QuarticGym: A Process Control Playground for RL Algorithms
The QuarticGym supplements several process control environments to the Openai Gym family, which quenches the pain of performing Deep Reinforcement Learning algorithms on them. Furthermore, we provided d4rl-like wrappers for accompanied datasets, make Offline RL on those environments even smoother.
Install
$ git clone --recurse-submodules git@github.com:Quarticai/QuarticGym.git
$ cd QuarticGym
$ pip install .
Note
if you want to use the PenSimPy environment with QuarticGym, you will have to build and install fastodeint following this instruction, then install PenSimPy.
For Linux users, you can just install fastodeint and PenSimPy by executing the following commands:
$ sudo apt-get install libomp-dev
$ sudo apt-get install libboost-all-dev
$ git clone --recursive git@github.com:Mohan-Zhang-u/fastodeint.git
$ cd fastodeint
$ pip install .
$ cd ..
$ git clone --recursive git@github.com:Mohan-Zhang-u/PenSimPy.git
$ cd PenSimpy
$ pip install .
Example Usage
You may want to consult this jupyter notebook to see some example use cases.