The repository is for Safe Multi-Objective Reinforcement Learning (MORL) research, leveraging MuJoCo, several Safe Multi-Objective environments have been designed to evaluate the performance of safe MORL algorithms: Safe Multi-Objective HalfCheetah, Safe Multi-Objective Hopper, Safe Multi-Objective Humanoid, Safe Multi-Objective Swimmer, Safe Multi-Objective Walker, and Safe Multi-Objective Pusher have been introduced to evaluate the effectiveness of safe MORL methods. (This repository is under actively development. We appreciate any constructive comments and suggestions)
If you find the repository useful, please cite the paper:
@article{gu2024safe,
title={Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning},
author={Gu, Shangding and Sel, Bilgehan and Ding, Yuhao and Wang, Lu and Lin, Qingwei and Knoll, Alois and Jin, Ming},
journal={arXiv preprint arXiv:2405.16390},
year={2024}
}