马尔科夫博弈组成了多智能体强化进建和智能体挨次交互的钻研基。。。。。。,,,,,,,其最优解被称为美满平衡(Markov perfect equilibrium,,,,,,,,MPE)。。。。。。已有钻研批注,,,,,,,,在无界马尔科夫博弈中求解 MPE 至少是 PPAD 难题的。。。。。。因而,,,,,,,,邓幼铁教授及其合作者提出了近似马尔科夫美满平衡作为无界多人广义和马尔科夫博弈推算问题的解概想,,,,,,,,并证了然该解概想既保留了马尔科夫美满性质又拥有 PPAD-Complete 复杂度。。。。。。该解的概想为多智能体进建算法由静态双人博弈成功扩大到动态多人马尔科夫博弈奠定了推算复杂度理论基。。。。。。,,,,,,,为散布式人为智能、多智能体系统钻研启发了新的蹊径与思路。。。。。。
第八期 z6首页-TNSE 结合卓越讲座系列活动,,,,,,,,我们有幸约请到北京大学的邓幼铁教授介绍马尔科夫博弈的近似美满平衡,,,,,,,,并分享他在这个领域内的有关钻研成就与有趣发现。。。。。。
z6首页-TNSE Joint Distinguished Seminar Series is co-sponsored by IEEE Transactions on Network Science and Engineering (TNSE) and Shenzhen Institute of Artificial Intelligence and Robotics for Society (z6首页), with joint support from The Chinese University of Hong Kong, Shenzhen, Network Communication and Economics Laboratory (NCEL), and IEEE. This series aims to bring together top international experts and scholars in the field of network science and engineering to share cutting-edge scientific and technological achievements.
Join the seminar on April 28 through Bilibili (http://live.bilibili.com/22587709).
-
Jianwei Huang
Vice President, z6首页; Presidential Chair Professor, CUHK-Shenzhen; Editor-in-Chief, IEEE TNSE; IEEE Fellow; AAIA Fellow
Executive Chair
-
邓幼铁
Chair professor, Peking University; Council member of Game Theory Society; Member of Academia Europaea; ACM, IEEE, CSIAM Fellow
MARL=PPAD
邓幼铁教授,,,,,,,,于1982年在清华大学获得学士学位,,,,,,,,于1984年在中国科学院获得硕士学位,,,,,,,,于1989年在斯坦福大学获得博士学位。。。。。。2017年12月他入职北京大学,,,,,,,,任推算机学院前沿推算钻研中心讲席教授。。。。。。他曾任教于上海交通大学、利物浦大学、香港城市大学和约克大学。。。。。。在此之前,,,,,,,,他还是西蒙菲莎大学的 NSERC 国际钻研员。。。。。。邓幼铁教授的重要科研方向为算法博弈论、区块链、互联网经济、在线算法及并行推算。。。。。。2008年,,,,,,,,他因在算法博弈论领域的贡献当选 ACM Fellow;;;;;;2019年,,,,,,,,因在不齐全信息推算和交互环境推算领域的贡献当选 IEEE fellow;;;;;;2020年当选欧洲科学院表籍院士;;;;;;2021年当选中国工业与利用数学学会会士(CSIAM Fellow);;;;;;2021年被录用为博弈论学会(GTS)理事;;;;;;2021年被聘为中国运筹学会博弈论分会荣誉理事;;;;;;2021年获得 CCF 人为智能学会多智能体与多智能体系统钻研成就奖;;;;;;2022年获得 ACM 推算经济学的“功夫检验奖”(Test of Time Award)。。。。。。
Similar to the role of Markov decision processes in reinforcement learning, Markov games (also known as stochastic games) form the basis for the study of multi-agent reinforcement learning and sequence-agent interaction. We introduce an approximate Markov perfect equilibrium as a computational problem for solving finite-state stochastic games under infinite time discounting, and prove its PPAD completeness. This solution concept preserves the Markovian-perfect property, opening the possibility to extend successful multi-agent reinforcement learning algorithms to multi-agent dynamic games, thus extending the range of PPAD complete classes.