EAQR: A Multiagent Q-Learning Algorithm for Coordination of Multiple Agents

Zhen Zhang and Dongqing Wang

Complexity, 2018, vol. 2018, 1-14

Abstract:

We propose a cooperative multiagent Q-learning algorithm called exploring actions according to Q-value ratios (EAQR). Our aim is to design a multiagent reinforcement learning algorithm for cooperative tasks where multiple agents need to coordinate their behavior to achieve the best system performance. In EAQR, Q-value represents the probability of getting the maximal reward, while each action is selected according to the ratio of its Q-value to the sum of all actions’ Q-value and the exploration rate . Seven cooperative repeated games are used as cases to study the dynamics of EAQR. Theoretical analyses show that in some cases the optimal joint strategies correspond to the stable critical points of EAQR. Moreover, comparison experiments on stochastic games with finite steps are conducted. One is the box-pushing, and the other is the distributed sensor network problem. Experimental results show that EAQR outperforms the other algorithms in the box-pushing problem and achieves the theoretical optimal performance in the distributed sensor network problem.

Date: 2018
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/8503/2018/7172614.pdf (application/pdf)
http://downloads.hindawi.com/journals/8503/2018/7172614.xml (text/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:complx:7172614

DOI: 10.1155/2018/7172614

Access Statistics for this article

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