Modelling the Dynamics of Regret Minimization in Large Agent Populations: A Master Equation Approach
Abstract
Understanding the learning dynamics in multiagent systems is an important and challenging task. Past research on multi-agent learning mostly focuses on two-agent settings. In this paper, we consider the scenario in which a population of infinitely many agents apply regret minimization in repeated symmetric games. We propose a new formal model based on the master equation approach in statistical physics to describe the evolutionary dynamics in the agent population. Our model takes the form of a partial differential equation, which describes how the probability distribution of regret evolves over time. Through experiments, we show that our theoretical results are consistent with the agent-based simulation results.
Cite
Text
Wang et al. "Modelling the Dynamics of Regret Minimization in Large Agent Populations: A Master Equation Approach." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/76Markdown
[Wang et al. "Modelling the Dynamics of Regret Minimization in Large Agent Populations: A Master Equation Approach." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/wang2022ijcai-modelling/) doi:10.24963/IJCAI.2022/76BibTeX
@inproceedings{wang2022ijcai-modelling,
title = {{Modelling the Dynamics of Regret Minimization in Large Agent Populations: A Master Equation Approach}},
author = {Wang, Zhen and Mu, Chunjiang and Hu, Shuyue and Chu, Chen and Li, Xuelong},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2022},
pages = {534-540},
doi = {10.24963/IJCAI.2022/76},
url = {https://mlanthology.org/ijcai/2022/wang2022ijcai-modelling/}
}