This project is the flexible job shop scheduling problem benchmarks (public standard instances). You can use those instances to validate the Deep reinforcement learning method in this author's account.
The benchmarks are used to evaluate the proposed method in our published paper: 'A Multi-action Deep Reinforcement Learning Framework for Flexible Job-shop Scheduling Problem'; Everyone is welcome to use our results as comparing baseline and cite our paper:
{Kun Lei, Peng Guo, Wenchao Zhao, Yi Wang, Linmao Qian, Xiangyin Meng, Liansheng Tang, A multi-action deep reinforcement learning framework for flexible Job-shop scheduling problem, Expert Systems with Applications, Volume 205, 2022, 117796, ISSN 0957-4174, https://doi.org/10.1016/j.eswa.2022.117796. (https://www.sciencedirect.com/science/article/pii/S0957417422010624)}