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.
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.
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
2.5. Supplemental Information¶
Here are some wheel files that might help if there are some errors during the installation:
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¶
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.
Download the MuJoCo version 2.0 binaries.
Unzip the downloaded
mujoco200
directory into~/.mujoco/mujoco200
, and place your license key (themjkey.txt
file from your email) at~/.mujoco/mjkey.txt
.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
Install PyBullet
pip install pybullet
2.6.3. SenseAct¶
Reinforcement learning tasks with multiple real-world robots
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
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