# Installation Guide
## Recommended Environments
Ubuntu 16.04 or newer is recommended for the installation environment. Some packages fail to build on Windows.

* [Ubuntu Desktop](https://ubuntu.com/download/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.

## Requirements
* [NVIDIA CUDA GPU](https://developer.nvidia.com/cuda-gpus): Compute Capability of the GPU must be at least 3.0.
* [CUDA Toolkit](https://developer.nvidia.com/cuda-zone): Supported Versions: 8.0, 9.0, 9.1, 9.2, 10.0, and 10.1.
* [Python 3.6+](https://www.python.org/)

.. note::

   Qualia2.0 can be used without GPU

## Install Qualia
Upgrade of setuptools and pip is recommended before the installation:
```bash
$ pip install -U setuptools pip
```
CUDA Toolkit version can be found by:
```bash
$ nvcc --version
```
Clone Github repo and cd to Qualia2.0 to install:
```bash
$ 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.
```bash
(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
```

## Uninstall Qualia
Use pip to uninstall Qualia:
```bash
$ pip uninstall qualia2
```

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

* [fastrlock](https://www.lfd.uci.edu/~gohlke/pythonlibs/#fastrlock)
* [atari-py](https://github.com/Kojoley/atari-py/releases)
* [box2d](https://www.lfd.uci.edu/~gohlke/pythonlibs/#pybox2d)

.. 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


## RL environments
### MuJoCo
1. Obtain a 30-day free trial on the [MuJoCo website](https://www.roboti.us/license.html)
   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

```bash
$ 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.

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

1. Install PyBullet

```bash
pip install pybullet
```

### [SenseAct](https://www.kindred.ai/senseact)
Reinforcement learning tasks with multiple real-world robots

1. Install SenseAct

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

### [OpenSim RL](http://osim-rl.stanford.edu/)
Reinforcement learning tasks with musculoskeletal models

1. Install OpenSim RL

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