DOI: 10.7763/IJCTE.2021.V13.1284
Heterogeneous Agent Cooperative Planning Based on Q-Learning
Abstract—In this paper, we present a model to achieve the collaboration of heterogeneous agent in the open-dynamic environment. This model simulates a disaster rescue scenario, defines the environment, action space, reward function and action selection strategy with Q-learning algorithm. Heterogeneous rescue agent is used to assist agent in the scene. Experiments based on the python environment prove that the heterogeneous agent collaboration method can effectively complete the collaboration in unknown environment, and it has better performance than the homogeneous method.
Index Terms—Multiagent-system, collaboration, heterogeneous, reinforcement learning.
Chenfeng Gan, Wei Liu, Ning Wang, and Xingyu Ye are with Wuhan Institute of Technology, Wuhan, China (e-mail: 728384289@qq.com, liuwei@wit.edu.cn, 1757674599@qq.com, 849413957@qq.com).
Cite:Chenfeng Gan, Wei Liu, Ning Wang, and Xingyu Ye, "Heterogeneous Agent Cooperative Planning Based on Q-Learning," International Journal of Computer Theory and Engineering vol. 13, no. 1, pp. 17-23, 2021.
Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).