Open Access

ARTICLE

Performance Evaluation of Multi-Agent Reinforcement Learning Algorithms

Abdulghani M. Abdulghani, Mokhles M. Abdulghani, Wilbur L. Walters, Khalid H. Abed^*
Department of Electrical & Computer Engineering and Computer Science, Jackson State University, Jackson, MS 39217, USA
* Corresponding Author: Khalid H. Abed. Email:
(This article belongs to the Special Issue: Intelligent Algorithms in Unmanned Systems and Swarms)

Intelligent Automation & Soft Computing https://doi.org/10.32604/iasc.2024.047017

Received 22 October 2023; Accepted 16 January 2024; Published online 12 April 2024

Abstract

Multi-Agent Reinforcement Learning (MARL) has proven to be successful in cooperative assignments. MARL is used to investigate how autonomous agents with the same interests can connect and act in one team. MARL cooperation scenarios are explored in recreational cooperative augmented reality environments, as well as real-world scenarios in robotics. In this paper, we explore the realm of MARL and its potential applications in cooperative assignments. Our focus is on developing a multi-agent system that can collaborate to attack or defend against enemies and achieve victory with minimal damage. To accomplish this, we utilize the StarCraft Multi-Agent Challenge (SMAC) environment and train four MARL algorithms: Q-learning with Mixtures of Experts (QMIX), Value-Decomposition Network (VDN), Multi-agent Proximal Policy Optimizer (MAPPO), and Multi-Agent Actor Attention Critic (MAA2C). These algorithms allow multiple agents to cooperate in a specific scenario to achieve the targeted mission. Our results show that the QMIX algorithm outperforms the other three algorithms in the attacking scenario, while the VDN algorithm achieves the best results in the defending scenario. Specifically, the VDN algorithm reaches the highest value of battle won mean and the lowest value of dead allies mean. Our research demonstrates the potential for MARL algorithms to be used in real-world applications, such as controlling multiple robots to provide helpful services or coordinating teams of agents to accomplish tasks that would be impossible for a human to do. The SMAC environment provides a unique opportunity to test and evaluate MARL algorithms in a challenging and dynamic environment, and our results show that these algorithms can be used to achieve victory with minimal damage.

---

Keywords

Reinforcement learning; RL; multi-agent; MARL; SMAC; VDN; QMIX; MAPPO

---