This repository contains the PyTorch implementation of Deep Q-Network (DQN) and Model Predictive Control (MPC), and the evaluation of them on the quanser robot platform.
- Zuxin Liu (Implement algorithms, clean code, run experiment and write report)
- Yunhao Li (Implement algorithms, Analyze algorithms, Run experiment and write report)
- Junfei Xiao (Analyze algorithms, Run experiment and write report)
For the installation of the Quanser robot simulation environment, please see this page
For the implementation of the algorithms, the following packages are required:
- python = 3.6.2
- pytorch = 1.0.1
- numpy = 1.12.1
- matplotlib = 2.1.1
- gym
You can simply create the same environment as ours by using Anaconda.
All the required packages are included in the environment.yaml file. You can create the environment by the following command
conda env create -f environment.yaml
Then, activate your environment by
source activate pytorch
- Choose the algorithm you want to use and change to the corresponding folder (DQN or MPC)
- Choose the environment you want to evaluate and change to the folder (CartPoleStab, Double, Qube or Swing)
- Change the configuration file
config.ymlto the parameters you want, and follow the instructions in the folder