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 3
/
Research Article
EAQR: A Multiagent Q-Learning Algorithm for Coordination of Multiple Agents
Table 3
Maximal steps for 4-agent/12-vertex box-pushing (evaluation episodes = 50,000).
= 100,000
= 500,000
= 1000,000
EAQR
2.77
1.85
1.81
WoLF-PHC
3.45
2.55
2.18
EMA Q-learning
5.90
4.66
4.61
Single-agent RL
15.89
3.66
2.20