Design and Development of Multi-Agent Reinforcement Learning Intelligence on the Robotarium Platform for Embedded System Applications

Author:

Canese Lorenzo1ORCID,Cardarilli Gian Carlo1ORCID,Dehghan Pir Mohammad Mahdi1ORCID,Di Nunzio Luca1ORCID,Spanò Sergio1ORCID

Affiliation:

1. Department of Electronic Engineering, Tor Vergata University of Rome, Via del Politecnico 1, 00133 Rome, Italy

Abstract

This research explores the use of Q-Learning for real-time swarm (Q-RTS) multi-agent reinforcement learning (MARL) algorithm for robotic applications. This study investigates the efficacy of Q-RTS in the reducing convergence time to a satisfactory movement policy through the successful implementation of four and eight trained agents. Q-RTS has been shown to significantly reduce search time in terms of training iterations, from almost a million iterations with one agent to 650,000 iterations with four agents and 500,000 iterations with eight agents. The scalability of the algorithm was addressed by testing it on several agents’ configurations. A central focus was placed on the design of a sophisticated reward function, considering various postures of the agents and their critical role in optimizing the Q-learning algorithm. Additionally, this study delved into the robustness of trained agents, revealing their ability to adapt to dynamic environmental changes. The findings have broad implications for improving the efficiency and adaptability of robotic systems in various applications such as IoT and embedded systems. The algorithm was tested and implemented using the Georgia Tech Robotarium platform, showing its feasibility for the above-mentioned applications.

Publisher

MDPI AG

Reference26 articles.

1. Deep learning in neural networks: An overview;Schmidhuber;Neural Netw.,2015

2. Fault diagnosis of actuator damage in UAVs using embedded recorded data and stacked machine learning models;Jaber;J. Supercomput.,2024

3. Approximated computing for low power neural networks;Cardarilli;Telkomnika Telecommun. Comput. Electron. Control,2019

4. Simonetta, A., Paoletti, M.C., and Nakajima, T. (2023, January 4). The SQuaRE Series as a Guarantee of Ethics in the Results of AI systems. Proceedings of the 11th International Workshop on Quantitative Approaches to Software Quality, Seoul, Republic of Korea.

5. Jaber, A.A., and Bicker, R. (2014, January 28–30). The optimum selection of wavelet transform parameters for the purpose of fault detection in an industrial robot. Proceedings of the 2014 IEEE International Conference on Control System, Computing and Engineering (ICCSCE 2014), Penang, Malaysia.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3