Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xihuai, Zhang, Zhicheng, Zhang, Weinan
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929646985019392
author Wang, Xihuai
Zhang, Zhicheng
Zhang, Weinan
author_facet Wang, Xihuai
Zhang, Zhicheng
Zhang, Weinan
contents Significant advances have recently been achieved in Multi-Agent Reinforcement Learning (MARL) which tackles sequential decision-making problems involving multiple participants. However, MARL requires a tremendous number of samples for effective training. On the other hand, model-based methods have been shown to achieve provable advantages of sample efficiency. However, the attempts of model-based methods to MARL have just started very recently. This paper presents a review of the existing research on model-based MARL, including theoretical analyses, algorithms, and applications, and analyzes the advantages and potential of model-based MARL. Specifically, we provide a detailed taxonomy of the algorithms and point out the pros and cons for each algorithm according to the challenges inherent to multi-agent scenarios. We also outline promising directions for future development of this field.
format Preprint
id arxiv_https___arxiv_org_abs_2203_10603
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects
Wang, Xihuai
Zhang, Zhicheng
Zhang, Weinan
Multiagent Systems
Artificial Intelligence
Machine Learning
Significant advances have recently been achieved in Multi-Agent Reinforcement Learning (MARL) which tackles sequential decision-making problems involving multiple participants. However, MARL requires a tremendous number of samples for effective training. On the other hand, model-based methods have been shown to achieve provable advantages of sample efficiency. However, the attempts of model-based methods to MARL have just started very recently. This paper presents a review of the existing research on model-based MARL, including theoretical analyses, algorithms, and applications, and analyzes the advantages and potential of model-based MARL. Specifically, we provide a detailed taxonomy of the algorithms and point out the pros and cons for each algorithm according to the challenges inherent to multi-agent scenarios. We also outline promising directions for future development of this field.
title Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects
topic Multiagent Systems
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2203.10603