中山大学学海讲坛（第42讲）暨岭南学术论坛系列讲座（第683期）

主要内容：

We propose a two-time scale evolutionary game approach to address multi-agent reinforcement learning (MARL) problems. The algorithm is built on three key components. First, we employ a perturbed best response to update agents’ policies. Second, we utilize a fictitious play rule to refine agents’ beliefs of their opponents. Third, policies and beliefs are updated at different learning rates compared to those used for Q-value updates. This novel approach provably converges to epsilon-Nash equilibria in general-sum MARL problems without imposing the restrictive assumptions commonly found in the literature.

AI-powered algorithms are increasingly adopted in marketplaces for pricing goods and services. However, regulators and academics have raised serious concerns about the potential for these algorithms to learn collusive behavior through their strategic interactions. While researchers predominantly rely on Q-learning to model the behavior of pricing algorithms, this method lacks convergence guarantees in multi-agent settings. Our approach offers an innovative framework for studying algorithmic collusion. Numerical experiments indicate that the sophistication of algorithms is a significant driving force behind the emergence of collusion among algorithmic agents.

报告人简介：

Nan Chen is Professor of Systems Engineering and Engineering Management at the Chinese University of Hong Kong. His research interests include financial engineering and FinTech, particularly quantitative methods in finance and risk management, Monte Carlo simulation, and applied probability. He has published in top journals and referred conference proceedings in the fields of operations research and quantitative finance, such as Review of Financial Studies, Journal of Econometrics, Operations Research, Mathematics of Operations Research, Mathematical Finance, Finance and Stochastics, Journal of Economic Dynamics and Control, and so on. The previous research topics included credit spread modeling, stochastic differential game in convertible security pricing, Monte Carlo methods in American option pricing and the related sensitivity analysis, simulation of stochastic differential equations, exotic option pricing under jump diffusion models, the dual methods for stochastic dynamic programs.

Currently, he is mainly focusing on modeling of systemic contagion and liquidity risk, complex social and financial network, single- and multi-agent reinforcement learning, Monte Carlo methods in stochastic control and learning, and Ito-Taylor expansions for jump diffusion models. Part of his research is supported by the scheme of General Research Fund, Hong Kong Research Grant Council.

     中山大学学海讲坛（第42讲），由中山大学党委办公室主办，中山大学岭南学院承办。

     欢迎师生参加！

【活动介绍】

     【中山大学学海讲坛】 “中山大学学术文化论坛”是中山大学委员会办公室统筹的校级讲座品牌项目，由南校园“学海讲坛”、北校园“杏林讲坛”、东校园“谷河讲坛”、珠海校区“若海讲坛”、深圳校区“相山讲坛”五个子品牌组成。旨在进一步丰富师生学术文化生活，提升学术文化氛围，促进“三校区五校园”学术资源共享。

     【岭南学术论坛系列讲座】中山大学岭南学术论坛系列讲座是中山大学岭南学院自2012年推出的品牌学术活动，迄今已成功举办680多期，得到了学界的高度评价。 岭南学术论坛分经济学和金融学两大系列，是定期邀请国内外优秀学者前来开展学术交流的平台。