Learning in repeated stochastic network aggregative games

被引:0
|
作者
Meigs, Emily [1 ]
Parise, Francesca [1 ]
Ozdaglar, Asuman [1 ]
机构
[1] MIT, Lab Informat & Decis Syst, 77 Massachusetts Ave, Cambridge, MA 02139 USA
来源
2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC) | 2019年
基金
瑞士国家科学基金会;
关键词
PUBLIC-GOODS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We consider a repeated network aggregative game where agents are unsure about a parameter that weights their neighbors' actions in their utility function. We consider simple learning dynamics where agents iteratively play their best response, given previous information, and update their estimate of the network weight parameter according to ordinary least squares. We derive a sufficient condition dependent on the network and on the agents' utility function to guarantee that, under these dynamics, the agents' strategies converge almost surely to the full information Nash equilibrium. We illustrate our theoretical results on a local public good game where agents are uncertain about the level of substitutability of their goods.
引用
收藏
页码:6918 / 6923
页数:6
相关论文
共 50 条
  • [1] Distributed No-Regret Learning for Stochastic Aggregative Games over Networks
    Lei, Jinlong
    Yi, Peng
    Li, Li
    2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 7512 - 7519
  • [2] Sensitivity analysis for network aggregative games
    Parise, Francesca
    Ozdaglar, Asuman
    2017 IEEE 56TH ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2017,
  • [3] Exploring selfish reinforcement learning in repeated games with stochastic rewards
    Katja Verbeeck
    Ann Nowé
    Johan Parent
    Karl Tuyls
    Autonomous Agents and Multi-Agent Systems, 2007, 14 : 239 - 269
  • [4] Exploring selfish reinforcement learning in repeated games with stochastic rewards
    Verbeeck, Katja
    Nowe, Ann
    Parent, Johan
    Tuyls, Karl
    AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 2007, 14 (03) : 239 - 269
  • [5] Fast Adaptive Learning in Repeated Stochastic Games by Game Abstraction
    Elidrisi, Mohamed
    Johnson, Nicholas
    Gini, Maria
    Crandall, Jacob
    AAMAS'14: PROCEEDINGS OF THE 2014 INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS & MULTIAGENT SYSTEMS, 2014, : 1141 - 1148
  • [6] Differentially private distributed algorithms for stochastic aggregative games
    Wang, Jimin
    Zhang, Ji-Feng
    He, Xingkang
    AUTOMATICA, 2022, 142
  • [7] Repeated games with stochastic discounting
    Baye, MR
    Jansen, DW
    ECONOMICA, 1996, 63 (252) : 531 - 541
  • [8] Robust Learning for Repeated Stochastic Games via Meta-Gaming
    Crandall, Jacob W.
    PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI), 2015, : 3416 - 3422
  • [9] Network aggregative games: Distributed convergence to Nash equilibria
    Parise, Francesca
    Gentile, Basilio
    Grammatico, Sergio
    Lygeros, John
    2015 54TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2015, : 2295 - 2300
  • [10] Aggregative games
    Corchon, Luis C.
    SERIES-JOURNAL OF THE SPANISH ECONOMIC ASSOCIATION, 2021, 12 (01): : 49 - 71