This repo contains code accompaning the paper: Zhi Wang, Chunlin Chen, Han-Xiong Li, Daoyi Dong, and Tzyh-Jong Tarn, "Incremental reinforcement learning with prioritized sweeping for dynamic environments", IEEE/ASME Transactions on Mechatronics, 2019. It contains code for running the incremental learning tasks with a discrete state-action space, including the simple maze and complex maze domains, as stated in the paper.
This code requires the following:
- python 3.*
- gym
- For the simple maze domain, data is generated from
myrllib/envs/simple_maze.py
- For the complex maze domain, data is generated from
myrllib/envs/complex_maze.py
- For example, to run the code in the simple maze domain with epsilon-greedy strategy, just run the bash script
./simple_maze_epsilon.sh
, also see the usage instructions in the script andmain.py
- When getting the results in the folder
output/*
, plot the results usingdata_process.py
. For example, the results for./simple_maze_epsilon.sh
is as follow:
Also, the results for other bash scripts are shown in exp/*
To ask questions or report issues, please open an issue on the issues tracker, or email to njuwangzhi@gmail.com.