A Formal Model for Multiagent Q-Learning Dynamics on Regular Graphs
Abstract
Modeling the dynamics of multi-agent learning has long been an important research topic. The focus of previous research has been either on 2-agent settings or well-mixed infinitely large agent populations. In this paper, we consider the scenario where n Q-learning agents locate on regular graphs, such that agents can only interact with their neighbors. We examine the local interactions between individuals and their neighbors, and derive a formal model to capture the Q-value dynamics of the entire population. Through comparisons with agent-based simulations on different types of regular graphs, we show that our model describes the agent learning dynamics in an exact manner.
Cite
Text
Chu et al. "A Formal Model for Multiagent Q-Learning Dynamics on Regular Graphs." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/28Markdown
[Chu et al. "A Formal Model for Multiagent Q-Learning Dynamics on Regular Graphs." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/chu2022ijcai-formal/) doi:10.24963/IJCAI.2022/28BibTeX
@inproceedings{chu2022ijcai-formal,
title = {{A Formal Model for Multiagent Q-Learning Dynamics on Regular Graphs}},
author = {Chu, Chen and Li, Yong and Liu, Jinzhuo and Hu, Shuyue and Li, Xuelong and Wang, Zhen},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2022},
pages = {194-200},
doi = {10.24963/IJCAI.2022/28},
url = {https://mlanthology.org/ijcai/2022/chu2022ijcai-formal/}
}