Park and rllib integration

This is a simple integration of a reinforcement leanrning library rllib with Park.

1. Download source code from GitHub

    git clone https://github.com/saeid93/park-rllib
   

2. Download and install miniconda

3. Create conda virtual-environment

    conda create --name parkrllib python=3
   

4. Activate conda environment

    conda activate parkrllib
   

5. if you want to use GPUs make sure that you have the correct version of CUDA and cuDNN installed from here

6. Use PyTorch or Tensorflow isntallation manual to install one of them based-on your preference

7. Install the followings

    sudo apt install cmake libz-dev
   

8. Install requirements

    pip install -r requirements.txt
   

• data/
• experiments/
• park/

The code is separated into three module:

1. data/: This is the folder containing all the configs and results of the project. Could be anywhere in the project.
2. /experiments: The scripts used for using rllib.
3. park/: The park library copied from the park repository.

Link the data folder (could be placed anywhere in your harddisk) to the project. A sample of the data folder is available at data/.

Go to /experiments/utils/constants.py and set the path to your data and project folders in the file. For example:

DATA_PATH = "/Users/saeid/Codes/park-rllib/data"

See the park original repository and paper.