Journals
Publish with us
Publishing partnerships
About us
Blog
Complexity
Journal overview
For authors
For reviewers
For editors
Table of Contents
Special Issues
Complexity
/
2018
/
Article
/
Tab 2
/
Research Article
EAQR: A Multiagent Q-Learning Algorithm for Coordination of Multiple Agents
Table 2
Average success rate for 4-agent/12-vertex box-pushing (evaluation episodes = 50,000).
= 100,000
= 500,000
= 1000,000
EAQR
82.6%
98.6%
99.6%
WoLF-PHC
80.7%
87.1%
91.7%
EMA Q-learning
66.7%
76.6%
78.7%
Single-agent RL
60.2%
91.2%
95.9%