade of setuptools and pip is recommended before the installation:

$ pip install -U setuptools pip

CUDA Toolkit version can be found by:

$ nvcc --version

Clone Github repo and cd to Qualia2.0 to install:

$ git clone https://github.com/Kashu7100/Qualia2.0.git
$ cd Qualia2.0

Depending on the CUDA version you have installed on your host, choose the best option from following.

(For CUDA 8.0)
$ python setup.py install --cuda 80
(For CUDA 9.0)
$ python setup.py install --cuda 90
(For CUDA 9.1)
$ python setup.py install --cuda 91
(For CUDA 9.2)
$ python setup.py install --cuda 92
(For CUDA 10.0)
$ python setup.py install --cuda 100
(For CUDA 10.1)
$ python setup.py install --cuda 101
(For without CUDA)
$ python setup.py install

2.4. Uninstall Qualia

Use pip to uninstall Qualia:

$ pip uninstall qualia2

2.5. Supplemental Information

Here are some wheel files that might help if there are some errors during the installation:

• fastrlock

• atari-py

• box2d

Note

You need the wheel package to install libraries from .whl files:

$ pip install wheel

Once you installed wheel package, you can install libraries from .whl file as follows:

$ pip install /path/to/the/wheel_file.whl

2.6. RL environments

2.6.1. MuJoCo

1. Obtain a 30-day free trial on the MuJoCo website or free license if you are a student. The license key will arrive in an email with your username and password.

2. Download the MuJoCo version 2.0 binaries.

3. Unzip the downloaded mujoco200 directory into ~/.mujoco/mujoco200, and place your license key (the mjkey.txt file from your email) at ~/.mujoco/mjkey.txt.

4. Install mujoco-py

$ git clone https://github.com/openai/mujoco-py.git
$ cd mujoco-py
$ pip install -r requirements.txt
$ pip install -r requirements.dev.txt
$ python setup.py install

Note

To run mujoco-py, MuJoCo needs to be installed on the machine.

2.6.2. PyBullet

Open source physics simulation, robotics and deep reinforcement learning based on the Bullet Physics SDK

1. Install PyBullet

pip install pybullet

2.6.3. SenseAct

Reinforcement learning tasks with multiple real-world robots

1. Install SenseAct

git clone https://github.com/kindredresearch/SenseAct.git
cd SenseAct
pip install -e .

2.6.4. OpenSim RL

Reinforcement learning tasks with musculoskeletal models

1. Install OpenSim RL

conda install -c kidzik opensim
conda install -c conda-forge lapack git
pip install git+https://github.com/stanfordnmbl/osim-rl.git