Cooperative multi-agent reinforcement learning is a powerful tool to solve many real-world cooperative tasks, but restrictions of real-world applications may require training the agents in a fully decentralized manner. Due to the lack of information about other agents, it is challenging to derive algorithms that can converge to the optimal joint policy in a fully decentralized setting. Thus, this research area has not been thoroughly studied. In this paper, we seek to systematically review the fully decentralized methods in two settings: maximizing a shared reward of all agents and maximizing the sum of individual rewards of all agents, and discuss open questions and future research directions.
@article{arxiv.2401.04934,
title = {Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey},
author = {Jiechuan Jiang and Kefan Su and Zongqing Lu},
journal= {arXiv preprint arXiv:2401.04934},
year = {2024}
}
Comments
The first two authors contribute equally with an alphabetic order