DECENTRALIZED LEARNING IN GENERAL-SUM MATRIX GAMES:AN L_(R-I) LAGGING ANCHOR ALGORITHM

XIAOSONG LU; HOWARD M. SCHWARTZ

首页> 外文期刊>International Journal of Innovative Computing Information and Control >DECENTRALIZED LEARNING IN GENERAL-SUM MATRIX GAMES:AN L_(R-I) LAGGING ANCHOR ALGORITHM

【24h】

DECENTRALIZED LEARNING IN GENERAL-SUM MATRIX GAMES:AN L_(R-I) LAGGING ANCHOR ALGORITHM

机译：通用和游戏中的分散学习：L_（R-I）滞后锚算法

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper presents an L_(R-I) lagging anchor algorithm that combines a lagging anchor method with an L_(R-I) learning algorithm. We prove that this decentralized learning algorithm converges in strategies to Nash equilibria in two-player two-action general-sum matrix games. A practical L_(R-I) lagging anchor algorithm is introduced for players to learn their Nash equilibrium strategies in general-sum stochastic games. Simulation results show the performance of the proposed L_(R-I) lagging anchor algorithm in both matrix games and stochastic games.

机译：本文提出了一种L_（R-I）滞后锚算法，该算法将滞后锚方法与L_（R-I）学习算法相结合。我们证明了这种分散式学习算法在两人两动作的一般和矩阵游戏中收敛于Nash均衡策略。介绍了一种实用的L_（R-I）滞后锚算法，供玩家学习广义和随机游戏中的纳什均衡策略。仿真结果表明了所提出的L_（R-I）滞后锚算法在矩阵博弈和随机博弈中的性能。

著录项

来源
《International Journal of Innovative Computing Information and Control》 |2013年第1期|17-32|共16页
作者
XIAOSONG LU; HOWARD M. SCHWARTZ;
展开▼
作者单位

Department of Systems and Computer Engineering Carleton University 1125 Colonel By Drive, Ottawa, ON, Canada;

Department of Systems and Computer Engineering Carleton University 1125 Colonel By Drive, Ottawa, ON, Canada;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
multiagent learning; matrix games; game theory;

机译：多主体学习;矩阵游戏;博弈论;

相似文献

外文文献
中文文献
专利

1. Learning in Two-Player Matrix Games by Policy Gradient Lagging Anchor [J] . Shiyao DING, Toshimitsu USHIO 電子情報通信学会技術研究報告. システム数理と応用. Mathematical Systems Science and its Applications . 2017,第506期

机译：通过策略梯度滞后锚定，在双人矩阵游戏中学习
2. The Lagging Anchor Algorithm: Reinforcement Learning in Two-Player Zero-Sum Games With Imperfect Information [J] . Fredrik A. Dahl Machine Learning . 2002,第1期

机译：滞后锚算法：具有不完善信息的两人零和游戏的强化学习
3. Multi-agent Inverse Reinforcement Learning for Certain General-Sum Stochastic Games [J] . Lin Xiaomin, Adams Stephen C., Beling Peter A. The Journal of Artificial Intelligence Research . 2019,第期

机译：用于某一般性加速游戏的多功能逆钢筋学习
4. Decentralized Learning in Two-Player Zero-Sum Games: A L_(R-I) Lagging Anchor Algorithm [C] . Xiaosong Lu, Howard M. Schwartz American Control Conference . 2011

机译：双人零和游戏中分散学习：一个L_（R-I）滞后锚算法
5. Decentralized algorithms for Nash equilibrium problems-applications to multi-agent network interdiction games and beyond. [D] . Sreekumaran, Harikrishnan. 2015

机译：纳什均衡问题的分散算法-在多主体网络拦截游戏及其他应用中的应用。
6. Changing the Game: Spine Care in the Era of Artificial Intelligence and Deep Learning Algorithms [O] . Karsten Wiechert, Jeffrey C. Wang, Jens R. Chapman 2020

机译：改变游戏规则：人工智能和深度学习算法时代的脊柱护理
7. Actor-Critic Algorithms for Learning Nash Equilibria in N-player General-Sum Games [O] . Prasad, H. L, Prashanth, L. A., Bhatnagar, Shalabh 2015

机译：N-player中学习纳什均衡的演员批评算法一般和游戏

DECENTRALIZED LEARNING IN GENERAL-SUM MATRIX GAMES:AN L_(R-I) LAGGING ANCHOR ALGORITHM

摘要

著录项

相似文献

相关主题

期刊订阅