Survey of Recent Multi-Agent Reinforcement Learning Algorithms Utilizing Centralized Training

TL;DR

This paper surveys recent multi-agent reinforcement learning algorithms that use centralized training to enhance cooperation, focusing on how information sharing mechanisms influence group behaviors.

Contribution

It provides a comprehensive overview of different centralized training approaches in MARL and analyzes their impact on multi-agent coordination.

Findings

Different centralized training methods lead to varied cooperative behaviors.

Information sharing mechanisms significantly influence group coordination.

The survey highlights key trends and future directions in MARL algorithms.

Abstract

Much work has been dedicated to the exploration of Multi-Agent Reinforcement Learning (MARL) paradigms implementing a centralized learning with decentralized execution (CLDE) approach to achieve human-like collaboration in cooperative tasks. Here, we discuss variations of centralized training and describe a recent survey of algorithmic approaches. The goal is to explore how different implementations of information sharing mechanism in centralized learning may give rise to distinct group coordinated behaviors in multi-agent systems performing cooperative tasks.