A Value Factorization Method for MARL Based on Correlation between Individuals

Liqin Xiong, Lei Cao, Xiliang Chen, Jun Lai, Xijian Luo and Guozeng Cui

Mathematical Problems in Engineering, 2022, vol. 2022, 1-8

Abstract: Value factorization is a popular method for cooperative multi-agent deep reinforcement learning, which effectively solves explosion of state-action spatial dimension and partial observability problems. However, most existing algorithms only consider the impact of individuals rather than correlation between individuals, which leads to poor coordination between agents in complex environments. In order to resolve this problem, this paper proposes a multi-agent deep reinforcement learning value factorization method based on correlation between individuals, CI-VF, which promotes coordination between agents effectively. Firstly, the individual value function vectors are obtained according to the output of individual networks in each round. Secondly, a Spearman correlation coefficient matrix can be calculated by the vectors to measure the correlation degree of agents, and the joint correlation coefficient can be obtained to optimize joint value function. Next, we use optimized joint value function to train individual networks. Experimental results show that our method outperforms QMIX and other baselines in various scenarios under the StarCraft Multi-Agent Challenge environment.

Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/mpe/2022/8573925.pdf (application/pdf)
http://downloads.hindawi.com/journals/mpe/2022/8573925.xml (application/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnlmpe:8573925

DOI: 10.1155/2022/8573925

Access Statistics for this article

More articles in Mathematical Problems in Engineering from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().